Arxiv今日论文 | 2025-11-25

本篇博文主要内容为 2025-11-25 从Arxiv.org论文网站获取的最新论文列表，自动更新，按照NLP、CV、ML、AI、IR五个大方向区分，若需要邮件定时接收，请在评论区留下你的邮箱号。

说明：每日论文数据从Arxiv.org获取，每天早上12:00左右定时自动更新。

友情提示: 如何您需要邮箱接收每日论文数据，请在评论处留下你的邮箱。

目录

• 概览
• 自然语言处理CL
• 人工智能AI
• 机器学习LG
• 计算机视觉CV
• 信息检索IR

概览 (2025-11-25)

今日共更新1150篇论文,其中:

• 自然语言处理共114篇(Computation and Language (cs.CL))
• 人工智能共334篇(Artificial Intelligence (cs.AI))
• 计算机视觉共374篇(Computer Vision and Pattern Recognition (cs.CV))
• 机器学习共344篇(Machine Learning (cs.LG))

自然语言处理

[NLP-0] Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration

链接: https://arxiv.org/abs/2511.19417
作者: James Y. Huang,Sheng Zhang,Qianchu Liu,Guanghui Qin,Tinghui Zhu,Tristan Naumann,Muhao Chen,Hoifung Poon
机构: University of Southern California (南加州大学); Microsoft Research (微软研究院); University of California, Davis (加州大学戴维斯分校)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-1] DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

链接: https://arxiv.org/abs/2511.19399
作者: Rulin Shao,Akari Asai,Shannon Zejiang Shen,Hamish Ivison,Varsha Kishore,Jingming Zhuo,Xinran Zhao,Molly Park,Samuel G. Finlayson,David Sontag,Tyler Murray,Sewon Min,Pradeep Dasigi,Luca Soldaini,Faeze Brahman,Wen-tau Yih,Tongshuang Wu,Luke Zettlemoyer,Yoon Kim,Hannaneh Hajishirzi,Pang Wei Koh
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-2] Scalable Parameter-Light Spectral Method for Clustering Short Text Embeddings with a Cohesion-Based Evaluation Metric

链接: https://arxiv.org/abs/2511.19350
作者: Nikita Neveditsin,Pawan Lingras,Vijay Mago
机构: Saint Mary’s University (圣玛丽大学); York University (约克大学)
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-3] Learning to Reason : Training LLM s with GPT -OSS or DeepSeek R1 Reasoning Traces

链接: https://arxiv.org/abs/2511.19333
作者: Shaltiel Shmidman,Asher Fredman,Oleg Sudakov,Meriem Bendris
机构: DICTA; NVIDIA
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-4] Generative Query Expansion with Multilingual LLM s for Cross-Lingual Information Retrieval

链接: https://arxiv.org/abs/2511.19325
作者: Olivia Macmillan-Scott,Roksana Goworek,Eda B. Özyiğit
机构: The Alan Turing Institute (艾伦图灵研究所); University College London (伦敦大学学院); Queen Mary University of London (伦敦玛丽女王大学)
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-5] What Drives Cross-lingual Ranking? Retrieval Approaches with Multilingual Language Models

【速读】： 该论文旨在解决跨语言信息检索（Cross-lingual Information Retrieval, CLIR）中因语言资源差异、书写系统不同以及嵌入模型跨语言语义对齐不足而导致的性能瓶颈问题。其关键解决方案在于系统性评估四类干预策略：文档翻译、多语言密集检索（multilingual dense retrieval）与预训练编码器、词、短语及查询-文档层级的对比学习（contrastive learning），以及交叉编码器重排序（cross-encoder re-ranking）。研究发现，专为CLIR训练的密集检索模型显著优于基于词汇匹配的方法，且无需依赖文档翻译；对比学习能有效缓解语言偏置并提升初始对齐较弱的编码器性能；而重排序效果则高度依赖交叉编码器训练数据的质量。整体表明，应优先采用语义层面的多语言嵌入和针对性的学习对齐方法，而非翻译驱动的流水线，尤其在低资源语言和跨书写系统场景下优势明显。

链接: https://arxiv.org/abs/2511.19324
作者: Roksana Goworek,Olivia Macmillan-Scott,Eda B. Özyiğit
机构: The Alan Turing Institute; Queen Mary University of London (伦敦玛丽女王大学); University College London (伦敦大学学院)
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

Abstract:Cross-lingual information retrieval (CLIR) enables access to multilingual knowledge but remains challenging due to disparities in resources, scripts, and weak cross-lingual semantic alignment in embedding models. Existing pipelines often rely on translation and monolingual retrieval heuristics, which add computational overhead and noise, degrading performance. This work systematically evaluates four intervention types, namely document translation, multilingual dense retrieval with pretrained encoders, contrastive learning at word, phrase, and query-document levels, and cross-encoder re-ranking, across three benchmark datasets. We find that dense retrieval models trained specifically for CLIR consistently outperform lexical matching methods and derive little benefit from document translation. Contrastive learning mitigates language biases and yields substantial improvements for encoders with weak initial alignment, and re-ranking can be effective, but depends on the quality of the cross-encoder training data. Although high-resource languages still dominate overall performance, gains over lexical and document-translated baselines are most pronounced for low-resource and cross-script pairs. These findings indicate that cross-lingual search systems should prioritise semantic multilingual embeddings and targeted learning-based alignment over translation-based pipelines, particularly for cross-script and under-resourced languages.
zh

[NLP-6] MultiBanAbs: A Comprehensive Multi-Domain Bangla Abstractive Text Summarization Dataset

链接: https://arxiv.org/abs/2511.19317
作者: Md. Tanzim Ferdous,Naeem Ahsan Chowdhury,Prithwiraj Bhattacharjee
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-7] PRInTS: Reward Modeling for Long-Horizon Information Seeking

【速读】： 该论文旨在解决大语言模型（Large Language Models, LLMs）在长轨迹多步信息获取任务中表现不佳的问题，特别是如何有效建模工具调用（tool interaction）与工具输出推理（reasoning over tool outputs）等复杂步骤质量维度，并应对长期任务中上下文快速增长带来的挑战。解决方案的关键在于提出一种生成式过程奖励模型（PRInTS），其具备双重能力：一是基于多维步骤质量指标（如工具输出解释性、工具调用信息量）进行密集评分（dense scoring）；二是通过轨迹摘要（trajectory summarization）压缩不断增长的上下文，同时保留用于步骤评估的关键信息。实验证明，结合最佳n抽样（best-of-n sampling）策略时，PRInTS显著提升了开源模型及专用智能体的信息获取能力，性能达到甚至超越前沿模型，且使用更小规模的骨干代理即可实现。

链接: https://arxiv.org/abs/2511.19314
作者: Jaewoo Lee,Archiki Prasad,Justin Chih-Yao Chen,Zaid Khan,Elias Stengel-Eskin,Mohit Bansal
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: 18 pages, code: this https URL

点击查看摘要

Abstract:Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step information-seeking tasks remain challenging for agents backed by language models. While process reward models (PRMs) can guide agents by ranking candidate steps at test-time, existing PRMs, designed for short reasoning with binary judgment, cannot capture richer dimensions of information-seeking steps, such as tool interactions and reasoning over tool outputs, nor handle the rapidly growing context in long-horizon tasks. To address these limitations, we introduce PRInTS, a generative PRM trained with dual capabilities: (1) dense scoring based on the PRM’s reasoning across multiple step quality dimensions (e.g., interpretation of tool outputs, tool call informativeness) and (2) trajectory summarization that compresses the growing context while preserving essential information for step evaluation. Extensive evaluations across FRAMES, GAIA (levels 1-3), and WebWalkerQA (easy-hard) benchmarks on multiple models, along with ablations, reveal that best-of-n sampling with PRInTS enhances information-seeking abilities of open-source models as well as specialized agents, matching or surpassing the performance of frontier models with a much smaller backbone agent and outperforming other strong reward modeling baselines.
zh

[NLP-8] AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning

链接: https://arxiv.org/abs/2511.19304
作者: Jiayi Zhang,Yiran Peng,Fanqi Kong,Yang Cheng,Yifan Wu,Zhaoyang Yu,Jinyu Xiang,Jianhao Ruan,Jinlin Wang,Maojia Song,HongZhang Liu,Xiangru Tang,Bang Liu,Chenglin Wu,Yuyu Luo
机构: The Hong Kong University of Science and Technology (Guangzhou); DeepWisdom; Peking University; Singapore University of Technology and Design; Sydney University; Yale University; Université de Montréal & Mila
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-9] MapFormer: Self-Supervised Learning of Cognitive Maps with Input-Dependent Positional Embeddings

【速读】： 该论文旨在解决当前人工智能系统在跨分布（out-of-distribution, OOD）场景下泛化能力不足的问题，特别是缺乏类似人类和动物所具备的基于认知地图（cognitive map）的灵活适应能力。其解决方案的关键在于提出了一种基于Transformer架构的新模型——MapFormers，通过引入输入依赖的位置编码（input-dependent positional encoding），实现结构关系与内容信息的解耦（structure-content disentanglement），从而在自监督学习框架下从观测数据中自动构建认知地图，并支持并行路径积分（path integration）。这一设计使模型能够有效建模情景记忆（episodic memory, EM）和工作记忆（working memory, WM），并在2D导航等任务中展现出显著优于现有架构的OOD泛化性能。

链接: https://arxiv.org/abs/2511.19279
作者: Victor Rambaud,Salvador Mascarenhas,Yair Lakretz
机构: Institut Jean Nicod; Laboratoire de Sciences Cognitives et Psycholinguistique (LSCP); Département d’Études Cognitives; École Normale Supérieure; EHESS; CNRS; PSL University
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注: 19 pages (29 with appendix), 8 figures

点击查看摘要

Abstract:A cognitive map is an internal model which encodes the abstract relationships among entities in the world, giving humans and animals the flexibility to adapt to new situations, with a strong out-of-distribution (OOD) generalization that current AI systems still do not possess. To bridge this gap, we introduce MapFormers, new architectures based on Transformer models, which can learn cognitive maps from observational data and perform path integration in parallel, in a self-supervised manner. Cognitive maps are learned in the model by disentangling structural relationships in the inputs from their specific content, a property that can be achieved naturally by updating the positional encoding in Transformers with input-dependent matrices. We developed two variants of MapFormers that unify absolute and relative positional encoding to model episodic (EM) and working memory (WM), respectively. We tested MapFormers on several tasks, including a classic 2D navigation task, showing that our models can learn a cognitive map of the underlying space and generalize OOD (e.g., to longer sequences) with near-perfect performance, unlike current architectures. Together, these results demonstrate the superiority of models designed to learn a cognitive map, and the importance of introducing a structural bias for structure-content disentanglement, which can be achieved in Transformers with input-dependent positional encoding. MapFormers have broad applications in both neuroscience and AI, by explaining the neural mechanisms giving rise to cognitive maps, while allowing these relation models to be learned at scale.
zh

[NLP-10] CDLM: Consistency Diffusion Language Models For Faster Sampling

链接: https://arxiv.org/abs/2511.19269
作者: Minseo Kim,Chenfeng Xu,Coleman Hooper,Harman Singh,Ben Athiwaratkun,Ce Zhang,Kurt Keutzer,Amir Gholami
机构: 未知
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注: 18 pages, 6 figures

点击查看摘要

[NLP-11] A Nutrition Multimodal Photoplethysmography Language Model

链接: https://arxiv.org/abs/2511.19260
作者: Kyle Verrier,Achille Nazaret,Joseph Futoma,Andrew C. Miller,Guillermo Sapiro
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 21 pages, 2 figures

点击查看摘要

[NLP-12] In Machina N400: Pinpointing Where a Causal Language Model Detects Semantic Violations

【速读】： 该论文旨在探究Transformer模型如何以及在何处识别句子语义上的异常（即“语义偏离”），以理解其内部表征机制。解决方案的关键在于对模型各层隐藏状态（hidden states）进行系统性分析，并结合两种互补的探测方法：一是使用线性探测器逐层检测语义合理性差异，发现模型在中层（middle blocks）表现出最佳判别能力；二是通过分析异常信息的有效维度变化，揭示出语义违规信号先扩展后压缩的动态过程，表明存在一个从探索到快速整合的转变阶段。这一发现与人类阅读中的心理语言学现象一致，即语义异常通常在句法解析之后才被察觉，支持了模型内部处理流程与人类认知机制的类比。

链接: https://arxiv.org/abs/2511.19232
作者: Christos-Nikolaos Zacharopoulos,Revekka Kyriakoglou
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Accepted at AICS2025

点击查看摘要

Abstract:How and where does a transformer notice that a sentence has gone semantically off the rails? To explore this question, we evaluated the causal language model (phi-2) using a carefully curated corpus, with sentences that concluded plausibly or implausibly. Our analysis focused on the hidden states sampled at each model layer. To investigate how violations are encoded, we utilized two complementary probes. First, we conducted a per-layer detection using a linear probe. Our findings revealed that a simple linear decoder struggled to distinguish between plausible and implausible endings in the lowest third of the model’s layers. However, its accuracy sharply increased in the middle blocks, reaching a peak just before the top layers. Second, we examined the effective dimensionality of the encoded violation. Initially, the violation widens the representational subspace, followed by a collapse after a mid-stack bottleneck. This might indicate an exploratory phase that transitions into rapid consolidation. Taken together, these results contemplate the idea of alignment with classical psycholinguistic findings in human reading, where semantic anomalies are detected only after syntactic resolution, occurring later in the online processing sequence.
zh

[NLP-13] RAVEN: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning EMNLP2025

链接: https://arxiv.org/abs/2511.19168
作者: Deyi Ji,Yuekui Yang,Liqun Liu,Peng Shu,Haiyang Wu,Shaogang Tang,Xudong Chen,Shaoping Ma,Tianrun Chen,Lanyun Zhu
机构: Tencent(腾讯); Tsinghua University (清华大学); Zhejiang University (浙江大学); Nanyang Technological University (南洋理工大学)
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注: EMNLP 2025 (Oral, Industry Track)

点击查看摘要

[NLP-14] Representational Stability of Truth in Large Language Models

【速读】： 该论文旨在解决大语言模型（Large Language Models, LLMs）在内部概率表示中对“真实”“虚假”及“既非真也非假”内容的编码稳定性问题，即这些模型是否能在面对语义扰动时保持对事实判断的一致性。其解决方案的关键在于引入“表征稳定性”（representational stability）这一概念，并通过训练线性探测器（linear probe）来分离真与非真陈述，进而测量在受控标签变更下决策边界的变化幅度。研究发现，不熟悉的真实缺失类陈述（unfamiliar neither statements）比熟悉的虚构类陈述（familiar neither statements）引发更大的边界偏移，表明表征稳定性更多依赖于认知熟悉度（epistemic familiarity）而非语言形式，从而为评估和训练LLMs在语义不确定性下维持一致事实判断提供了新的诊断工具。

链接: https://arxiv.org/abs/2511.19166
作者: Samantha Dies,Courtney Maynard,Germans Savcisens,Tina Eliassi-Rad
机构: Khoury College of Computer Sciences, Northeastern University (东北大学计算机科学学院); Network Science Institute, Northeastern University (东北大学网络科学研究所); Santa Fe Institute (圣达菲研究所)
类目: Computation and Language (cs.CL)
备注: 25 pages, 24 figures

点击查看摘要

Abstract:Large language models (LLMs) are widely used for factual tasks such as “What treats asthma?” or “What is the capital of Latvia?”. However, it remains unclear how stably LLMs encode distinctions between true, false, and neither-true-nor-false content in their internal probabilistic representations. We introduce representational stability as the robustness of an LLM’s veracity representations to perturbations in the operational definition of truth. We assess representational stability by (i) training a linear probe on an LLM’s activations to separate true from not-true statements and (ii) measuring how its learned decision boundary shifts under controlled label changes. Using activations from sixteen open-source models and three factual domains, we compare two types of neither statements. The first are fact-like assertions about entities we believe to be absent from any training data. We call these unfamiliar neither statements. The second are nonfactual claims drawn from well-known fictional contexts. We call these familiar neither statements. The unfamiliar statements induce the largest boundary shifts, producing up to 40% flipped truth judgements in fragile domains (such as word definitions), while familiar fictional statements remain more coherently clustered and yield smaller changes ( \leq 8.2% ). These results suggest that representational stability stems more from epistemic familiarity than from linguistic form. More broadly, our approach provides a diagnostic for auditing and training LLMs to preserve coherent truth assignments under semantic uncertainty, rather than optimizing for output accuracy alone.
zh

[NLP-15] From Pixels to Posts: Retrieval-Augmented Fashion Captioning and Hashtag Generation

【速读】： 该论文旨在解决现有端到端时尚图像描述生成模型在属性保真度（attribute fidelity）和领域泛化能力（domain generalization）方面的不足，尤其是在生成与视觉内容不符或缺乏风格一致性的文本时表现不佳的问题。其解决方案的关键在于提出一种基于检索增强生成（Retrieval-Augmented Generation, RAG）的框架，通过多服装检测（multi-garment detection）、属性推理（attribute reasoning）和大语言模型（Large Language Model, LLM）提示工程相结合的方式，构建一个包含视觉事实证据包（factual evidence pack）的生成流程。该证据包由YOLO检测器定位服装、k-means聚类提取主色调、CLIP-FAISS模块从结构化商品索引中检索面料与性别属性，并结合风格样例共同引导LLM生成具有语义准确性和风格多样性的时尚描述及上下文丰富的标签（hashtag）。实验表明，该方法在属性覆盖率和事实一致性方面显著优于监督基线模型BLIP，展现出更强的可解释性和可扩展性。

链接: https://arxiv.org/abs/2511.19149
作者: Moazzam Umer Gondal,Hamad Ul Qudous,Daniya Siddiqui,Asma Ahmad Farhan
机构: NU (National University); NU (National University)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Submitted to Expert Systems with Applications

点击查看摘要

Abstract:This paper introduces the retrieval-augmented framework for automatic fashion caption and hashtag generation, combining multi-garment detection, attribute reasoning, and Large Language Model (LLM) prompting. The system aims to produce visually grounded, descriptive, and stylistically interesting text for fashion imagery, overcoming the limitations of end-to-end captioners that have problems with attribute fidelity and domain generalization. The pipeline combines a YOLO-based detector for multi-garment localization, k-means clustering for dominant color extraction, and a CLIP-FAISS retrieval module for fabric and gender attribute inference based on a structured product index. These attributes, together with retrieved style examples, create a factual evidence pack that is used to guide an LLM to generate human-like captions and contextually rich hashtags. A fine-tuned BLIP model is used as a supervised baseline model for comparison. Experimental results show that the YOLO detector is able to obtain a mean Average Precision (mAP@0.5) of 0.71 for nine categories of garments. The RAG-LLM pipeline generates expressive attribute-aligned captions and achieves mean attribute coverage of 0.80 with full coverage at the 50% threshold in hashtag generation, whereas BLIP gives higher lexical overlap and lower generalization. The retrieval-augmented approach exhibits better factual grounding, less hallucination, and great potential for scalable deployment in various clothing domains. These results demonstrate the use of retrieval-augmented generation as an effective and interpretable paradigm for automated and visually grounded fashion content generation.
zh

[NLP-16] Eliciting Chain-of-Thought in Base LLM s via Gradient-Based Representation Optimization AAAI2026

链接: https://arxiv.org/abs/2511.19131
作者: Zijian Wang,Yanxiang Ma,Chang Xu
机构: 未知
类目: Computation and Language (cs.CL)
备注: AAAI2026

点击查看摘要

[NLP-17] Emotion-Enhanced Multi-Task Learning with LLM s for Aspect Category Sentiment Analysis

链接: https://arxiv.org/abs/2511.19122
作者: Yaping Chai,Haoran Xie,Joe S. Qin
机构: Lingnan University (岭南大学)
类目: Computation and Language (cs.CL)
备注: 8 pages, 4 figures

点击查看摘要

[NLP-18] On the Optimality of Discrete Object Naming: a Kinship Case Study

链接: https://arxiv.org/abs/2511.19120
作者: Phong Le,Mees Lindeman,Raquel G. Alhama
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-19] A symbolic Perl algorithm for the unification of Nahuatl word spellings

链接: https://arxiv.org/abs/2511.19118
作者: Juan-José Guzmán-Landa,Jesús Vázquez-Osorio,Juan-Manuel Torres-Moreno,Ligia Quintana Torres,Miguel Figueroa-Saavedra,Martha-Lorena Avendaño-Garrido,Graham Ranger,Patricia Velázquez-Morales,Gerardo Eugenio Sierra Martínez
机构: Avignon Université (阿维尼翁大学); Universidad Veracruzana (韦拉克鲁斯大学); Universidad Nacional Autónoma de México (墨西哥国立自治大学)
类目: Computation and Language (cs.CL)
备注: MICAI 2025, LNAI 16221, pp. 141-154, 2026. 10 pages, 4 Figures, 8 Tables

点击查看摘要

[NLP-20] DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF AAAI2026

链接: https://arxiv.org/abs/2511.19097
作者: Ziyuan Gao,Di Liang,Xianjie Wu,Philippe Morel,Minlong Peng
机构: 未知
类目: Computation and Language (cs.CL)
备注: Accepted by AAAI 2026

点击查看摘要

[NLP-21] A Multi-Agent LLM Framework for Multi-Domain Low-Resource In-Context NER via Knowledge Retrieval Disambiguation and Reflective Analysis AAAI2026

链接: https://arxiv.org/abs/2511.19083
作者: Wenxuan Mu,Jinzhong Ning,Di Zhao,Yijia Zhang
机构: 未知
类目: Computation and Language (cs.CL)
备注: This paper has been accepted by AAAI 2026 (Main Technical Track)

点击查看摘要

[NLP-22] GraphMind: Theorem Selection and Conclusion Generation Framework with Dynamic GNN for LLM Reasoning

链接: https://arxiv.org/abs/2511.19078
作者: Yutong Li,Yitian Zhou,Xudong Wang,GuoChen,Caiyan Qin
机构: University of Electronic Science and Technology of China (电子科技大学); School of Robotics and Advanced Manufacture, Harbin Institute of Technology, Shenzhen (哈尔滨工业大学深圳校区机器人与先进制造学院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-23] Logic of Montage

链接: https://arxiv.org/abs/2511.19063
作者: Hayami Takahashi,Kensuke Takahashi
机构: Caché et Wavelet, Inc. (Caché et Wavelet, Inc.); Tokyo University of Science (东京理科大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-24] Understanding and Mitigating Over-refusal for Large Language Models via Safety Representation

链接: https://arxiv.org/abs/2511.19009
作者: Junbo Zhang,Ran Chen,Qianli Zhou,Xinyang Deng,Wen Jiang
机构: Northwestern Polytechnical University (西北工业大学)
类目: Cryptography and Security (cs.CR); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-25] Knowledge-based Graphical Method for Safety Signal Detection in Clinical Trials

链接: https://arxiv.org/abs/2511.18937
作者: Francois Vandenhende,Anna Georgiou,Michalis Georgiou,Theodoros Psaras,Ellie Karekla,Elena Hadjicosta
机构: ClinBAY Limited( ClinBAY 有限公司)
类目: Computation and Language (cs.CL)
备注: 13 pages, 3 tables, 5 figures

点击查看摘要

[NLP-26] SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression

链接: https://arxiv.org/abs/2511.18936
作者: Santhosh G S,Saurav Prakash,Balaraman Ravindran
机构: Indian Institute of Technology Madras (印度理工学院马德拉斯分校)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-27] Skeletons Matter: Dynamic Data Augmentation for Text-to-Query EMNLP2025

链接: https://arxiv.org/abs/2511.18934
作者: Yuchen Ji,Bo Xu,Jie Shi,Jiaqing Liang,Deqing Yang,Yu Mao,Hai Chen,Yanghua Xiao
机构: Fudan University (复旦大学); Donghua University (东华大学); Ant Group (蚂蚁集团); Shanghai Key Laboratory of Data Science (上海市数据科学重点实验室)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Databases (cs.DB)
备注: Accepted at EMNLP 2025

点击查看摘要

[NLP-28] Look It Up: Analysing Internal Web Search Capabilities of Modern LLM s

链接: https://arxiv.org/abs/2511.18931
作者: Sahil Kale
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 10 pages, 8 figures

点击查看摘要

[NLP-29] How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining

链接: https://arxiv.org/abs/2511.18903
作者: Kairong Luo,Zhenbo Sun,Haodong Wen,Xinyu Shi,Jiarui Cui,Chenyi Dang,Kaifeng Lyu,Wenguang Chen
机构: Tsinghua University (清华大学); Peng Cheng Laboratory (鹏城实验室)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-30] Reproducibility Study of Large Language Model Bayesian Optimization ICLR2024

链接: https://arxiv.org/abs/2511.18891
作者: Adam Rychert,Gasper Spagnolo,Evgenii Posashkov
机构: 未知
类目: Computation and Language (cs.CL)
备注: 7 pages, 8 figures. Reproducibility study of the LLAMBO framework (ICLR 2024). Code: this https URL

点击查看摘要

[NLP-31] CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation ACL’25

链接: https://arxiv.org/abs/2511.18889
作者: Jingqian Zhao,Bingbing Wang,Geng Tu,Yice Zhang,Qianlong Wang,Bin Liang,Jing Li,Ruifeng Xu
机构: Harbin Institute of Technology, Shenzhen, China (哈尔滨工业大学深圳校区); Peng Cheng Laboratory, Shenzhen, China (鹏城实验室); Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies (广东省新型安全智能技术重点实验室); The Chinese University of Hong Kong, Hong Kong, China (香港中文大学); The Hong Kong Polytechnic University, Hong Kong, China (香港理工大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: ACL’25

点击查看摘要

[NLP-32] hink Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models

链接: https://arxiv.org/abs/2511.18864
作者: Yang Xiang,Yixin Ji,Juntao Li,Min Zhang
机构: Soochow University (苏州大学)
类目: Computation and Language (cs.CL)
备注: Under Review

点击查看摘要

[NLP-33] Generating Reading Comprehension Exercises with Large Language Models for Educational Applications

链接: https://arxiv.org/abs/2511.18860
作者: Xingyu Huang,Fei Jiang,Jianli Xiao
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-34] FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Models

链接: https://arxiv.org/abs/2511.18852
作者: Masoomali Fatehkia,Enes Altinisik,Husrev Taha Sencar
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-35] Cognitive Alpha Mining via LLM -Driven Code-Based Evolution

链接: https://arxiv.org/abs/2511.18850
作者: Fengyuan Liu,Huang Yi,Sichun Luo,Yuqi Wang,Yazheng Yang,Xinye Li,Zefa Hu,Junlan Feng,Qi Liu
机构: JIUTIAN Research (九天研究院); China Mobile (中国移动); School of Computing and Data Science (计算与数据科学学院); The University of Hong Kong (香港大学); Grace Investment Machine (格蕾丝投资机器)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-36] Large Language Models for the Summarization of Czech Documents: From History to the Present

链接: https://arxiv.org/abs/2511.18848
作者: Václav Tran,Jakub Šmíd,Ladislav Lenc,Jean-Pierre Salmon,Pavel Král
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-37] A Reproducible Framework for Neural Topic Modeling in Focus Group Analysis

链接: https://arxiv.org/abs/2511.18843
作者: Heger Arfaoui,Mohammed Iheb Hergli,Beya Benzina,Slimane BenMiled
机构: National Engineering School of Tunis, University of Tunis El Manar, Tunis, Tunisia; Pasteur Institute of Tunis, University of Tunis El Manar, Tunis, Tunisia; Mediterranean Institute of Technology, South Mediterranean University, Tunis, Tunisia; Faculty of Medicine of Tunis, University of Tunis El Manar, Tunis, Tunisia
类目: Computation and Language (cs.CL); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-38] Concept than Document: Context Compression via AMR-based Conceptual Entropy

链接: https://arxiv.org/abs/2511.18832
作者: Kaize Shi,Xueyao Sun,Xiaohui Tao,Lin Li,Qika Lin,Guandong Xu
机构: University of Southern Queensland (南昆士兰大学); University of Technology Sydney (悉尼科技大学); The Hong Kong Polytechnic University (香港理工大学); Wuhan University of Technology (武汉理工大学); National University of Singapore (新加坡国立大学); The Education University of Hong Kong (香港教育大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-39] Assessing the alignment between infants visual and linguistic experience using multimodal language models

链接: https://arxiv.org/abs/2511.18824
作者: Alvin Wei Ming Tan,Jane Yang,Tarun Sepuri,Khai Loong Aw,Robert Z. Sparks,Zi Yin,Virginia A. Marchman,Michael C. Frank,Bria Long
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-40] HyperbolicRAG : Enhancing Retrieval-Augmented Generation with Hyperbolic Representations

链接: https://arxiv.org/abs/2511.18808
作者: Cao Linxiao,Wang Ruitao,Li Jindong,Zhou Zhipeng,Yang Menglin
机构: Hong Kong University of Science and Technology (Guangzhou) (香港科技大学（广州）); Nanyang Technological University (南洋理工大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 12 pages

点击查看摘要

[NLP-41] Context-Aware Whisper for Arabic ASR Under Linguistic Varieties

链接: https://arxiv.org/abs/2511.18774
作者: Bashar Talafha,Amin Abu Alhassan,Muhammad Abdul-Mageed
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-42] Robust Multimodal Sentiment Analysis with Distribution-Based Feature Recovery and Fusion ACM-MM2024

链接: https://arxiv.org/abs/2511.18751
作者: Daiqing Wu,Dongbao Yang,Can Ma,Yu Zhou
机构: Institute of Information Engineering, Chinese Academy of Sciences (中国科学院信息工程研究所); School of Cyber Security, University of Chinese Academy of Sciences (中国科学院大学网络空间安全学院); TMCC, College of Computer Science, Nankai University (南开大学计算机学院)
类目: Computation and Language (cs.CL)
备注: Accepted by ACM MM 2024

点击查看摘要

[NLP-43] Large Language Models Require Curated Context for Reliable Political Fact-Checking – Even with Reasoning and Web Search

链接: https://arxiv.org/abs/2511.18749
作者: Matthew R. DeVerna,Kai-Cheng Yang,Harry Yaojun Yan,Filippo Menczer
机构: 未知
类目: Computation and Language (cs.CL); Computers and Society (cs.CY); Information Retrieval (cs.IR)
备注:

点击查看摘要

[NLP-44] RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context

链接: https://arxiv.org/abs/2511.18743
作者: Yu Lei,Shuzheng Si,Wei Wang,Yifei Wu,Gang Chen,Fanchao Qi,Maosong Sun
机构: DeepLang AI; Department of Computer Science and Technology, Tsinghua University (清华大学计算机科学与技术系); Beijing University of Posts and Telecommunications (北京邮电大学); Beijing Jiaotong University (北京交通大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-45] Empathetic Cascading Networks: A Multi-Stage Prompting Technique for Reducing Social Biases in Large Language Models

链接: https://arxiv.org/abs/2511.18696
作者: Wangjiaxuan Xin
机构: Sichuan University (四川大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-46] CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning

链接: https://arxiv.org/abs/2511.18659
作者: Jie He,Richard He Bai,Sinead Williamson,Jeff Z. Pan,Navdeep Jaitly,Yizhe Zhang
机构: Apple(苹果公司); University of Edinburgh (爱丁堡大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-47] Evaluating Large Language Models on the 2026 Korean CSAT Mathematics Exam: Measuring Mathematical Ability in a Zero-Data-Leakage Setting

链接: https://arxiv.org/abs/2511.18649
作者: Goun Pyeon,Inbum Heo,Jeesu Jung,Taewook Hwang,Hyuk Namgoong,Hyein Seo,Yerim Han,Eunbin Kim,Hyeonseok Kang,Sangkeun Jung
机构: 未知
类目: Computation and Language (cs.CL)
备注: 52 pages, Korean

点击查看摘要

[NLP-48] No Free Lunch in Language Model Bias Mitigation? Targeted Bias Reduction Can Exacerbate Unmitigated LLM Biases

链接: https://arxiv.org/abs/2511.18635
作者: Shireen Chand,Faith Baca,Emilio Ferrara
机构: University of Southern California (南加州大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注:

点击查看摘要

[NLP-49] Majority of the Bests: Improving Best-of-N via Bootstrapping

链接: https://arxiv.org/abs/2511.18630
作者: Amin Rakhsha,Kanika Madan,Tianyu Zhang,Amir-massoud Farahmand,Amir Khasahmadi
机构: University of Toronto (多伦多大学); Vector Institute (矢量研究所); Autodesk (欧特克); Polytechnique Montréal (蒙特利尔理工学院); Mila - Quebec AI Institute (魁北克人工智能研究所)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Methodology (stat.ME); Machine Learning (stat.ML)
备注:

点击查看摘要

[NLP-50] OpenGloss: A Synthetic Encyclopedic Dictionary and Semantic Knowledge Graph

链接: https://arxiv.org/abs/2511.18622
作者: Michael J. Bommarito II
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 30 pages, 5 figures, 8 tables. Dataset available at this https URL

点击查看摘要

[NLP-51] Prompt Optimization as a State-Space Search Problem

链接: https://arxiv.org/abs/2511.18619
作者: Maanas Taneja
机构: University of Minnesota (明尼苏达大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-52] A Unified BERT-CNN-BiLSTM Framework for Simultaneous Headline Classification and Sentiment Analysis of Bangla News

链接: https://arxiv.org/abs/2511.18618
作者: Mirza Raquib,Munazer Montasir Akash,Tawhid Ahmed,Saydul Akbar Murad,Farida Siddiqi Prity,Mohammad Amzad Hossain,Asif Pervez Polok,Nick Rahimi
机构: International Islamic University Chittagong (国际伊斯兰大学吉大港分校); Noakhali Science and Technology University (诺阿哈尔科技大学); Bangladesh University of Engineering and Technology (孟加拉国工程技术大学); University of Southern Mississippi (南密西西比大学); Netrokona University (内特罗纳大学); NSTU (诺阿哈尔科技大学); mPower Social Enterprise (mPower 社会企业)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-53] A Benchmark for Zero-Shot Belief Inference in Large Language Models

链接: https://arxiv.org/abs/2511.18616
作者: Joseph Malone,Rachith Aiyappa,Byunghwee Lee,Haewoon Kwak,Jisun An,Yong-Yeol Ahn
机构: Center for Complex Networks and Systems Research, Indiana University, Bloomington, IN, USA; School of Data Science, University of Virginia, Charlottesville, VA 22903, USA
类目: Computation and Language (cs.CL)
备注: 28 pages, 5 figures

点击查看摘要

[NLP-54] oward Trustworthy Difficulty Assessments: Large Language Models as Judges in Programming and Synthetic Tasks

链接: https://arxiv.org/abs/2511.18597
作者: H.M. Shadman Tabib,Jaber Ahmed Deedar
机构: Bangladesh University of Engineering and Technology (孟加拉国工程与技术大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-55] Dealing with the Hard Facts of Low-Resource African NLP

链接: https://arxiv.org/abs/2511.18557
作者: Yacouba Diarra,Nouhoum Souleymane Coulibaly,Panga Azazia Kamaté,Madani Amadou Tall,Emmanuel Élisé Koné,Aymane Dembélé,Michael Leventhal
机构: RobotsMali AI4D Lab (RobotsMali AI4D 实验室)
类目: Computation and Language (cs.CL)
备注: 10 pages, 4 figures

点击查看摘要

[NLP-56] From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence

链接: https://arxiv.org/abs/2511.18538
作者: Jian Yang,Wei Zhang,Shark Liu,Jiajun Wu,Shawn Guo,Yizhi Li
机构: Beihang University(北京航空航天大学); M-A-P
类目: oftware Engineering (cs.SE); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-57] For Those Who May Find Themselves on the Red Team

链接: https://arxiv.org/abs/2511.18499
作者: Tyler Shoemaker
机构: Texas A&M University (德克萨斯A&M大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-58] MindEval: Benchmarking Language Models on Multi-turn Mental Health Support

链接: https://arxiv.org/abs/2511.18491
作者: José Pombal,Maya D’Eon,Nuno M. Guerreiro,Pedro Henrique Martins,António Farinhas,Ricardo Rei
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-59] Shadows in the Code: Exploring the Risks and Defenses of LLM -based Multi-Agent Software Development Systems AAAI2026

链接: https://arxiv.org/abs/2511.18467
作者: Xiaoqing Wang,Keman Huang,Bin Liang,Hongyu Li,Xiaoyong Du
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Accepted by AAAI 2026 Alignment Track

点击查看摘要

[NLP-60] General Agent ic Memory Via Deep Research

链接: https://arxiv.org/abs/2511.18423
作者: B.Y. Yan,Chaofan Li,Hongjin Qian,Shuqi Lu,Zheng Liu
机构: Beijing Academy of Artificial Intelligence (北京人工智能研究院); Renmin University of China (中国人民大学); Peking University (北京大学); Hong Kong Polytechnic University (香港理工大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-61] Multi-Agent Collaborative Filtering: Orchestrating Users and Items for Agent ic Recommendations

链接: https://arxiv.org/abs/2511.18413
作者: Yu Xia,Sungchul Kim,Tong Yu,Ryan A. Rossi,Julian McAuely
机构: University of California San Diego (加州大学圣地亚哥分校); Adobe Research (Adobe 研究院)
类目: Computation and Language (cs.CL); Information Retrieval (cs.IR)
备注:

点击查看摘要

[NLP-62] SmolKalam: Ensemble Quality-Filtered Translation at Scale for High Quality Arabic Post-Training Data

链接: https://arxiv.org/abs/2511.18411
作者: Sultan Alrashed,Chadi Helwe,Francesco Orabona
机构: King Abdullah University of Science and Technology (KAUST)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Work in progress

点击查看摘要

[NLP-63] Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models

链接: https://arxiv.org/abs/2511.18409
作者: Dana Arad,Yonatan Belinkov,Hanjie Chen,Najoung Kim,Hosein Mohebbi,Aaron Mueller,Gabriele Sarti,Martin Tutek
机构: Technion – IIT (以色列理工学院); Rice University (莱斯大学); Boston University (波士顿大学); Tilburg University (蒂尔堡大学); University of Groningen (格罗宁根大学); University of Zagreb (萨格勒布大学); Harvard University (哈佛大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-64] owards Robust and Fair Next Visit Diagnosis Prediction under Noisy Clinical Notes with Large Language Models ALT AAAI

链接: https://arxiv.org/abs/2511.18393
作者: Heejoon Koo
机构: 未知
类目: Computation and Language (cs.CL)
备注: Accepted by the Association for the Advancement of Artificial Intelligence (AAAI) 2026 1st Workshop on Safe, Ethical, Certified, Uncertainty-aware, Robust, and Explainable AI for Health (SECURE-AI4H)

点击查看摘要

[NLP-65] u crois que cest vrai ? Diversite des regimes denonciation face aux fake news et mecanismes dautoregulation conversationnelle

链接: https://arxiv.org/abs/2511.18369
作者: Manon Berriche
机构: 未知
类目: Computation and Language (cs.CL); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC); Multimedia (cs.MM)
备注: in French language

点击查看摘要

[NLP-66] OmniStruct: Universal Text-to-Structure Generation across Diverse Schemas

链接: https://arxiv.org/abs/2511.18335
作者: James Y. Huang,Wenxuan Zhou,Nan Xu,Fei Wang,Qin Liu,Sheng Zhang,Hoifung Poon,Muhao Chen
机构: University of Southern California (南加州大学); University of California, Davis (加州大学戴维斯分校); Microsoft Research (微软研究院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-67] Gradient Masters at BLP-2025 Task 1: Advancing Low-Resource NLP for Bengali using Ensemble-Based Adversarial Training for Hate Speech Detection AACL MICRO

链接: https://arxiv.org/abs/2511.18324
作者: Syed Mohaiminul Hoque,Naimur Rahman,Md Sakhawat Hossain
机构: SUST (Sylhet Agricultural University)
类目: Computation and Language (cs.CL)
备注: 6 pages, 2 figures, 4 tables. Accepted at the Second International Workshop on Bangla Language Processing (BLP-2025) co-located with AACL-IJCNLP 2025. Ranked 6th (Subtask 1A, 73.23% micro F1) and 3rd (Subtask 1B, 73.28% micro F1) on the official leaderboard

点击查看摘要

[NLP-68] Path-Constrained Retrieval: A Structural Approach to Reliable LLM Agent Reasoning Through Graph-Scoped Semantic Search

链接: https://arxiv.org/abs/2511.18313
作者: Joseph Oladokun
机构: 未知
类目: Computation and Language (cs.CL); Databases (cs.DB); Information Retrieval (cs.IR); Machine Learning (cs.LG)
备注: 10 pages

点击查看摘要

[NLP-69] able Comprehension in Building Codes using Vision Language Models and Domain-Specific Fine-Tuning

链接: https://arxiv.org/abs/2511.18306
作者: Mohammad Aqib,Mohd Hamza,Ying Hei Chui,Qipei Mei
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-70] “AGI” team at SHROOM-CAP: Data-Centric Approach to Multilingual Hallucination Detection using XLM-RoBERTa AACL

链接: https://arxiv.org/abs/2511.18301
作者: Harsh Rathva,Pruthwik Mishra,Shrikant Malviya
机构: Sardar Vallabhbhai National Institute of Technology (SVNIT) (萨达尔·瓦拉巴伊·国立技术学院)
类目: Computation and Language (cs.CL)
备注: Accepted to the 1st Workshop on Confabulation, Hallucinations Overgeneration in Multilingual and Practical Settings (CHOMPS) at AACL-IJCNLP 2025

点击查看摘要

[NLP-71] From Archives to Decisions: Multi-Agent Pharmaceutical Co-Scientist for Traceable Drug Discovery and Reverse Translation

链接: https://arxiv.org/abs/2511.18259
作者: Xiaochen Zheng,Alvaro Serra,Ilya Schneider Chernov,Maddalena Marchesi,Eunice Musvasva,Tatyana Y. Doktorova
机构: F. Hoffmann-La Roche Ltd. (罗氏有限公司)
类目: Computation and Language (cs.CL); Multiagent Systems (cs.MA)
备注: 22 pages, 4 figures, 3 tables

点击查看摘要

[NLP-72] Agent -as-a-Graph: Knowledge Graph-Based Tool and Agent Retrieval for LLM Agent Retrieval for LLM Multi-Agent Systems

链接: https://arxiv.org/abs/2511.18194
作者: Faheem Nizar,Elias Lumer,Anmol Gulati,Pradeep Honaganahalli Basavaraju,Vamse Kumar Subbiah
机构: PricewaterhouseCoopers(普华永道)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-73] Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agent ic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models

链接: https://arxiv.org/abs/2511.18177
作者: Elias Lumer,Matt Melich,Olivia Zino,Elena Kim,Sara Dieter,Pradeep Honaganahalli Basavaraju,Vamse Kumar Subbiah,James A. Burke,Roberto Hernandez
机构: PricewaterhouseCoopers U.S. (普华永道美国)
类目: Computation and Language (cs.CL)
备注: 8 pages, 2 figures

点击查看摘要

[NLP-74] Vector Arithmetic in Concept and Token Subspaces NEURIPS2025

链接: https://arxiv.org/abs/2511.18162
作者: Sheridan Feucht,Byron Wallace,David Bau
机构: Northeastern University (东北大学)
类目: Computation and Language (cs.CL)
备注: 9 pages, 6 figures. NeurIPS 2025 Mechanistic Interpretability Workshop

点击查看摘要

[NLP-75] GeeSanBhava: Sentiment Tagged Sinhala Music Video Comment Data Set

链接: https://arxiv.org/abs/2511.18146
作者: Yomal De Mel,Nisansa de Silva
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-76] Bias Is a Subspace Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models

链接: https://arxiv.org/abs/2511.18123
作者: Dachuan Zhao,Weiyue Li,Zhenda Shen,Yushu Qiu,Bowen Xu,Haoyu Chen,Yongchao Chen
机构: Harvard University (哈佛大学); MIT (麻省理工学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-77] Comparing Labeled Markov Chains: A Cantor-Kantorovich Approach

链接: https://arxiv.org/abs/2511.18103
作者: Adrien Banse,Alessandro Abate,Raphaël M. Jungers
机构: ICTEAM, UCLouvain (ICTEAM, 鲁汶大学); Department of Computer Science, University of Oxford (计算机科学系，牛津大学); European Research Council (欧洲研究委员会); Horizon Europe programme (地平线欧洲计划); ARC (法国社区)
类目: Logic in Computer Science (cs.LO); Computation and Language (cs.CL); Formal Languages and Automata Theory (cs.FL); Probability (math.PR)
备注:

点击查看摘要

[NLP-78] IE-Critic-R1: Advancing the Explanatory Measurement of Text-Driven Image Editing for Human Perception Alignment

链接: https://arxiv.org/abs/2511.18055
作者: Bowen Qu,Shangkun Sun,Xiaoyu Liang,Wei Gao
机构: Peking University (北京大学); Peng Cheng Laboratory (鹏城实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 18 pages, 10 figures, 8 tables

点击查看摘要

[NLP-79] Blu-WERP (Web Extraction and Refinement Pipeline): A Scalable Pipeline for Preprocessing Large Language Model Datasets

链接: https://arxiv.org/abs/2511.18054
作者: Gowtham,Sai Rupesh,Sanjay Kumar,Saravanan,Venkata Chaithanya
机构: BluBridge Research
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-80] Paper2SysArch: Structure-Constrained System Architecture Generation from Scientific Papers

链接: https://arxiv.org/abs/2511.18036
作者: Ziyi Guo,Zhou Liu,Wentao Zhang
机构: Beijing University of Posts and Telecommunications (北京邮电大学); Peking University (北京大学)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR)
备注:

点击查看摘要

[NLP-81] MTikGuard System: A Transformer-Based Multimodal System for Child-Safe Content Moderation on TikTok ACL

链接: https://arxiv.org/abs/2511.17955
作者: Dat Thanh Nguyen,Nguyen Hung Lam,Anh Hoang-Thi Nguyen,Trong-Hop Do
机构: University of Information Technology (信息科技大学); Vietnam National University, Ho Chi Minh City (胡志明市国家大学)
类目: Computation and Language (cs.CL)
备注: Accepted at PACLIC39

点击查看摘要

[NLP-82] Measuring the Impact of Lexical Training Data Coverag e on Hallucination Detection in Large Language Models

链接: https://arxiv.org/abs/2511.17946
作者: Shuo Zhang,Fabrizio Gotti,Fengran Mo,Jian-Yun Nie
机构: Université de Montréal (蒙特利尔大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-83] SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization

链接: https://arxiv.org/abs/2511.17938
作者: Jianghao Wu,Yasmeen George,Jin Ye,Yicheng Wu,Daniel F. Schmidt,Jianfei Cai
机构: Monash University (莫纳什大学); Imperial College London (帝国理工学院)
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-84] owards Efficient LLM -aware Heterogeneous Graph Learning

链接: https://arxiv.org/abs/2511.17923
作者: Wenda Li,Tongya Zheng,Shunyu Liu,Yu Wang,Kaixuan Chen,Hanyang Yuan,Bingde Hu,Zujie Ren,Mingli Song,Gang Chen
机构: Zhejiang University (浙江大学); Zhejiang Lab; Hangzhou City University (杭州城市大学); Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security (杭州市滨江区区块链与数据安全研究院); Nanyang Technological University (南洋理工大学); Bangsun Technology
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-85] L2V-CoT: Cross-Modal Transfer of Chain-of-Thought Reasoning via Latent Intervention AAAI2026

链接: https://arxiv.org/abs/2511.17910
作者: Yuliang Zhan,Xinyu Tang,Han Wan,Jian Li,Ji-Rong Wen,Hao Sun
机构: 未知
类目: Computation and Language (cs.CL)
备注: AAAI 2026 oral

点击查看摘要

[NLP-86] Principled Context Engineering for RAG : Statistical Guarantees via Conformal Prediction

链接: https://arxiv.org/abs/2511.17908
作者: Debashish Chakraborty,Eugene Yang,Daniel Khashabi,Dawn Lawrie,Kevin Duh
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
备注: Preprint

点击查看摘要

[NLP-87] When Better Teachers Dont Make Better Students: Revisiting Knowledge Distillation for CLIP Models in VQA

链接: https://arxiv.org/abs/2511.17886
作者: Pume Tuchinda,Parinthapat Pengpun,Romrawin Chumpu,Sarana Nutanong,Peerat Limkonchotiwat
机构: VISTEC; Bangkok Christian International School; AI Singapore
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-88] A superpersuasive autonomous policy debating system AAAI2026

链接: https://arxiv.org/abs/2511.17854
作者: Allen Roush,Devin Gonier,John Hines,Judah Goldfeder,Philippe Martin Wyder,Sanjay Basu,Ravid Shwartz Ziv
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA)
备注: Accepted to CLIP workshop at AAAI 2026

点击查看摘要

[NLP-89] Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch

链接: https://arxiv.org/abs/2511.17826
作者: Ziyang Zhang,Xinheng Ding,Jiayi Yuan,Rixin Liu,Huizi Mao,Jiarong Xing,Zirui Liu
机构: 未知
类目: Machine Learning (cs.LG); Computation and Language (cs.CL); Machine Learning (stat.ML)
备注:

点击查看摘要

[NLP-90] Point of Order: Action-Aware LLM Persona Modeling for Realistic Civic Simulation ACL2026

链接: https://arxiv.org/abs/2511.17813
作者: Scott Merrill,Shashank Srivastava
机构: University of North Carolina at Chapel Hill (北卡罗来纳大学教堂山分校)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Sound (cs.SD)
备注: 8 pages (29 pages including appendix), 18 figures. Code and datasets are available at this https URL . Submitted to ACL 2026

点击查看摘要

[NLP-91] PoETa v2: Toward More Robust Evaluation of Large Language Models in Portuguese

链接: https://arxiv.org/abs/2511.17808
作者: Thales Sales Almeida,Rodrigo Nogueira,Hélio Pedrini
机构: Institute of Computing, University of Campinas (UNICAMP); School of Electrical and Computer Engineering, University of Campinas (UNICAMP); Maritaca AI
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-92] Computational frame analysis revisited: On LLM s for studying news coverag e

链接: https://arxiv.org/abs/2511.17746
作者: Sharaj Kunjar,Alyssa Hasegawa Smith,Tyler R Mckenzie,Rushali Mohbe,Samuel V Scarpino,Brooke Foucault Welles
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-93] DeepCoT: Deep Continual Transformers for Real-Time Inference on Data Streams

链接: https://arxiv.org/abs/2511.17693
作者: Ginés Carreto Picón,Peng Yuan Zhou,Qi Zhang,Alexandros Iosifidis
机构: 未知
类目: Machine Learning (cs.LG); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
备注: 13 pages, 5 figures

点击查看摘要

[NLP-94] A Cross-Cultural Assessment of Human Ability to Detect LLM -Generated Fake News about South Africa

链接: https://arxiv.org/abs/2511.17682
作者: Tim Schlippe,Matthias Wölfel,Koena Ronny Mabokela
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-95] LLM and Agent -Driven Data Analysis: A Systematic Approach for Enterprise Applications and System-level Deployment

链接: https://arxiv.org/abs/2511.17676
作者: Xi Wang,Xianyao Ling,Kun Li,Gang Yin,Liang Zhang,Jiang Wu,Annie Wang,Weizhe Wang
机构: 未知
类目: Databases (cs.DB); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-96] Bridging Symbolic Control and Neural Reasoning in LLM Agents : The Structured Cognitive Loop

链接: https://arxiv.org/abs/2511.17673
作者: Myung Ho Kim
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 27 pages

点击查看摘要

[NLP-97] MURMUR: Using cross-user chatter to break collaborative language agents in groups

链接: https://arxiv.org/abs/2511.17671
作者: Atharv Singh Patlan,Peiyao Sheng,S. Ashwin Hebbar,Prateek Mittal,Pramod Viswanath
机构: Princeton University (普林斯顿大学); Sentient
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 20 pages, 7 figures

点击查看摘要

[NLP-98] PocketLLM : Ultimate Compression of Large Language Models via Meta Networks AAAI2026

链接: https://arxiv.org/abs/2511.17637
作者: Ye Tian,Chengcheng Wang,Jing Han,Yehui Tang,Kai Han
机构: 未知
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注: AAAI 2026 camera ready

点击查看摘要

[NLP-99] From Competition to Coordination: Market Making as a Scalable Framework for Safe and Aligned Multi-Agent LLM Systems

链接: https://arxiv.org/abs/2511.17621
作者: Brendan Gho,Suman Muppavarapu,Afnan Shaik,Tyson Tsay,James Begin,Kevin Zhu,Archana Vaidheeswaran,Vasu Sharma
机构: Algoverse AI Research
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-100] Robustness of Structured Data Extraction from Perspectively Distorted Documents

链接: https://arxiv.org/abs/2511.17607
作者: Hyakka Nakada,Yoshiyasu Tanaka
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: 8 pages, 12 figures

点击查看摘要

[NLP-101] Llamazip: Leverag ing LLaMA for Lossless Text Compression and Training Dataset Detection

链接: https://arxiv.org/abs/2511.17589
作者: Sören Dréano,Derek Molloy,Noel Murphy
机构: Dublin City University (都柏林城市大学)
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-102] Efficient Mathematical Reasoning Models via Dynamic Pruning and Knowledge Distillation

链接: https://arxiv.org/abs/2511.17577
作者: Fengming Yu,Qingyu Meng,Haiwei Pan,Kejia Zhang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 12 pages, 1 figure

点击查看摘要

[NLP-103] Random Text Zipfs Law Critical Lengthand Implications for Large Language Models

链接: https://arxiv.org/abs/2511.17575
作者: Vladimir Berman
机构: 未知
类目: Computation and Language (cs.CL); Methodology (stat.ME); Machine Learning (stat.ML); Other Statistics (stat.OT)
备注:

点击查看摘要

[NLP-104] Community-Aligned Behavior Under Uncertainty: Evidence of Epistemic Stance Transfer in LLM s

链接: https://arxiv.org/abs/2511.17572
作者: Patrick Gerard,Aiden Chang,Svitlana Volkova
机构: 未知
类目: Computation and Language (cs.CL); Social and Information Networks (cs.SI)
备注: 37 pages, EurIPS 2025

点击查看摘要

[NLP-105] Generative Caching for Structurally Similar Prompts and Responses

链接: https://arxiv.org/abs/2511.17565
作者: Sarthak Chakraborty,Suman Nath,Xuchao Zhang,Chetan Bansal,Indranil Gupta
机构: University of Illinois at Urbana-Champaign (伊利诺伊大学厄巴纳-香槟分校); Microsoft Research (微软研究院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-106] ChineseErrorCorrector3-4B: State-of-the-Art Chinese Spelling and Grammar Corrector

链接: https://arxiv.org/abs/2511.17562
作者: Wei Tian,YuhaoZhou
机构: East China Normal University (华东师范大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-107] LexInstructEval: Lexical Instruction Following Evaluation for Large Language Models

链接: https://arxiv.org/abs/2511.17561
作者: Huimin Ren,Yan Liang,Baiqiao Su,Chaobo Sun,Hengtong Lu,Kaike Zhang,Chen Wei
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-108] A3: Attention-Aware Accurate KV Cache Fusion for Fast Large Language Model Serving

链接: https://arxiv.org/abs/2511.17560
作者: Yuechi Zhou,Yi Su,Jianxin Zhang,Juntao Li,Qingrong Xia,Zhefeng Wang,Xinyu Duan,Baoxing Huai
机构: 1. University of Science and Technology of China (中国科学技术大学); 2. Alibaba Group (阿里巴巴集团)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-109] SCARE: A Benchmark for SQL Correction and Question Answerability Classification for Reliable EHR Question Answering ML4H2025

链接: https://arxiv.org/abs/2511.17559
作者: Gyubok Lee,Woosog Chay,Edward Choi
机构: Korea Advanced Institute of Science & Technology (韩国科学技术院)
类目: Computation and Language (cs.CL); Databases (cs.DB)
备注: ML4H 2025 Proceedings

点击查看摘要

[NLP-110] Beyond the Rubric: Cultural Misalignment in LLM Benchmarks for Sexual and Reproductive Health ALT

链接: https://arxiv.org/abs/2511.17554
作者: Sumon Kanti Dey,Manvi S,Zeel Mehta,Meet Shah,Unnati Agrawal,Suhani Jalota,Azra Ismail
机构: Emory University (埃默里大学); Stanford University (斯坦福大学); Myna Mahila Foundation (迈娜女性基金会)
类目: Computers and Society (cs.CY); Computation and Language (cs.CL)
备注: this https URL

点击查看摘要

[NLP-111] Practical Machine Learning for Aphasic Discourse Analysis

链接: https://arxiv.org/abs/2511.17553
作者: Jason M. Pittman,Anton Phillips Jr.,Yesenia Medina-Santos,Brielle C. Stark
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 14 pages, 4 tables, 2 figures

点击查看摘要

[NLP-112] Classification EM-PCA for clustering and embedding

链接: https://arxiv.org/abs/2511.18992
作者: Zineddine Tighidet,Lazhar Labiod,Mohamed Nadif
机构: 未知
类目: Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: Accepted at the IEEE conference on Big Data (Special Session on Machine Learning)

点击查看摘要

[NLP-113] InstructAudio: Unified speech and music generation with natural language instruction

链接: https://arxiv.org/abs/2511.18487
作者: Chunyu Qiang,Kang Yin,Xiaopeng Wang,Yuzhe Liang,Jiahui Zhao,Ruibo Fu,Tianrui Wang,Cheng Gong,Chen Zhang,Longbiao Wang,Jianwu Dang
机构: 未知
类目: Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Sound (cs.SD)
备注:

点击查看摘要

计算机视觉

[CV-0] LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context

链接: https://arxiv.org/abs/2511.19437
作者: Jingzhi Bao,Hongze Chen,Lingting Zhu,Chenyu Liu,Runze Zhang,Keyang Luo,Zeyu Hu,Weikai Chen,Yingda Yin,Xin Wang,Zehong Lin,Jun Zhang,Xiaoguang Han
机构: CUHK(SZ)(香港中文大学（深圳）); HKUST(香港科技大学); HKU(香港大学); PKU(北京大学); LIGHTSPEED
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-1] VDC-Agent : When Video Detailed Captioners Evolve Themselves via Agent ic Self-Reflection

链接: https://arxiv.org/abs/2511.19436
作者: Qiang Wang,Xinyuan Gao,SongLin Dong,Jizhou Han,Jiangyang Li,Yuhang He,Yihong Gong
机构: Xi’an Jiaotong University (西安交通大学); Kuaishou Technology (快手科技); Shenzhen University of Advanced Technology (深圳先进技术研究院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multimedia (cs.MM)
备注:

点击查看摘要

[CV-2] Are Image-to-Video Models Good Zero-Shot Image Editors?

链接: https://arxiv.org/abs/2511.19435
作者: Zechuan Zhang,Zhenyuan Chen,Zongxin Yang,Yi Yang
机构: Zhejiang University (浙江大学); Harvard University (哈佛大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: technical report

点击查看摘要

[CV-3] Breaking the Likelihood-Quality Trade-off in Diffusion Models by Merging Pretrained Experts ICLR2025

链接: https://arxiv.org/abs/2511.19434
作者: Yasin Esfandiari,Stefan Bauer,Sebastian U. Stich,Andrea Dittadi
机构: Saarland University (萨尔兰大学); Helmholtz AI; Technical University of Munich (慕尼黑工业大学); CISPA Helmholtz Center for Information Security (信息安全赫尔姆霍兹中心); MPI for Intelligent Systems, Tübingen (图宾根马克斯普朗克智能系统研究所)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Machine Learning (stat.ML)
备注: ICLR 2025 DeLTa workshop

点击查看摘要

[CV-4] Mixture of Horizons in Action Chunking

链接: https://arxiv.org/abs/2511.19433
作者: Dong Jing,Gang Wang,Jiaqi Liu,Weiliang Tang,Zelong Sun,Yunchao Yao,Zhenyu Wei,Yunhui Liu,Zhiwu Lu,Mingyu Ding
机构: RUC(中国人民大学); UNC(北卡罗来纳大学); CUHK(香港中文大学)
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: 15 pages, 14 figures

点击查看摘要

[CV-5] Cloud4D NEURIPS2025

链接: https://arxiv.org/abs/2511.19431
作者: Jacob Lin,Edward Gryspeerdt,Ronald Clark
机构: University of Oxford (牛津大学); Imperial College London (帝国理工学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Atmospheric and Oceanic Physics (physics.ao-ph)
备注: NeurIPS 2025 Spotlight, project page: this https URL

点击查看摘要

[CV-6] Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution AAAI2026

链接: https://arxiv.org/abs/2511.19430
作者: Dingkang Liang,Cheng Zhang,Xiaopeng Xu,Jianzhong Ju,Zhenbo Luo,Xiang Bai
机构: 1. Institute of Automation, Chinese Academy of Sciences (中国科学院自动化研究所); 2. School of Information Science and Technology, Sun Yat-sen University (中山大学信息科学与技术学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to AAAI 2026 (Oral). The code is available at \url{ this https URL }

点击查看摘要

[CV-7] Flow Map Distillation Without Data

链接: https://arxiv.org/abs/2511.19428
作者: Shangyuan Tong,Nanye Ma,Saining Xie,Tommi Jaakkola
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-8] Ref-SAM3D: Bridging SAM3D with Text for Reference 3D Reconstruction

【速读】：该论文旨在解决SAM3D在3D物体重建中无法根据文本描述进行特定对象重建的问题，这一局限性制约了其在3D编辑、游戏开发和虚拟环境等实际应用场景中的使用。解决方案的关键在于提出Ref-SAM3D，通过引入文本描述作为高层先验信息，实现仅依赖单张RGB图像和自然语言提示即可完成文本引导的3D重建，从而有效弥合2D视觉线索与3D几何理解之间的鸿沟。

链接: https://arxiv.org/abs/2511.19426
作者: Yun Zhou,Yaoting Wang,Guangquan Jie,Jinyu Liu,Henghui Ding
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Code: this https URL

点击查看摘要

Abstract:SAM3D has garnered widespread attention for its strong 3D object reconstruction capabilities. However, a key limitation remains: SAM3D cannot reconstruct specific objects referred to by textual descriptions, a capability that is essential for practical applications such as 3D editing, game development, and virtual environments. To address this gap, we introduce Ref-SAM3D, a simple yet effective extension to SAM3D that incorporates textual descriptions as a high-level prior, enabling text-guided 3D reconstruction from a single RGB image. Through extensive qualitative experiments, we show that Ref-SAM3D, guided only by natural language and a single 2D view, delivers competitive and high-fidelity zero-shot reconstruction performance. Our results demonstrate that Ref-SAM3D effectively bridges the gap between 2D visual cues and 3D geometric understanding, offering a more flexible and accessible paradigm for reference-guided 3D reconstruction. Code is available at: this https URL.
zh

[CV-9] SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation Shadow Detection and Medical Image Segmentation

链接: https://arxiv.org/abs/2511.19425
作者: Tianrun Chen,Runlong Cao,Xinda Yu,Lanyun Zhu,Chaotao Ding,Deyi Ji,Cheng Chen,Qi Zhu,Chunyan Xu,Papa Mao,Ying Zang
机构: KOKONI, Moxin (Huzhou) Tech. Co., LTD(科科尼，湖州科技有限公司); Zhejiang University(浙江大学); Nanjing University of Science and Technology(南京理工大学); Huzhou University(湖州大学); Nanyang Technological University(南洋理工大学); University of Science and Technology of China(中国科学技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-10] Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens

链接: https://arxiv.org/abs/2511.19418
作者: Yiming Qin,Bomin Wei,Jiaxin Ge,Konstantinos Kallidromitis,Stephanie Fu,Trevor Darrell,Xudong Wang
机构: UC Berkeley (加州大学伯克利分校); UCLA (加州大学洛杉矶分校); Panasonic AI Research (松下人工智能研究院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Project page: this https URL

点击查看摘要

[CV-11] UniGame: Turning a Unified Multimodal Model Into Its Own Adversary

链接: https://arxiv.org/abs/2511.19413
作者: Zhaolong Su,Wang Lu,Hao Chen,Sharon Li,Jindong Wang
机构: William & Mary (威廉玛丽学院); Independent Researcher (独立研究员); Carnegie Mellon University (卡内基梅隆大学); University of Wisconsin–Madison (威斯康星大学麦迪逊分校)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-12] In-Video Instructions: Visual Signals as Generative Control

链接: https://arxiv.org/abs/2511.19401
作者: Gongfan Fang,Xinyin Ma,Xinchao Wang
机构: National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-13] Real-Time Object Tracking with On-Device Deep Learning for Adaptive Beamforming in Dynamic Acoustic Environments

链接: https://arxiv.org/abs/2511.19396
作者: Jorge Ortigoso-Narro,Jose A. Belloch,Adrian Amor-Martin,Sandra Roger,Maximo Cobos
机构: 未知
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-14] BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation

链接: https://arxiv.org/abs/2511.19394
作者: Rachit Saluja,Asli Cihangir,Ruining Deng,Johannes C. Paetzold,Fengbei Liu,Mert R. Sabuncu
机构: Cornell University (康奈尔大学); Cornell Tech (康奈尔科技); Weill Cornell Medicine (威尔康奈尔医学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-15] UISearch: Graph-Based Embeddings for Multimodal Enterprise UI Screenshots Retrieval

链接: https://arxiv.org/abs/2511.19380
作者: Maroun Ayli,Youssef Bakouny,Tushar Sharma,Nader Jalloul,Hani Seifeddine,Rima Kilany
机构: Saint Joseph University of Beirut (贝鲁特圣约瑟夫大学); Dalhousie University (达尔豪斯大学); Murex (穆雷克斯)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 12 pages, 2 figures, 3 algorithms, 4 tables

点击查看摘要

[CV-16] An Anatomy Aware Hybrid Deep Learning Framework for Lung Cancer Tumor Stage Classification

【速读】：该论文旨在解决肺癌肿瘤分期（tumor staging）在端到端深度学习方法中因忽视空间和解剖信息而导致的准确性不足问题。传统模型将分期视为纯图像分类任务，忽略了肿瘤大小及其与邻近解剖结构距离等关键定量指标，而这些因素对分期结果具有决定性影响。解决方案的关键在于提出一种医学导向的混合流程：首先利用专用的编码器-解码器网络精确分割肺部及相邻结构（包括肺叶、肿瘤、纵隔和膈肌），进而通过量化分析分割掩膜提取肿瘤最大直径及与邻近解剖结构的距离，最后依据临床指南应用规则化分期策略。该方法不仅实现了91.36%的整体分类准确率，还首次将显式的临床语境嵌入到肿瘤分期中，显著提升了模型的可解释性和决策透明度。

链接: https://arxiv.org/abs/2511.19367
作者: Saniah Kayenat Chowdhury,Rusab Sarmun,Muhammad E. H. Chowdhury,Sohaib Bassam Zoghoul,Israa Al-Hashimi,Adam Mushtak,Amith Khandakar
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

Abstract:Accurate lung cancer tumor staging is crucial for prognosis and treatment planning. However, it remains challenging for end-to-end deep learning approaches, as such approaches often overlook spatial and anatomical information that are central to the tumor-node-metastasis system. The tumor stage depends on multiple quantitative criteria, including the tumor size and its proximity to the nearest anatomical structures, and small variations can alter the staging outcome. We propose a medically grounded hybrid pipeline that performs staging by explicitly measuring the tumor’s size and distance properties rather than treating it as a pure image classification task. Our method employs specialized encoder-decoder networks to precisely segment the lung and adjacent anatomy, including the lobes, tumor, mediastinum, and diaphragm. Subsequently, we extract the necessary tumor properties, i.e. measure the largest tumor dimension and calculate the distance between the tumor and neighboring anatomical structures by a quantitative analysis of the segmentation masks. Finally, we apply rule-based tumor staging aligned with the medical guidelines. This novel framework has been evaluated on the Lung-PET-CT-Dx dataset, demonstrating superior performance compared to traditional deep learning models, achieving an overall classification accuracy of 91.36%. We report the per-stage F1-scores of 0.93 (T1), 0.89 (T2), 0.96 (T3), and 0.90 (T4), a critical evaluation aspect often omitted in prior literature. To our knowledge, this is the first study that embeds explicit clinical context into tumor stage classification. Unlike standard convolutional neural networks that operate in an uninterpretable “black box” manner, our method offers both state-of-the-art performance and transparent decision support.
zh

[CV-17] DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation

链接: https://arxiv.org/abs/2511.19365
作者: Zehong Ma,Longhui Wei,Shuai Wang,Shiliang Zhang,Qi Tian
机构: Peking University (北京大学); Nanjing University (南京大学); Huawei Inc. (华为公司)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Project Page: this https URL . Code Repository: this https URL

点击查看摘要

[CV-18] Growing with the Generator: Self-paced GRPO for Video Generation

链接: https://arxiv.org/abs/2511.19356
作者: Rui Li,Yuanzhi Liang,Ziqi Ni,Haibing Huang,Chi Zhang,Xuelong Li
机构: University of Science and Technology of China (中国科学技术大学); Southeast University (东南大学); Institute of Artificial Intelligence (TeleAI), China Telecom (中国电信人工智能研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-19] CellFMCount: A Fluorescence Microscopy Dataset Benchmark and Methods for Cell Counting ICDM

链接: https://arxiv.org/abs/2511.19351
作者: Abdurahman Ali Mohammed,Catherine Fonder,Ying Wei,Wallapak Tavanapong,Donald S Sakaguchi,Qi Li,Surya K. Mallapragada
机构: Iowa State University (爱荷华州立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: The IEEE International Conference on Data Mining (ICDM) 2025

点击查看摘要

[CV-20] Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception Reasoning

链接: https://arxiv.org/abs/2511.19343
作者: Qihan Huang,Haofei Zhang,Rong Wei,Yi Wang,Rui Tang,Mingli Song,Jie Song
机构: Zhejiang University (浙江大学); Manycore Tech Inc.
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-21] POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse

链接: https://arxiv.org/abs/2511.19339
作者: Anjie Le,Can Peng,Yuyuan Liu,J. Alison Noble
机构: University of Oxford (牛津大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-22] MonoMSK: Monocular 3D Musculoskeletal Dynamics Estimation

链接: https://arxiv.org/abs/2511.19326
作者: Farnoosh Koleini,Hongfei Xue,Ahmed Helmy,Pu Wang
机构: University of North Carolina at Charlotte (北卡罗来纳大学夏洛特分校)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-23] SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation

【速读】：该论文旨在解决人类图像动画中“首帧身份保持”与“精确运动控制”之间的矛盾问题，尤其针对主流参考到视频（Reference-to-Video, R2V）范式在实际应用中因时空错位导致的身份漂移（identity drift）和视觉伪影（visual artifacts）问题。其解决方案的关键在于提出一种基于图像到视频（Image-to-Video, I2V）范式的框架 SteadyDancer，通过三个核心技术实现：1）条件 reconcilation 机制（Condition-Reconciliation Mechanism），用于调和身份与运动控制之间的冲突，确保高保真度的同时实现精准控制；2）协同姿态调制模块（Synergistic Pose Modulation Modules），生成与参考图像高度兼容的自适应姿态表示；3）分阶段解耦目标训练流程（Staged Decoupled-Objective Training Pipeline），分层优化模型在运动保真度、视觉质量和时序一致性上的表现。该方案首次实现了首帧身份的鲁棒性保障，并在性能与资源消耗上优于现有方法。

链接: https://arxiv.org/abs/2511.19320
作者: Jiaming Zhang,Shengming Cao,Rui Li,Xiaotong Zhao,Yutao Cui,Xinglin Hou,Gangshan Wu,Haolan Chen,Yu Xu,Limin Wang,Kai Ma
机构: Nanjing University (南京大学); Tencent (腾讯); Shanghai AI Lab (上海人工智能实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, with supp

点击查看摘要

Abstract:Preserving first-frame identity while ensuring precise motion control is a fundamental challenge in human image animation. The Image-to-Motion Binding process of the dominant Reference-to-Video (R2V) paradigm overlooks critical spatio-temporal misalignments common in real-world applications, leading to failures such as identity drift and visual artifacts. We introduce SteadyDancer, an Image-to-Video (I2V) paradigm-based framework that achieves harmonized and coherent animation and is the first to ensure first-frame preservation robustly. Firstly, we propose a Condition-Reconciliation Mechanism to harmonize the two conflicting conditions, enabling precise control without sacrificing fidelity. Secondly, we design Synergistic Pose Modulation Modules to generate an adaptive and coherent pose representation that is highly compatible with the reference image. Finally, we employ a Staged Decoupled-Objective Training Pipeline that hierarchically optimizes the model for motion fidelity, visual quality, and temporal coherence. Experiments demonstrate that SteadyDancer achieves state-of-the-art performance in both appearance fidelity and motion control, while requiring significantly fewer training resources than comparable methods.
zh

[CV-24] SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesis

链接: https://arxiv.org/abs/2511.19319
作者: Lingwei Dang,Zonghan Li,Juntong Li,Hongwen Zhang,Liang An,Yebin Liu,Qingyao Wu
机构: South China University of Technology (华南理工大学); Beijing Normal University (北京师范大学); Tsinghua University (清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project Page: this https URL

点击查看摘要

[CV-25] Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach

链接: https://arxiv.org/abs/2511.19316
作者: Xincheng Wang,Hanchi Sun,Wenjun Sun,Kejun Xue,Wangqiu Zhou,Jianbo Zhang,Wei Sun,Dandan Zhu,Xiongkuo Min,Jun Jia,Zhijun Fang
机构: Donghua University (东华大学); Shanghai JiaoTong University (上海交通大学); Xidian University (西安电子科技大学); Hefei University of Technology (合肥工业大学); East China Normal University (华东师范大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-26] Dual-Granularity Semantic Prompting for Language Guidance Infrared Small Target Detection

链接: https://arxiv.org/abs/2511.19306
作者: Zixuan Wang,Haoran Sun,Jiaming Lu,Wenxuan Wang,Zhongling Huang,Dingwen Zhang,Xuelin Qian,Junwei Han
机构: School of Automation, Northwestern Polytechnical University (西北工业大学自动化学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 2 figures

点击查看摘要

[CV-27] IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection

链接: https://arxiv.org/abs/2511.19301
作者: Johannes Meier,Florian Günther,Riccardo Marin,Oussema Dhaouadi,Jacques Kaiser,Daniel Cremers
机构: Technical University of Munich (慕尼黑工业大学); Ludwig-Maximilians-Universität München (慕尼黑大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-28] DensifyBeforehand: LiDAR-assisted Content-aware Densification for Efficient and Quality 3D Gaussian Splatting

链接: https://arxiv.org/abs/2511.19294
作者: Phurtivilai Patt,Leyang Huang,Yinqiang Zhang,Yang Lei
机构: The University of Hong Kong (香港大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-29] ReMatch: Boosting Representation through Matching for Multimodal Retrieval

链接: https://arxiv.org/abs/2511.19278
作者: Qianying Liu,Xiao Liang,Zhiqiang Zhang,Yibo Chen,Xu Tang,Zhongfei Qing,Fengfan Zhou,Yao Hu,Paul Henderson
机构: University of Glasgow (格拉斯哥大学); Xiaohongshu Inc. (小红书公司); Huazhong University of Science and Technology (华中科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-30] Diffusion Reconstruction-based Data Likelihood Estimation for Core-Set Selection AAAI2026

链接: https://arxiv.org/abs/2511.19274
作者: Mingyang Chen,Jiawei Du,Bo Huang,Yi Wang,Xiaobo Zhang,Wei Wang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by AAAI 2026

点击查看摘要

[CV-31] BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment

链接: https://arxiv.org/abs/2511.19268
作者: Dewei Zhou,Mingwei Li,Zongxin Yang,Yu Lu,Yunqiu Xu,Zhizhong Wang,Zeyi Huang,Yi Yang
机构: Zhejiang University (浙江大学); Harvard University (哈佛大学); Huawei Technologies Ltd. (华为技术有限公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 29 pages

点击查看摘要

[CV-32] LAST: LeArning to Think in Space and Time for Generalist Vision-Language Models

【速读】：该论文旨在解决当前视觉语言模型（Vision-Language Models, VLMs）在理解三维空间（3D space）和长视频（long videos）方面表现不足的问题，尽管它们在典型视觉语言任务中已具备较强能力。现有方法通常依赖于针对3D任务或视频理解任务分别设计的专用架构，难以实现统一建模。解决方案的关键在于提出LAST（LeArn to Think in Space and Time），通过引入“空间-时间视觉思维轨迹”机制，使VLMs在生成最终答案前，基于输入的2D图像自主构建跨空间维度和时间维度的视觉推理路径，从而增强对复杂场景结构与动态变化的理解能力。该方法无需额外的专用网络结构，在零样本提示和微调两种场景下均显著提升多个基准测试性能，验证了其有效性与通用性。

链接: https://arxiv.org/abs/2511.19261
作者: Shuai Wang,Daoan Zhang,Tianyi Bai,Shitong Shao,Jiebo Luo,Jiaheng Wei
机构: HKUST(GZ)(香港科技大学（广州）); University of Rochester(罗切斯特大学); HKUST(香港科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

Abstract:Humans can perceive and understand 3D space and long videos from sequential visual observations. But do vision-language models (VLMs) can? Recent work demonstrates that even state-of-the-art VLMs still struggle to understand 3D space and long videos, although they are powerful in typical vision-language tasks. Current methods often rely on specialized architectural designs to improve performance for 3D tasks and video understanding tasks separately. In contrast, we propose LAST, short for LeArn to Think in Space and Time, to jointly improve 3D spatial and long video understanding for general VLMs with only a set of 2D images as inputs. LAST makes VLMs think in space and time rather than only with text before giving the final answer, building visual thinking trajectories in 3D space and temporal dimension. We demonstrate the effectiveness of LAST in two scenarios: 1) zero-shot, where we directly prompt proprietary models; and 2) fine-tuning general VLMs with data that include thinking trajectories in 3D space and time. We show that LAST brings substantial gains in various benchmarks, including 3 spatial understanding, 4 video understanding, and 3 image understanding tasks. Notably, 15.8% gains on EgoSchema with GPT-4o in a zero-shot manner and 8.3 gains on VSI-Bench compared with Qwen2.5-VL-7B.
zh

[CV-33] Adversarial Patch Attacks on Vision-Based Cargo Occupancy Estimation via Differentiable 3D Simulation

【速读】：该论文旨在解决物流场景中基于计算机视觉的货厢占用率估计系统在面对物理空间中的对抗攻击时的安全性问题，特别是针对可打印并放置于货厢内表面的对抗补丁（adversarial patches）的有效性进行研究。解决方案的关键在于利用基于可微分渲染的全仿真3D环境（Mitsuba 3），对补丁纹理进行优化，以适应几何、光照和视角的变化，从而实现比传统2D合成基线更高的攻击成功率，尤其在“拒绝服务”类攻击（将实际满载误判为空载）中达到84.94%的成功率，验证了物理现实条件下对抗补丁对自动化物流流程构成实质性威胁。

链接: https://arxiv.org/abs/2511.19254
作者: Mohamed Rissal Hedna,Sesugh Samuel Nder
机构: University of Hamburg (汉堡大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 9 pages, 5 figures, 1 algorithm

点击查看摘要

Abstract:Computer vision systems are increasingly adopted in modern logistics operations, including the estimation of trailer occupancy for planning, routing, and billing. Although effective, such systems may be vulnerable to physical adversarial attacks, particularly adversarial patches that can be printed and placed on interior surfaces. In this work, we study the feasibility of such attacks on a convolutional cargo-occupancy classifier using fully simulated 3D environments. Using Mitsuba 3 for differentiable rendering, we optimize patch textures across variations in geometry, lighting, and viewpoint, and compare their effectiveness to a 2D compositing baseline. Our experiments demonstrate that 3D-optimized patches achieve high attack success rates, especially in a denial-of-service scenario (empty to full), where success reaches 84.94 percent. Concealment attacks (full to empty) prove more challenging but still reach 30.32 percent. We analyze the factors influencing attack success, discuss implications for the security of automated logistics pipelines, and highlight directions for strengthening physical robustness. To our knowledge, this is the first study to investigate adversarial patch attacks for cargo-occupancy estimation in physically realistic, fully simulated 3D scenes.
zh

[CV-34] FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization

链接: https://arxiv.org/abs/2511.19248
作者: Md Akil Raihan Iftee,Syed Md. Ahnaf Hasan,Amin Ahsan Ali,AKM Mahbubur Rahman,Sajib Mistry,Aneesh Krishna
机构: Center for Computational & Data Sciences (CCDS), Independent University, Bangladesh; Curtin University, Australia
类目: Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV)
备注: 13 pages, 3 figures, 2 tables

点击查看摘要

[CV-35] IDSplat: Instance-Decomposed 3D Gaussian Splatting for Driving Scenes

链接: https://arxiv.org/abs/2511.19235
作者: Carl Lindström,Mahan Rafidashti,Maryam Fatemi,Lars Hammarstrand,Martin R. Oswald,Lennart Svensson
机构: Zenseact; Chalmers University of Technology; University of Amsterdam
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-36] Learning Plug-and-play Memory for Guiding Video Diffusion Models

链接: https://arxiv.org/abs/2511.19229
作者: Selena Song,Ziming Xu,Zijun Zhang,Kun Zhou,Jiaxian Guo,Lianhui Qin,Biwei Huang
机构: University of California, San Diego (加州大学圣地亚哥分校); Google Research, Australia (谷歌研究院，澳大利亚)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-37] Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving

链接: https://arxiv.org/abs/2511.19221
作者: Jianhua Han,Meng Tian,Jiangtong Zhu,Fan He,Huixin Zhang,Sitong Guo,Dechang Zhu,Hao Tang,Pei Xu,Yuze Guo,Minzhe Niu,Haojie Zhu,Qichao Dong,Xuechao Yan,Siyuan Dong,Lu Hou,Qingqiu Huang,Xiaosong Jia,Hang Xu
机构: Yinwang Intelligent Technology Co. Ltd.(亿万个智能科技有限公司); Fudan University(复旦大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-38] Are Large Vision Language Models Truly Grounded in Medical Images? Evidence from Italian Clinical Visual Question Answering ALT

链接: https://arxiv.org/abs/2511.19220
作者: Federico Felizzi,Olivia Riccomi,Michele Ferramola,Francesco Andrea Causio,Manuel Del Medico,Vittorio De Vita,Lorenzo De Mori,Alessandra Piscitelli Pietro Eric Risuleo,Bianca Destro Castaniti,Antonio Cristiano Alessia Longo,Luigi De Angelis,Mariapia Vassalli,Marcello Di Pumpo
机构: SIIAM(意大利国家研究委员会); NSBProject; Dept. of Life Sciences & Public Health, UCSC(生命科学与公共卫生系，罗马大学); ASL RM 4; UCSC(罗马大学); Univ. Paris Cité; Univ. of Pisa
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Accepted at the Workshop on Multimodal Representation Learning for Healthcare (MMRL4H), EurIPS 2025

点击查看摘要

[CV-39] ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment AAAI2026

链接: https://arxiv.org/abs/2511.19217
作者: Wanjiang Weng,Xiaofeng Tan,Junbo Wang,Guo-Sen Xie,Pan Zhou,Hongsong Wang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by AAAI 2026

点击查看摘要

[CV-40] NVGS: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting

【速读】：该论文旨在解决3D高斯溅射（3D Gaussian Splatting）在大规模场景渲染中因高斯分布的半透明特性而无法应用遮挡剔除（occlusion culling）的问题，从而限制了渲染效率。解决方案的关键在于提出一种新型方法，通过一个小型共享多层感知机（MLP）学习训练模型中所有高斯的视角依赖可见性函数，并在光栅化前对视锥体内的高斯进行神经查询，以剔除被遮挡的原始对象；该方法利用Tensor Cores加速计算，并集成到一个新的实例化软件光栅器中，实现了比现有方法更优的显存占用和图像质量表现，且与现有的细节层次（LoD）技术具有互补性。

链接: https://arxiv.org/abs/2511.19202
作者: Brent Zoomers,Florian Hahlbohm,Joni Vanherck,Lode Jorissen,Marcus Magnor,Nick Michiels
机构: Digital Future Lab, Hasselt University, Belgium (比利时哈塞尔特大学数字未来实验室); Computer Graphics Lab, TU Braunschweig, Germany (德国不伦瑞克工业大学计算机图形学实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR)
备注: 15 pages, 13 figures

点击查看摘要

Abstract:3D Gaussian Splatting can exploit frustum culling and level-of-detail strategies to accelerate rendering of scenes containing a large number of primitives. However, the semi-transparent nature of Gaussians prevents the application of another highly effective technique: occlusion culling. We address this limitation by proposing a novel method to learn the viewpoint-dependent visibility function of all Gaussians in a trained model using a small, shared MLP across instances of an asset in a scene. By querying it for Gaussians within the viewing frustum prior to rasterization, our method can discard occluded primitives during rendering. Leveraging Tensor Cores for efficient computation, we integrate these neural queries directly into a novel instanced software rasterizer. Our approach outperforms the current state of the art for composed scenes in terms of VRAM usage and image quality, utilizing a combination of our instanced rasterizer and occlusion culling MLP, and exhibits complementary properties to existing LoD techniques.
zh

[CV-41] Can Modern Vision Models Understand the Difference Between an Object and a Look-alike?

链接: https://arxiv.org/abs/2511.19200
作者: Itay Cohen,Ethan Fetaya,Amir Rosenfeld
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-42] CLASH: A Benchmark for Cross-Modal Contradiction Detection

链接: https://arxiv.org/abs/2511.19199
作者: Teodora Popordanoska,Jiameng Li,Matthew B. Blaschko
机构: ESAT-PSI, KU Leuven (鲁汶大学ESAT-PSI实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: First two authors contributed equally

点击查看摘要

[CV-43] hree-Dimensional Anatomical Data Generation Based on Artificial Neural Networks IROS

链接: https://arxiv.org/abs/2511.19198
作者: Ann-Sophia Müller,Moonkwang Jeong,Meng Zhang,Jiyuan Tian,Arkadiusz Miernik,Stefanie Speidel,Tian Qiu
机构: German Cancer Research Center (DKFZ); Dresden University of Technology (德累斯顿工业大学); University of Freiburg - Medical Centre (弗莱堡大学医学院附属医院); National Center for Tumor Diseases (NCT/UCC) Dresden (德累斯顿肿瘤疾病中心)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: 6 pages, 4 figures, 1 table, IEEE International Conference on Intelligent Robots and Systems (IROS)

点击查看摘要

[CV-44] SpectraNet: FFT-assisted Deep Learning Classifier for Deepfake Face Detection

链接: https://arxiv.org/abs/2511.19187
作者: Nithira Jayarathne,Naveen Basnayake,Keshawa Jayasundara,Pasindu Dodampegama,Praveen Wijesinghe,Hirushika Pelagewatta,Kavishka Abeywardana,Sandushan Ranaweera,Chamira Edussooriya
机构: University of Moratuwa (莫鲁图瓦大学); University of Sri Jayewardenepura (斯里贾亚瓦德纳普拉大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 4 pages, 3 figures

点击查看摘要

[CV-45] nnActive: A Framework for Evaluation of Active Learning in 3D Biomedical Segmentation

链接: https://arxiv.org/abs/2511.19183
作者: Carsten T. Lüth,Jeremias Traub,Kim-Celine Kahl,Till J. Bungert,Lukas Klein,Lars Krämer,Paul F. Jaeger,Fabian Isensee,Klaus Maier-Hein
机构: German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Germany; Helmholtz Imaging, German Cancer Research Center (DKFZ), Heidelberg, Germany; Faculty of Mathematics and Computer Science, University of Heidelberg, Germany; German Cancer Research Center (DKFZ) Heidelberg, Division of Intelligent Medical Systems, Germany; Institute for Machine Learning, ETH Zürich, Switzerland; German Cancer Research Center (DKFZ) Heidelberg, Interactive Machine Learning Group, Germany; Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital, Germany; National Center for Tumor Diseases (NCT) Heidelberg, Germany
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at TMLR

点击查看摘要

[CV-46] Evaluating Deep Learning and Traditional Approaches Used in Source Camera Identification

链接: https://arxiv.org/abs/2511.19180
作者: Mansur Ozaman
机构: Nazarbayev Intellectual School of Science and Mathematics (纳扎尔巴耶夫科学与数学精英学校)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 4 figures

点击查看摘要

[CV-47] MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes

链接: https://arxiv.org/abs/2511.19172
作者: Kehua Chen,Tianlu Mao,Zhuxin Ma,Hao Jiang,Zehao Li,Zihan Liu,Shuqi Gao,Honglong Zhao,Feng Dai,Yucheng Zhang,Zhaoqi Wang
机构: Institute of Computing Technology, Chinese Academy of Sciences, ICT (中国科学院计算技术研究所); University of Chinese Academy of Sciences, UCAS (中国科学院大学); Beihang University (北京航空航天大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-48] st-Time Preference Optimization for Image Restoration AAAI26

链接: https://arxiv.org/abs/2511.19169
作者: Bingchen Li,Xin Li,Jiaqi Xu,Jiaming Guo,Wenbo Li,Renjing Pei,Zhibo Chen
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by AAAI26

点击查看摘要

[CV-49] Collaborative Learning with Multiple Foundation Models for Source-Free Domain Adaptation

链接: https://arxiv.org/abs/2511.19147
作者: Huisoo Lee,Jisu Han,Hyunsouk Cho,Wonjun Hwang
机构: Ajou University (阿肖大学); Korea University (韩国大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 15 pages, 8 figures

点击查看摘要

[CV-50] ABM-LoRA: Activation Boundary Matching for Fast Convergence in Low-Rank Adaptation

链接: https://arxiv.org/abs/2511.19145
作者: Dongha Lee,Jinhee Park,Minjun Kim,Junseok Kwon
机构: Chung-Ang University (中央大学); Korea Electronics Technology Institute (韩国电子技术研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 16 pages, 5 figures, under review

点击查看摘要

[CV-51] FilmSceneDesigner: Chaining Set Design for Procedural Film Scene Generation

【速读】：该论文旨在解决传统电影场景设计依赖专家手动建模所带来的劳动密集与耗时问题，从而提升影视制作中场景生成的自动化水平。其解决方案的关键在于提出FilmSceneDesigner系统，该系统采用基于智能体的链式框架（agent-based chaining framework），将自然语言描述转化为符合专业流程的结构化参数，并通过一个程序化生成流水线（procedural generation pipeline）执行包括平面布局、结构构建、材质分配、门窗放置及物体检索与布局等模块化操作，最终从零开始生成具备强 cinematic fidelity（电影真实感）的完整场景。此外，为增强资产多样性与真实性，研究还构建了SetDepot-Pro数据集，包含6,862个电影专用3D资产和733种材料，支撑系统输出高质量且多样化的场景内容。

链接: https://arxiv.org/abs/2511.19137
作者: Zhifeng Xie,Keyi Zhang,Yiye Yan,Yuling Guo,Fan Yang,Jiting Zhou,Mengtian Li
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

Abstract:Film set design plays a pivotal role in cinematic storytelling and shaping the visual atmosphere. However, the traditional process depends on expert-driven manual modeling, which is labor-intensive and time-consuming. To address this issue, we introduce FilmSceneDesigner, an automated scene generation system that emulates professional film set design workflow. Given a natural language description, including scene type, historical period, and style, we design an agent-based chaining framework to generate structured parameters aligned with film set design workflow, guided by prompt strategies that ensure parameter accuracy and coherence. On the other hand, we propose a procedural generation pipeline which executes a series of dedicated functions with the structured parameters for floorplan and structure generation, material assignment, door and window placement, and object retrieval and layout, ultimately constructing a complete film scene from scratch. Moreover, to enhance cinematic realism and asset diversity, we construct SetDepot-Pro, a curated dataset of 6,862 film-specific 3D assets and 733 materials. Experimental results and human evaluations demonstrate that our system produces structurally sound scenes with strong cinematic fidelity, supporting downstream tasks such as virtual previs, construction drawing and mood board creation.
zh

[CV-52] MambaRefine-YOLO: A Dual-Modality Small Object Detector for UAV Imagery

链接: https://arxiv.org/abs/2511.19134
作者: Shuyu Cao,Minxin Chen,Yucheng Song,Zhaozhong Chen,Xinyou Zhang
机构: SWJTU-Leeds Joint School (西南交通大学-利兹大学联合学院); School of Computing and AI (计算机与人工智能学院), Southwest Jiaotong University (西南交通大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Submitted to IEEE Geoscience and Remote Sensing Letters

点击查看摘要

[CV-53] When Semantics Regulate: Rethinking Patch Shuffle and Internal Bias for Generated Image Detection with CLIP

链接: https://arxiv.org/abs/2511.19126
作者: Beilin Chu,Weike You,Mengtao Li,Tingting Zheng,Kehan Zhao,Xuan Xu,Zhigao Lu,Jia Song,Moxuan Xu,Linna Zhou
机构: Beijing University of Posts and Telecommunications (北京邮电大学); Central University of Finance and Economics (中央财经大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 14 pages, 7 figures and 7 tables

点击查看摘要

[CV-54] MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images

链接: https://arxiv.org/abs/2511.19119
作者: Qirui Wang,Jingyi He,Yining Pan,Si Yong Yeo,Xulei Yang,Shijie Li
机构: Technical University of Munich; Institute for Infocomm Research (I2R), A*STAR, Singapore; Nanyang Technological University
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-55] 3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusion

链接: https://arxiv.org/abs/2511.19117
作者: Minchong Chen,Xiaoyun Yuan,Junzhe Wan,Jianing Zhang,Jun Zhang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Optics (physics.optics)
备注: 11 pages, 7 figures

点击查看摘要

[CV-56] DiffSeg30k: A Multi-Turn Diffusion Editing Benchmark for Localized AIGC Detection

链接: https://arxiv.org/abs/2511.19111
作者: Hai Ci,Ziheng Peng,Pei Yang,Yingxin Xuan,Mike Zheng Shou
机构: Show Lab, National University of Singapore (新加坡国立大学); South China University of Technology (华南理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 16 pages, 10 figures

点击查看摘要

[CV-57] HABIT: Human Action Benchmark for Interactive Traffic in CARLA WACV2026

链接: https://arxiv.org/abs/2511.19109
作者: Mohan Ramesh,Mark Azer,Fabian B. Flohr
机构: Munich University of Applied Sciences (慕尼黑应用技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to WACV 2026. This is the pre-camera-ready version

点击查看摘要

[CV-58] Graph-based 3D Human Pose Estimation using WiFi Signals

链接: https://arxiv.org/abs/2511.19105
作者: Jichao Chen,YangYang Qu,Ruibo Tang,Dirk Slock
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-59] owards Generalizable Deepfake Detection via Forgery-aware Audio-Visual Adaptation: A Variational Bayesian Approach

链接: https://arxiv.org/abs/2511.19080
作者: Fan Nie,Jiangqun Ni,Jian Zhang,Bin Zhang,Weizhe Zhang,Bin Li
机构: Sun Yat-sen University (中山大学); Pengcheng Laboratory (鹏城实验室); Guangzhou University (广州大学); Harbin Institute of Technology (哈尔滨工业大学); Shenzhen University (深圳大学)
类目: Multimedia (cs.MM); Computer Vision and Pattern Recognition (cs.CV)
备注: TIFS AQE

点击查看摘要

[CV-60] DEAP-3DSAM: Decoder Enhanced and Auto Prompt SAM for 3D Medical Image Segmentation

链接: https://arxiv.org/abs/2511.19071
作者: Fangda Chen,Jintao Tang,Pancheng Wang,Ting Wang,Shasha Li,Ting Deng
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by BIBM 2024

点击查看摘要

[CV-61] DynaMix: Generalizable Person Re-identification via Dynamic Relabeling and Mixed Data Sampling

链接: https://arxiv.org/abs/2511.19067
作者: Timur Mamedov,Anton Konushin,Vadim Konushin
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-62] Understanding Accelerating and Improving MeanFlow Training

链接: https://arxiv.org/abs/2511.19065
作者: Jin-Young Kim,Hyojun Go,Lea Bogensperger,Julius Erbach,Nikolai Kalischek,Federico Tombari,Konrad Schindler,Dominik Narnhofer
机构: ETH Zurich; University of Zurich; Google(谷歌)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-63] Granular Computing-driven SAM: From Coarse-to-Fine Guidance for Prompt-Free Segmentation

链接: https://arxiv.org/abs/2511.19062
作者: Qiyang Yu,Yu Fang,Tianrui Li,Xuemei Cao,Yan Chen,Jianghao Li,Fan Min,Yi Zhang
机构: Southwest Petroleum University (西南石油大学); Southwest Jiaotong University (西南交通大学); Southwestern University of Finance and Economics (西南财经大学); Sichuan University (四川大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 19 pages, 7 figures

点击查看摘要

[CV-64] LAA3D: A Benchmark of Detecting and Tracking Low-Altitude Aircraft in 3D Space

链接: https://arxiv.org/abs/2511.19057
作者: Hai Wu,Shuai Tang,Jiale Wang,Longkun Zou,Mingyue Guo,Rongqin Liang,Ke Chen,Yaowei Wang
机构: Pengcheng Laboratory (鹏城实验室); South China University of Technology (华南理工大学); University of Southern California (南加州大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 25 pages

点击查看摘要

[CV-65] Beyond Reward Margin: Rethinking and Resolving Likelihood Displacement in Diffusion Models via Video Generation

链接: https://arxiv.org/abs/2511.19049
作者: Ruojun Xu,Yu Kai,Xuhua Ren,Jiaxiang Cheng,Bing Ma,Tianxiang Zheng,Qinhlin Lu
机构: Zhejiang University (浙江大学); Tencent (腾讯)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-66] MedSAM3: Delving into Segment Anything with Medical Concepts

链接: https://arxiv.org/abs/2511.19046
作者: Anglin Liu,Rundong Xue,Xu R. Cao,Yifan Shen,Yi Lu,Xiang Li,Qianqian Chen,Jintai Chen
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-67] CSD: Change Semantic Detection with only Semantic Change Masks for Damage Assessment in Conflict Zones

链接: https://arxiv.org/abs/2511.19035
作者: Kai Zhenga,Zhenkai Wu,Fupeng Wei,Miaolan Zhou,Kai Lie,Haitao Guo,Lei Ding,Wei Zhang,Hang-Cheng Dong
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-68] ReEXplore: Improving MLLM s for Embodied Exploration with Contextualized Retrospective Experience Replay

链接: https://arxiv.org/abs/2511.19033
作者: Gengyuan Zhang,Mingcong Ding,Jingpei Wu,Ruotong Liao,Volker Tresp
机构: LMU Munich (慕尼黑路德维希-马克西米利安大学); Munich Center for Machine Learning (慕尼黑机器学习中心); TU Munich (慕尼黑工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 main pages plus 13 pages Appendix

点击查看摘要

[CV-69] Benchmarking Corruption Robustness of LVLMs: A Discriminative Benchmark and Robustness Alignment Metric

链接: https://arxiv.org/abs/2511.19032
作者: Xiangjie Sui,Songyang Li,Hanwei Zhu,Baoliang Chen,Yuming Fang,Xin Sun
机构: City University of Macau (澳门城市大学); Nanyang Technological University (南洋理工大学); South China Normal University (华南师范大学); Jiangxi University of Finance and Economics (江西财经大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 15 pages

点击查看摘要

[CV-70] Life-IQA: Boosting Blind Image Quality Assessment through GCN-enhanced Layer Interaction and MoE-based Feature Decoupling

链接: https://arxiv.org/abs/2511.19024
作者: Long Tang,Guoquan Zhen,Jie Hao,Jianbo Zhang,Huiyu Duan,Liang Yuan,Guangtao Zhai
机构: Shanghai Jiao Tong University (上海交通大学); Beijing University of Chemical Technology (北京化工大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-71] Dynamic Granularity Matters: Rethinking Vision Transformers Beyond Fixed Patch Splitting

链接: https://arxiv.org/abs/2511.19021
作者: Qiyang Yu,Yu Fang,Tianrui Li,Xuemei Cao,Yan Chen,Jianghao Li,Fan Min
机构: Southwest Petroleum University (西南石油大学); Southwest Jiaotong University (西南交通大学); Southwestern University of Finance and Economics (西南财经大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 7 figures

点击查看摘要

[CV-72] A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation

链接: https://arxiv.org/abs/2511.19004
作者: Wentao Qu,Guofeng Mei,Yang Wu,Yongshun Gong,Xiaoshui Huang,Liang Xiao
机构: NJUST(南京理工大学); FBK(意大利特伦托大学Fondazione Bruno Kessler); SDU(山东大学); SJTU(上海交通大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-73] AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization WACV2026

链接: https://arxiv.org/abs/2511.18993
作者: Christos Koutlis,Symeon Papadopoulos
机构: Information Technologies Institute @ CERTH (信息与技术研究所 @ 希腊研究中心与技术基金会)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: WACV 2026

点击查看摘要

[CV-74] View-Consistent Diffusion Representations for 3D-Consistent Video Generation

链接: https://arxiv.org/abs/2511.18991
作者: Duolikun Danier,Ge Gao,Steven McDonagh,Changjian Li,Hakan Bilen,Oisin Mac Aodha
机构: University of Edinburgh (爱丁堡大学); University of Bristol (布里斯托大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-75] Rethinking Plant Disease Diagnosis: Bridging the Academic-Practical Gap with Vision Transformers and Zero-Shot Learning

链接: https://arxiv.org/abs/2511.18989
作者: Wassim Benabbas,Mohammed Brahimi,Samir Akhrouf,Bilal Fortas
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-76] UMCL: Unimodal-generated Multimodal Contrastive Learning for Cross-compression-rate Deepfake Detection

链接: https://arxiv.org/abs/2511.18983
作者: Ching-Yi Lai,Chih-Yu Jian,Pei-Cheng Chuang,Chia-Ming Lee,Chih-Chung Hsu,Chiou-Ting Hsu,Chia-Wen Lin
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 24-page manuscript accepted to IJCV

点击查看摘要

[CV-77] Zero-shot segmentation of skin tumors in whole-slide images with vision-language foundation models

链接: https://arxiv.org/abs/2511.18978
作者: Santiago Moreno,Pablo Meseguer,Rocío del Amor,Valery Naranjo
机构: Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano (HUMAN-Tech); Universitat Politécnica de Valencia (瓦伦西亚理工大学); Artikode Intelligence S.L.
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Conference manuscript accepted for oral presentation at CASEIB 2025

点击查看摘要

[CV-78] Peregrine: One-Shot Fine-Tuning for FHE Inference of General Deep CNNs

链接: https://arxiv.org/abs/2511.18976
作者: Huaming Ling,Ying Wang,Si Chen,Junfeng Fan
机构: Cipherflow( Cipherflow); Open Security Research (Open Security Research)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-79] CataractCompDetect: Intraoperative Complication Detection in Cataract Surgery

链接: https://arxiv.org/abs/2511.18968
作者: Bhuvan Sachdeva,Sneha Kumari,Rudransh Agarwal,Shalaka Kumaraswamy,Niharika Singri Prasad,Simon Mueller,Raphael Lechtenboehmer,Maximilian W. M. Wintergerst,Thomas Schultz,Kaushik Murali,Mohit Jain
机构: Sankara Eye Hospital (Sankara眼科医院); Microsoft Research (微软研究院); University of Bonn (波恩大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-80] AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention

链接: https://arxiv.org/abs/2511.18960
作者: Lei Xiao,Jifeng Li,Juntao Gao,Feiyang Ye,Yan Jin,Jingjing Qian,Jing Zhang,Yong Wu,Xiaoyuan Yu
机构: LiAuto Inc.; School of Information Science and Technology, Beijing University of Technology; School of Data Science, The Chinese University of Hong Kong, Shenzhen
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: 18 pages, 10 figures

点击查看摘要

[CV-81] Eevee: Towards Close-up High-resolution Video-based Virtual Try-on

链接: https://arxiv.org/abs/2511.18957
作者: Jianhao Zeng,Yancheng Bai,Ruidong Chen,Xuanpu Zhang,Lei Sun,Dongyang Jin,Ryan Xu,Nannan Zhang,Dan Song,Xiangxiang Chu
机构: Amap, Alibaba Group (高德地图，阿里巴巴集团); Tianjin University (天津大学); Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences (中国科学院深圳先进技术研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-82] Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic Manipulation

链接: https://arxiv.org/abs/2511.18950
作者: Juntao Gao,Feiyang Ye,Jing Zhang,Wenjing Qian
机构: Beijing University of Technology (北京工业大学); LiAuto Inc. (小鹏汽车公司)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 11 pages, 5 figures

点击查看摘要

[CV-83] Leverag ing Adversarial Learning for Pathological Fidelity in Virtual Staining

链接: https://arxiv.org/abs/2511.18946
作者: José Teixeira,Pascal Klöckner,Diana Montezuma,Melis Erdal Cesur,João Fraga,Hugo M. Horlings,Jaime S. Cardoso,Sara P. Oliveira
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-84] VeCoR - Velocity Contrastive Regularization for Flow Matching

链接: https://arxiv.org/abs/2511.18942
作者: Zong-Wei Hong,Jing-lun Li,Lin-Ze Li,Shen Zhang,Yao Tang
机构: JIIOV Technology
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-85] Human-Centric Open-Future Task Discovery: Formulation Benchmark and Scalable Tree-Based Search

链接: https://arxiv.org/abs/2511.18929
作者: Zijian Song,Xiaoxin Lin,Tao Pu,Zhenlong Yuan,Guangrun Wang,Liang Lin
机构: 1. University of Science and Technology of China (中国科学技术大学); 2. Institute of Artificial Intelligence, University of Science and Technology of China (中国科学技术大学人工智能研究院); 3. Anhui Provincial Key Laboratory of Artificial Intelligence, University of Science and Technology of China (安徽省人工智能重点实验室，中国科学技术大学); 4. Tsinghua University (清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 9 figures

点击查看摘要

[CV-86] FineXtrol: Controllable Motion Generation via Fine-Grained Text AAAI2026

链接: https://arxiv.org/abs/2511.18927
作者: Keming Shen,Bizhu Wu,Junliang Chen,Xiaoqin Wang,Linlin Shen
机构: 1. University of Science and Technology of China (中国科学技术大学); 2. Institute of Artificial Intelligence, University of Science and Technology of China (中国科学技术大学人工智能研究院); 3. School of Computer Science and Technology, University of Science and Technology of China (中国科学技术大学计算机科学与技术学院); 4. Department of Computer Science and Engineering, Zhejiang University (浙江大学计算机科学与工程系); 5. Hefei National Laboratory for Physical Sciences at the Microscale, University of Science and Technology of China (中国科学技术大学微尺度物理科学国家实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 20 pages, 14 figures, AAAI 2026

点击查看摘要

[CV-87] AttenDence: Maximizing Attention Confidence for Test Time Adaptation

链接: https://arxiv.org/abs/2511.18925
作者: Yash Mali
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Initial submission. 5 pages, 4 figures

点击查看摘要

[CV-88] One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control

链接: https://arxiv.org/abs/2511.18922
作者: Zhenxing Mi,Yuxin Wang,Dan Xu
机构: The Hong Kong University of Science and Technology (香港科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-89] BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models

链接: https://arxiv.org/abs/2511.18921
作者: Juncheng Li,Yige Li,Hanxun Huang,Yunhao Chen,Xin Wang,Yixu Wang,Xingjun Ma,Yu-Gang Jiang
机构: Fudan University (复旦大学); Singapore Management University (新加坡管理大学); The University of Melbourne (墨尔本大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-90] EventSTU: Event-Guided Efficient Spatio-Temporal Understanding for Video Large Language Models

链接: https://arxiv.org/abs/2511.18920
作者: Wenhao Xu,Xin Dong,Yue Li,Haoyuan Shi,Zhiwei Xiong
机构: University of Science and Technology of China (中国科学技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 7 figures

点击查看摘要

[CV-91] Learning What to Trust: Bayesian Prior-Guided Optimization for Visual Generation

链接: https://arxiv.org/abs/2511.18919
作者: Ruiying Liu,Yuanzhi Liang,Haibin Huang,Tianshu Yu,Chi Zhang
机构: The Chinese University of Hong Kong, Shenzhen (香港中文大学（深圳）); Institute of Artificial Intelligence, China Telecom (TeleAI) (中国电信人工智能研究院（TeleAI)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-92] MatMart: Material Reconstruction of 3D Objects via Diffusion

链接: https://arxiv.org/abs/2511.18900
作者: Xiuchao Wu,Pengfei Zhu,Jiangjing Lyu,Xinguo Liu,Jie Guo,Yanwen Guo,Weiwei Xu,Chengfei Lyu
机构: Zhejiang University (浙江大学); Nanjing University (南京大学); Alibaba Group (阿里巴巴集团)
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-93] MetaDCSeg: Robust Medical Image Segmentation via Meta Dynamic Center Weighting

链接: https://arxiv.org/abs/2511.18894
作者: Chenyu Mu,Guihai Chen,Xun Yang,Erkun Yang,Cheng Deng
机构: Xidian University (西安电子科技大学); University of Science and Technology of China (中国科学技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-94] MFmamba: A Multi-function Network for Panchromatic Image Resolution Restoration Based on State-Space Model AAAI-2026

链接: https://arxiv.org/abs/2511.18888
作者: Qian Jiang,Qianqian Wang,Xin Jin,Michal Wozniak,Shaowen Yao,Wei Zhou
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages, 9 figures. This paper has been accepted for publication in AAAI-2026

点击查看摘要

[CV-95] MagicWorld: Interactive Geometry-driven Video World Exploration

链接: https://arxiv.org/abs/2511.18886
作者: Guangyuan Li,Siming Zheng,Shuolin Xu,Jinwei Chen,Bo Li,Xiaobin Hu,Lei Zhao,Peng-Tao Jiang
机构: Zhejiang University (浙江大学); vivo Mobile Communication Co., Ltd (维沃移动通信有限公司); National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-96] Facade Segmentation for Solar Photovoltaic Suitability NEURIPS2025

链接: https://arxiv.org/abs/2511.18882
作者: Ayca Duran,Christoph Waibel,Bernd Bickel,Iro Armeni,Arno Schlueter
机构: ETH Zurich (苏黎世联邦理工学院); VITO (比利时弗拉芒政府应用科学研究组织); Stanford University (斯坦福大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: NeurIPS 2025 Tackling Climate Change with Machine Learning Workshop version. Non-archival

点击查看摘要

[CV-97] Parallel Vision Token Scheduling for Fast and Accurate Multimodal LMMs Inference

链接: https://arxiv.org/abs/2511.18875
作者: Wengyi Zhan,Mingbao Lin,Zhihang Lin,Rongrong Ji
机构: Xiamen University (厦门大学); Rakuten Asia Pte. Ltd. (乐天亚洲有限公司); Shanghai Innovation Institute (上海创新研究院)
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注:

点击查看摘要

[CV-98] GContextFormer: A global context-aware hybrid multi-head attention approach with scaled additive aggregation for multimodal trajectory prediction

链接: https://arxiv.org/abs/2511.18874
作者: Yuzhi Chen,Yuanchang Xie,Lei Zhao,Pan Liu,Yajie Zou,Chen Wang
机构: 未知
类目: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Multiagent Systems (cs.MA); Robotics (cs.RO); Social and Information Networks (cs.SI)
备注:

点击查看摘要

[CV-99] Neural Texture Splatting: Expressive 3D Gaussian Splatting for View Synthesis Geometry and Dynamic Reconstruction SIGGRAPH

链接: https://arxiv.org/abs/2511.18873
作者: Yiming Wang,Shaofei Wang,Marko Mihajlovic,Siyu Tang
机构: ETH Zurich (苏黎世联邦理工学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR)
备注: SIGGRAPH Asia 2025 (conference track), Project page: this https URL

点击查看摘要

[CV-100] HunyuanVideo 1.5 Technical Report

链接: https://arxiv.org/abs/2511.18870
作者: Bing Wu,Chang Zou,Changlin Li,Duojun Huang,Fang Yang,Hao Tan,Jack Peng,Jianbing Wu,Jiangfeng Xiong,Jie Jiang,Linus,Patrol,Peizhen Zhang,Peng Chen,Penghao Zhao,Qi Tian,Songtao Liu,Weijie Kong,Weiyan Wang,Xiao He,Xin Li,Xinchi Deng,Xuefei Zhe,Yang Li,Yanxin Long,Yuanbo Peng,Yue Wu,Yuhong Liu,Zhenyu Wang,Zuozhuo Dai,Bo Peng,Coopers Li,Gu Gong,Guojian Xiao,Jiahe Tian,Jiaxin Lin,Jie Liu,Jihong Zhang,Jiesong Lian,Kaihang Pan,Lei Wang,Lin Niu,Mingtao Chen,Mingyang Chen,Mingzhe Zheng,Miles Yang,Qiangqiang Hu,Qi Yang,Qiuyong Xiao,Runzhou Wu,Ryan Xu,Rui Yuan,Shanshan Sang,Shisheng Huang,Siruis Gong,Shuo Huang,Weiting Guo,Xiang Yuan,Xiaojia Chen,Xiawei Hu,Wenzhi Sun,Xiele Wu,Xianshun Ren,Xiaoyan Yuan,Xiaoyue Mi,Yepeng Zhang,Yifu Sun,Yiting Lu,Yitong Li,You Huang,Yu Tang,Yixuan Li,Yuhang Deng,Yuan Zhou,Zhichao Hu,Zhiguang Liu,Zhihe Yang,Zilin Yang,Zhenzhi Lu,Zixiang Zhou,Zhao Zhong
机构: Tencent Hunyuan Foundation Model Team (腾讯混元大模型团队)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-101] DualGazeNet: A Biologically Inspired Dual-Gaze Query Network for Salient Object Detection

链接: https://arxiv.org/abs/2511.18865
作者: Yu Zhang,Haoan Ping,Yuchen Li,Zhenshan Bing,Fuchun Sun,Alois Knoll
机构: Technical University of Munich (慕尼黑工业大学); Obuda University (欧布达大学); Nanjing University Suzhou Campus (南京大学苏州校区); Tsinghua University (清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-102] Robust and Generalizable GNN Fine-Tuning via Uncertainty-aware Adapter Learning

链接: https://arxiv.org/abs/2511.18859
作者: Bo Jiang,Weijun Zhao,Beibei Wang,Xiao Wang,Jin Tang
机构: Anhui University (安徽大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-103] Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabeling AAAI2026

链接: https://arxiv.org/abs/2511.18858
作者: Xiao Cui,Yulei Qin,Xinyue Li,Wengang Zhou,Hongsheng Li,Houqiang Li
机构: 1. Institute of Automation, Chinese Academy of Sciences (中国科学院自动化研究所); 2. University of Chinese Academy of Sciences (中国科学院大学); 3. Huawei Noah’s Ark Lab (华为诺亚方舟实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: AAAI 2026 (Oral)

点击查看摘要

[CV-104] Deep Hybrid Model for Region of Interest Detection in Omnidirectional Videos

链接: https://arxiv.org/abs/2511.18856
作者: Sana Alamgeer
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-105] Robust Long-term Test-Time Adaptation for 3D Human Pose Estimation through Motion Discretization AAAI2026

链接: https://arxiv.org/abs/2511.18851
作者: Yilin Wen,Kechuan Dong,Yusuke Sugano
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by AAAI 2026, main track

点击查看摘要

[CV-106] Personalized Federated Segmentation with Shared Feature Aggregation and Boundary-Focused Calibration

链接: https://arxiv.org/abs/2511.18847
作者: Ishmam Tashdeed,Md. Atiqur Rahman,Sabrina Islam,Md. Azam Hossain
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-107] Enhancing Multi-Label Thoracic Disease Diagnosis with Deep Ensemble-Based Uncertainty Quantification

链接: https://arxiv.org/abs/2511.18839
作者: Yasiru Laksara,Uthayasanker Thayasivam
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-108] FVAR: Visual Autoregressive Modeling via Next Focus Prediction

链接: https://arxiv.org/abs/2511.18838
作者: Xiaofan Li,Chenming Wu,Yanpeng Sun,Jiaming Zhou,Delin Qu,Yansong Qu,Weihao Bo,Haibao Yu,Dingkang Liang
机构: Baidu Inc. (百度公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 4 figures

点击查看摘要

[CV-109] FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectories

链接: https://arxiv.org/abs/2511.18834
作者: Lei Ke,Hubery Yin,Gongye Liu,Zhengyao Lv,Jingcai Guo,Chen Li,Wenhan Luo,Yujiu Yang,Jing Lyu
机构: Tsinghua University (清华大学); WeChat Vision, Tencent Inc. (腾讯公司微信视觉部门); The Hong Kong University of Science and Technology (香港科技大学); The University of Hong Kong (香港大学); The Hong Kong Polytechnic University (香港理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Few-Step Image Synthesis

点击查看摘要

[CV-110] PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation

链接: https://arxiv.org/abs/2511.18833
作者: Huadai Liu,Kaicheng Luo,Wen Wang,Qian Chen,Peiwen Sun,Rongjie Huang,Xiangang Li,Jieping Ye,Wei Xue
机构: Hong Kong University of Science and Technology (HKUST); Tongyi Fun Team, Alibaba Group; CUHK; Meta FAIR
类目: ound (cs.SD); Computer Vision and Pattern Recognition (cs.CV); Audio and Speech Processing (eess.AS); Image and Video Processing (eess.IV)
备注: Preprint

点击查看摘要

[CV-111] VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction

链接: https://arxiv.org/abs/2511.18831
作者: Shaobo Wang,Tianle Niu,Runkang Yang,Deshan Liu,Xu He,Zichen Wen,Conghui He,Xuming Hu,Linfeng Zhang
机构: EPIC Lab, SJTU (上海交通大学); KTH; Shanghai AI Laboratory (上海人工智能实验室); HKUST (香港科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 15 pages, 6 tables, 8 figures

点击查看摘要

[CV-112] Leverag ing Metaheuristic Approaches to Improve Deep Learning Systems for Anxiety Disorder Detection

链接: https://arxiv.org/abs/2511.18827
作者: Mohammadreza Amiri,Monireh Hosseini
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 12 pages

点击查看摘要

[CV-113] Uncertainty-Aware Dual-Student Knowledge Distillation for Efficient Image Classification

链接: https://arxiv.org/abs/2511.18826
作者: Aakash Gore,Anoushka Dey,Aryan Mishra
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-114] Q-Save: Towards Scoring and Attribution for Generated Video Evaluation

链接: https://arxiv.org/abs/2511.18825
作者: Xiele Wu,Zicheng Zhang,Mingtao Chen,Yixian Liu,Yiming Liu,Shushi Wang,Zhichao Hu,Yuhong Liu,Guangtao Zhai,Xiaohong Liu
机构: Shanghai Jiao Tong University (上海交通大学); Shanghai Innovation Institute (上海创新研究院); Hunyuan, Tencent (腾讯混元)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 20 pages, 11 figures

点击查看摘要

[CV-115] VideoPerceiver: Enhancing Fine-Grained Temporal Perception in Video Multimodal Large Language Models

链接: https://arxiv.org/abs/2511.18823
作者: Fufangchen Zhao,Liao Zhang,Daiqi Shi,Yuanjun Gao,Chen Ye,Yang Cai,Jian Gao,Danfeng Yan
机构: State Key Laboratory of Networking and Switching Technology, BUPT (北京邮电大学网络与交换技术国家重点实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-116] DiP: Taming Diffusion Models in Pixel Space

链接: https://arxiv.org/abs/2511.18822
作者: Zhennan Chen,Junwei Zhu,Xu Chen,Jiangning Zhang,Xiaobin Hu,Hanzhen Zhao,Chengjie Wang,Jian Yang,Ying Tai
机构: Nanjing University (南京大学); Tencent Youtu Lab (腾讯优图实验室); National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-117] Disc3D: Automatic Curation of High-Quality 3D Dialog Data via Discriminative Object Referring

链接: https://arxiv.org/abs/2511.18817
作者: Siyuan Wei,Chunjie Wang,Xiao Liu,Xiaosheng Yan,Zhishan Zhou,Rui Huang
机构: PICO, ByteDance(字节跳动); Tsinghua University(清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages

点击查看摘要

[CV-118] SupLID: Geometrical Guidance for Out-of-Distribution Detection in Semantic Segmentation CIKM2025

链接: https://arxiv.org/abs/2511.18816
作者: Nimeshika Udayangani,Sarah Erfani,Christopher Leckie
机构: The University of Melbourne (墨尔本大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, CIKM 2025

点击查看摘要

[CV-119] DetAny4D: Detect Anything 4D Temporally in a Streaming RGB Video

链接: https://arxiv.org/abs/2511.18814
作者: Jiawei Hou,Shenghao Zhang,Can Wang,Zheng Gu,Yonggen Ling,Taiping Zeng,Xiangyang Xue,Jingbo Zhang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-120] Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache

链接: https://arxiv.org/abs/2511.18811
作者: Yuqiu Jiang,Xiaozhen Qiao,Tianyu Mei,Haojian Huang,Yifan Chen,Ye Zheng,Zhe Sun
机构: TeleAI(TeleAI); Fudan University (复旦大学); University of Science and Technology of China (中国科学技术大学); Beijing University of Aeronautics and Astronautics (北京航空航天大学); The Hong Kong University of Science and Technology (香港科技大学); Northwestern Polytechnical University (西北工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-121] PG-INR: Target Prior-Guided Implicit 3D CT Reconstruction for Enhanced Sparse-view Imaging

链接: https://arxiv.org/abs/2511.18806
作者: Qinglei Cao,Ziyao Tang,Xiaoqin Tang
机构: Southwest University (西南大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Please consider this version as the latest camera-ready version

点击查看摘要

[CV-122] PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusion

链接: https://arxiv.org/abs/2511.18801
作者: Yichen Yang,Hong Li,Haodong Zhu,Linin Yang,Guojun Lei,Sheng Xu,Baochang Zhang
机构: Beihang University (北京航空航天大学); Communication University of China (中国传媒大学); Zhejiang University (浙江大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-123] ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes

链接: https://arxiv.org/abs/2511.18794
作者: Zhongtao Wang,Jiaqi Dai,Qingtian Zhu,Yilong Li,Mai Su,Fei Zhu,Meng Gai,Shaorong Wang,Chengwei Pan,Yisong Chen,Guoping Wang
机构: 未知
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-124] Scale What Counts Mask What Matters: Evaluating Foundation Models for Zero-Shot Cross-Domain Wi-Fi Sensing

链接: https://arxiv.org/abs/2511.18792
作者: Cheng Jiang,Yihe Yan,Yanxiang Wang,Chun Tung Chou,Wen Hu
机构: University of New South Wales (新南威尔士大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Information Theory (cs.IT)
备注:

点击查看摘要

[CV-125] StereoDETR: Stereo-based Transformer for 3D Object Detection

链接: https://arxiv.org/abs/2511.18788
作者: Shiyi Mu,Zichong Gu,Zhiqi Ai,Anqi Liu,Yilin Gao,Shugong Xu
机构: Shanghai University (上海大学); Xi’an Jiaotong-Liverpool University (西安交通大学利物浦大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by IEEE TCSVT, 2025

点击查看摘要

[CV-126] Understanding Task Transfer in Vision-Language Models

链接: https://arxiv.org/abs/2511.18787
作者: Bhuvan Sachdeva,Karan Uppal,Abhinav Java,Vineeth N. Balasubramanian
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-127] STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolution

链接: https://arxiv.org/abs/2511.18786
作者: Junyang Chen,Jiangxin Dong,Long Sun,Yixin Yang,Jinshan Pan
机构: Nanjing University of Science and Technology (南京理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-128] A Novel Dual-Stream Framework for dMRI Tractography Streamline Classification with Joint dMRI and fMRI Data

链接: https://arxiv.org/abs/2511.18781
作者: Haotian Yan,Bocheng Guo,Jianzhong He,Nir A. Sochen,Ofer Pasternak,Lauren J O’Donnell,Fan Zhang
机构: University of Electronic Science and Technology of China (电子科技大学); Zhejiang University of Technology (浙江工业大学); University of Tel Aviv (特拉维夫大学); Harvard Medical School (哈佛医学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Submitted to ISBI 2026, 7 pages, 2 figures

点击查看摘要

[CV-129] ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection

链接: https://arxiv.org/abs/2511.18780
作者: Ruize Ma,Minghong Cai,Yilei Jiang,Jiaming Han,Yi Feng,Yingshui Tan,Xiaoyong Zhu,Bo Zhang,Bo Zheng,Xiangyu Yue
机构: CUHK MMLab (香港中文大学多媒体实验室); Alibaba Group (阿里巴巴集团); Nanjing University (南京大学); Shanghai AI Laboratory (上海人工智能实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-130] Rethinking Garment Conditioning in Diffusion-based Virtual Try-On

链接: https://arxiv.org/abs/2511.18775
作者: Kihyun Na,Jinyoung Choi,Injung Kim
机构: Handong Global University (海东全球大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 15 pages (including references and supplementary material), 10 figures, 7 tables. Code and pretrained models will be released

点击查看摘要

[CV-131] Sampling Control for Imbalanced Calibration in Semi-Supervised Learning AAAI2026

链接: https://arxiv.org/abs/2511.18773
作者: Senmao Tian,Xiang Wei,Shunli Zhang
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
备注: Accepted at AAAI 2026

点击查看摘要

[CV-132] Unsupervised Multi-View Visual Anomaly Detection via Progressive Homography-Guided Alignment

链接: https://arxiv.org/abs/2511.18766
作者: Xintao Chen,Xiaohao Xu,Bozhong Zheng,Yun Liu,Yingna Wu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-133] NI-Tex: Non-isometric Image-based Garment Texture Generation

链接: https://arxiv.org/abs/2511.18765
作者: Hui Shan,Ming Li,Haitao Yang,Kai Zheng,Sizhe Zheng,Yanwei Fu,Xiangru Huang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-134] VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement

链接: https://arxiv.org/abs/2511.18763
作者: Xuanzhao Dong,Wenhui Zhu,Yujian Xiong,Xiwen Chen,Hao Wang,Xin Li,Jiajun Cheng,Zhipeng Wang,Shao Tang,Oana Dumitrascu,Yalin Wang
机构: Arizona State University (亚利桑那州立大学); Clemson University (克莱姆森大学); LinkedIn Corporation (领英公司); Mayo Clinic (梅奥诊所)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-135] From Features to Reference Points: Lightweight and Adaptive Fusion for Cooperative Autonomous Driving

链接: https://arxiv.org/abs/2511.18757
作者: Yongqi Zhu,Morui Zhu,Qi Chen,Deyuan Qu,Song Fu,Qing Yang
机构: University of North Texas (北德克萨斯大学); Toyota InfoTech Labs (丰田信息科技实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 4 figures

点击查看摘要

[CV-136] Any4D: Open-Prompt 4D Generation from Natural Language and Images

链接: https://arxiv.org/abs/2511.18746
作者: Hao Li,Qiao Sun
机构: Fudan University (复旦大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-137] ProxT2I: Efficient Reward-Guided Text-to-Image Generation via Proximal Diffusion

链接: https://arxiv.org/abs/2511.18742
作者: Zhenghan Fang,Jian Zheng,Qiaozi Gao,Xiaofeng Gao,Jeremias Sulam
机构: Johns Hopkins University (约翰霍普金斯大学); Amazon (亚马逊)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-138] hinking Ahead: Foresight Intelligence in MLLM s and World Models CVPR2026

链接: https://arxiv.org/abs/2511.18735
作者: Zhantao Gong,Liaoyuan Fan,Qing Guo,Xun Xu,Xulei Yang,Shijie Li
机构: Nankai University (南开大学); The University of Hong Kong (香港大学); Institute for Infocomm Research (I2R), A*STAR, Singapore (新加坡资讯通信研究院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 25 pages, 27 figures, submitted to CVPR 2026

点击查看摘要

[CV-139] YoCity: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion

链接: https://arxiv.org/abs/2511.18734
作者: Keyang Lu,Sifan Zhou,Hongbin Xu,Gang Xu,Zhifei Yang,Yikai Wang,Zhen Xiao,Jieyi Long,Ming Li
机构: Beihang University (北京航空航天大学); Carnegie Mellon University (卡内基梅隆大学); ByteDance Seed (字节跳动种子团队); Guangming Laboratory (光明实验室); Peking University (北京大学); Beijing Normal University (北京师范大学); Theta Labs (Theta 实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 22 pages, 16 figures

点击查看摘要

[CV-140] GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Driving

链接: https://arxiv.org/abs/2511.18729
作者: Lin Liu,Caiyan Jia,Guanyi Yu,Ziying Song,JunQiao Li,Feiyang Jia,Peiliang Wu,Xiaoshuai Hao,Yandan Luo
机构: Beijing Jiaotong University (北京交通大学); Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence (北京市交通数据挖掘与具身智能重点实验室); Qcraft; Yanshan University (燕山大学); Institute of Information Engineering, Chinese Academy of Sciences (中国科学院信息工程研究所); The University of Queensland (昆士兰大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-141] Seeing What Matters: Visual Preference Policy Optimization for Visual Generation

链接: https://arxiv.org/abs/2511.18719
作者: Ziqi Ni,Yuanzhi Liang,Rui Li,Yi Zhou,Haibing Huang,Chi Zhang,Xuelong Li
机构: Southeast University (东南大学); Institute of Artificial Intelligence (TeleAI), China Telecom (中国电信人工智能研究院); University of Science and Technology of China (中国科学技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-142] GRIT-LP: Graph Transformer with Long-Range Skip Connection and Partitioned Spatial Graphs for Accurate Ice Layer Thickness Prediction

链接: https://arxiv.org/abs/2511.18716
作者: Zesheng Liu,Maryam Rahnemoonfar
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-143] DriveFlow: Rectified Flow Adaptation for Robust 3D Object Detection in Autonomous Driving AAAI2026

链接: https://arxiv.org/abs/2511.18713
作者: Hongbin Lin,Yiming Yang,Chaoda Zheng,Yifan Zhang,Shuaicheng Niu,Zilu Guo,Yafeng Li,Gui Gui,Shuguang Cui,Zhen Li
机构: 1. Tsinghua University (清华大学); 2. Institute for AI Industry Research (清华大学人工智能研究院); 3. University of California, Berkeley (加州大学伯克利分校); 4. Peking University (北京大学); 5. Microsoft (微软); 6. Alibaba Group (阿里巴巴集团); 7. Huawei Technologies (华为技术有限公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by AAAI 2026

点击查看摘要

[CV-144] Modality-Collaborative Low-Rank Decomposers for Few-Shot Video Domain Adaptation

链接: https://arxiv.org/abs/2511.18711
作者: Yuyang Wanyan,Xiaoshan Yang,Weiming Dong,Changsheng Xu
机构: State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences (中国科学院自动化研究所多模态人工智能系统重点实验室); School of Artificial Intelligence, University of Chinese Academy of Sciences (中国科学院大学人工智能学院); PengCheng Laboratory (鹏城实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-145] CoD: A Diffusion Foundation Model for Image Compression

链接: https://arxiv.org/abs/2511.18706
作者: Zhaoyang Jia,Zihan Zheng,Naifu Xue,Jiahao Li,Bin Li,Zongyu Guo,Xiaoyi Zhang,Houqiang Li,Yan Lu
机构: University of Science and Technology of China (中国科学技术大学); Communication University of China (中国传媒大学); Microsoft Research Asia (微软亚洲研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-146] CNN-Based Camera Pose Estimation and Localisation of Scan Images for Aircraft Visual Inspection

链接: https://arxiv.org/abs/2511.18702
作者: Xueyan Oh,Leonard Loh,Shaohui Foong,Zhong Bao Andy Koh,Kow Leong Ng,Poh Kang Tan,Pei Lin Pearlin Toh,U-Xuan Tan
机构: Singapore University of Technology and Design (新加坡科技设计大学); ST Engineering Aerospace Ltd.
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注: 12 pages, 12 figures

点击查看摘要

[CV-147] ObjectAlign: Neuro-Symbolic Object Consistency Verification and Correction

链接: https://arxiv.org/abs/2511.18701
作者: Mustafa Munir,Harsh Goel,Xiwen Wei,Minkyu Choi,Sahil Shah,Kartikeya Bhardwaj,Paul Whatmough,Sandeep Chinchali,Radu Marculescu
机构: The University of Texas at Austin(德克萨斯大学奥斯汀分校); Qualcomm AI Research(高通人工智能研究中心)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Formal Languages and Automata Theory (cs.FL); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-148] Dendritic Convolution for Noise Image Recognition

链接: https://arxiv.org/abs/2511.18699
作者: Jiarui Xue,Dongjian Yang,Ye Sun,Gang Liu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 11 pages, 8 figures

点击查看摘要

[CV-149] Multimodal Real-Time Anomaly Detection and Industrial Applications

链接: https://arxiv.org/abs/2511.18698
作者: Aman Verma,Keshav Samdani,Mohd. Samiuddin Shafi
机构: 未知
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Multimedia (cs.MM)
备注:

点击查看摘要

[CV-150] Exploring Surround-View Fisheye Camera 3D Object Detection AAAI2026

链接: https://arxiv.org/abs/2511.18695
作者: Changcai Li,Wenwei Lin,Zuoxun Hou,Gang Chen,Wei Zhang,Huihui Zhou,Weishi Zheng
机构: 1. University of Science and Technology of China (中国科学技术大学); 2. Tsinghua University (清华大学); 3. Institute of Computing Technology, Chinese Academy of Sciences (中国科学院计算技术研究所)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages,6 figures, accepted at AAAI 2026

点击查看摘要

[CV-151] Stable Multi-Drone GNSS Tracking System for Marine Robots

链接: https://arxiv.org/abs/2511.18694
作者: Shuo Wen,Edwin Meriaux,Mariana Sosa Guzmán,Zhizun Wang,Junming Shi,Gregory Dudek
机构: McGill University (麦吉尔大学); MILA - Quebec AI Institute (魁北克人工智能研究所); Université Paris-Saclay (巴黎萨克雷大学)
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-152] VLM in a flash: I/O-Efficient Sparsification of Vision-Language Model via Neuron Chunking

链接: https://arxiv.org/abs/2511.18692
作者: Kichang Yang,Seonjun Kim,Minjae Kim,Nairan Zhang,Chi Zhang,Youngki Lee
机构: Seoul National University (首尔国立大学); Meta; Amazon
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Performance (cs.PF)
备注:

点击查看摘要

[CV-153] EVCC: Enhanced Vision Transformer-ConvNeXt-CoAtNet Fusion for Classification

链接: https://arxiv.org/abs/2511.18691
作者: Kazi Reyazul Hasan,Md Nafiu Rahman,Wasif Jalal,Sadif Ahmed,Shahriar Raj,Mubasshira Musarrat,Muhammad Abdullah Adnan
机构: Bangladesh University of Engineering and Technology (BUET)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-154] Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents

链接: https://arxiv.org/abs/2511.18685
作者: Dayong Liu,Chao Xu,Weihong Chen,Suyu Zhang,Juncheng Wang,Jiankang Deng,Baigui Sun,Yang Liu
机构: Zhejiang University (浙江大学); Wolf 1069B, Sany Group; The Hong Kong Polytechnic University (香港理工大学); Imperial College London
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-155] Now You See It Now You Dont - Instant Concept Erasure for Safe Text-to-Image and Video Generation

链接: https://arxiv.org/abs/2511.18684
作者: Shristi Das Biswas,Arani Roy,Kaushik Roy
机构: Purdue University (普渡大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-156] Hierarchical GraphCut Phase Unwrapping based on Invariance of Diffeomorphisms Framework ICIP2025

链接: https://arxiv.org/abs/2511.18682
作者: Xiang Gao,Xinmu Wang,Zhou Zhao,Junqi Huang,Xianfeng David Gu
机构: Stony Brook University (石溪大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Open Journal of Signal Processing (OJSP) as journal paper for ICIP2025 Accepted

点击查看摘要

[CV-157] Inverse Rendering for High-Genus Surface Meshes from Multi-View Images

链接: https://arxiv.org/abs/2511.18680
作者: Xiang Gao,Xinmu Wang,Xiaolong Wu,Jiazhi Li,Jingyu Shi,Yu Guo,Yuanpeng Liu,Xiyun Song,Heather Yu,Zongfang Lin,Xianfeng David Gu
机构: Futurewei Technologies(未来wei科技); Stony Brook University (石溪大学); Purdue University (普渡大学); University of Southern California (南加州大学); George Mason University (乔治梅森大学)
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV)
备注: 3DV2026 Accepted (Poster)

点击查看摘要

[CV-158] Neural Geometry Image-Based Representations with Optimal Transport (OT) WACV2026

链接: https://arxiv.org/abs/2511.18679
作者: Xiang Gao,Yuanpeng Liu,Xinmu Wang,Jiazhi Li,Minghao Guo,Yu Guo,Xiyun Song,Heather Yu,Zhiqiang Lao,Xianfeng David Gu
机构: Futurewei Technologies(未来wei科技公司); Stony Brook University (石溪大学); University of Southern California (南加州大学); Massachusetts Institute of Technology (麻省理工学院); George Mason University (乔治梅森大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: WACV2026 Rround 2 Accepted

点击查看摘要

[CV-159] A Theory-Inspired Framework for Few-Shot Cross-Modal Sketch Person Re-Identification AAAI2026

链接: https://arxiv.org/abs/2511.18677
作者: Yunpeng Gong,Yongjie Hou,Jiangming Shi,Kim Long Diep,Min Jiang
机构: Xiamen University (厦门大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by AAAI2026

点击查看摘要

[CV-160] MedVision: Dataset and Benchmark for Quantitative Medical Image Analysis

链接: https://arxiv.org/abs/2511.18676
作者: Yongcheng Yao,Yongshuo Zong,Raman Dutt,Yongxin Yang,Sotirios A Tsaftaris,Timothy Hospedales
机构: University of Edinburgh (爱丁堡大学); Queen Mary University of London (伦敦玛丽女王大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 8 pages, 8 figures, 4 tables

点击查看摘要

[CV-161] Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers

链接: https://arxiv.org/abs/2511.18673
作者: Yiqing Shi,Yiren Song,Mike Zheng Shou
机构: Peking University (北京大学); Show Lab; National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-162] Sphinx: Efficiently Serving Novel View Synthesis using Regression-Guided Selective Refinement

链接: https://arxiv.org/abs/2511.18672
作者: Yuchen Xia,Souvik Kundu,Mosharaf Chowdhury,Nishil Talati
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-163] Deterministic Continuous Replacement: Fast and Stable Module Replacement in Pretrained Transformers NEURIPS2025

链接: https://arxiv.org/abs/2511.18670
作者: Rowan Bradbury,Aniket Srinivasan Ashok,Sai Ram Kasanagottu,Gunmay Jhingran,Shuai Meng
机构: Bradbury Group; University of Waterloo (滑铁卢大学); SUNY Stony Brook (纽约州立大学石溪分校); Delhi Technological University (德里技术大学); UC Berkeley (加州大学伯克利分校)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to NeurIPS 2025 ScaleOPT Workshop; 8 pages; includes figures

点击查看摘要

[CV-164] Data Augmentation Strategies for Robust Lane Marking Detection

链接: https://arxiv.org/abs/2511.18668
作者: Flora Lian,Dinh Quang Huynh,Hector Penades,J. Stephany Berrio Perez,Mao Shan,Stewart Worrall
机构: Australian Centre for Robotics (澳大利亚机器人中心); The University of Sydney (悉尼大学); Insurance Australia Group Limited (保险澳大利亚集团有限公司); iMOVE CRC; Cooperative Research Centres program; MCIN/AEI; European Regional Development Fund (欧洲区域发展基金)
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注: 8 figures, 2 tables, 10 pages, ACRA, Australasian conference on robotics and automation

点击查看摘要

[CV-165] Robust Physical Adversarial Patches Using Dynamically Optimized Clusters

链接: https://arxiv.org/abs/2511.18656
作者: Harrison Bagley,Will Meakin,Simon Lucey,Yee Wei Law,Tat-Jun Chin
机构: Australian Institute for Machine Learning (澳大利亚机器学习研究所); The University of Adelaide (阿德莱德大学); UniSA STEM, University of South Australia (南澳大学STEM学院); SmartSat CRC (智能卫星CRC)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Supplementary material available at: this https URL

点击查看摘要

[CV-166] From Healthy Scans to Annotated Tumors: A Tumor Fabrication Framework for 3D Brain MRI Synthesis

链接: https://arxiv.org/abs/2511.18654
作者: Nayu Dong,Townim Chowdhury,Hieu Phan,Mark Jenkinson,Johan Verjans,Zhibin Liao
机构: Australian Institute for Machine Learning (澳大利亚机器学习研究所); The University of Adelaide (阿德莱德大学); School of Computer and Mathematical Sciences (计算机与数学科学学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-167] Health system learning achieves generalist neuroimaging models

链接: https://arxiv.org/abs/2511.18640
作者: Akhil Kondepudi,Akshay Rao,Chenhui Zhao,Yiwei Lyu,Samir Harake,Soumyanil Banerjee,Rushikesh Joshi,Anna-Katharina Meissner,Renly Hou,Cheng Jiang,Asadur Chowdury,Ashok Srinivasan,Brian Athey,Vikas Gulani,Aditya Pandey,Honglak Lee,Todd Hollon
机构: University of Michigan; University of Michigan Computational Medicine and Bioinformatics; University of Michigan Computer Science and Engineering; University of Michigan Neurosugery; University of Cologne Neurosugery; University of Michigan Radiology
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 53 pages, 4 main figures, 10 extended data figures

点击查看摘要

[CV-168] Functional Localization Enforced Deep Anomaly Detection Using Fundus Images

链接: https://arxiv.org/abs/2511.18627
作者: Jan Benedikt Ruhland,Thorsten Papenbrock,Jan-Peter Sowa,Ali Canbay,Nicole Eter,Bernd Freisleben,Dominik Heider
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-169] AutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations

链接: https://arxiv.org/abs/2511.18617
作者: Litian Gong(1),Fatemeh Bahrani(2),Yutai Zhou(2),Amin Banayeeanzade(2),Jiachen Li(1),Erdem Biyik(2) ((1) University of California, Riverside, USA, (2) University of Southern California, USA)
机构: University of California, Riverside (加州大学河滨分校); University of Southern California (南加州大学)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 6 figures. Code and datasets available at this http URL

点击查看摘要

[CV-170] RigAnyFace: Scaling Neural Facial Mesh Auto-Rigging with Unlabeled Data NEURIPS2025

链接: https://arxiv.org/abs/2511.18601
作者: Wenchao Ma,Dario Kneubuehler,Maurice Chu,Ian Sachs,Haomiao Jiang,Sharon Xiaolei Huang
机构: Penn State University (宾夕法尼亚州立大学); Roblox
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by NeurIPS 2025

点击查看摘要

[CV-171] NeAR: Coupled Neural Asset-Renderer Stack

链接: https://arxiv.org/abs/2511.18600
作者: Hong Li,Chongjie Ye,Houyuan Chen,Weiqing Xiao,Ziyang Yan,Lixing Xiao,Zhaoxi Chen,Jianfeng Xiang,Shaocong Xu,Xuhui Liu,Yikai Wang,Baochang Zhang,Xiaoguang Han,Jiaolong Yang,Hao Zhao
机构: BAAI; BUAA; FNii, CUHKSZ; NJU; UniTn; ZJU; NTU; THU; BNU; SSE, CUHKSZ; MSRA; AIR, THU
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 20 pages, 16 figures

点击查看摘要

[CV-172] Stage-Specific Benchmarking of Deep Learning Models for Glioblastoma Follow-Up MRI

链接: https://arxiv.org/abs/2511.18595
作者: Wenhao Guo,Golrokh Mirzaei
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 17 pages, 11 figures

点击查看摘要

[CV-173] Zero-Reference Joint Low-Light Enhancement and Deblurring via Visual Autoregressive Modeling with VLM-Derived Modulation AAAI2026

链接: https://arxiv.org/abs/2511.18591
作者: Wei Dong,Han Zhou,Junwei Lin,Jun Chen
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by AAAI 2026; First Var-based method for joint LLIE and deblurring

点击查看摘要

[CV-174] PhysGS: Bayesian-Inferred Gaussian Splatting for Physical Property Estimation CVPR2026

链接: https://arxiv.org/abs/2511.18570
作者: Samarth Chopra,Jing Liang,Gershom Seneviratne,Dinesh Manocha
机构: University of Maryland, College Park (马里兰大学学院市分校); Stanford University (斯坦福大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: Submitted to CVPR 2026

点击查看摘要

[CV-175] C3Po: Cross-View Cross-Modality Correspondence by Pointmap Prediction NEURIPS2025

链接: https://arxiv.org/abs/2511.18559
作者: Kuan Wei Huang,Brandon Li,Bharath Hariharan,Noah Snavely
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: NeurIPS 2025

点击查看摘要

[CV-176] mePre: Bridging Accuracy Efficiency and Stability in Probabilistic Time-Series Forecasting

链接: https://arxiv.org/abs/2511.18539
作者: Lingyu Jiang,Lingyu Xu,Peiran Li,Qianwen Ge,Dingyi Zhuang,Shuo Xing,Wenjing Chen,Xiangbo Gao,Ting-Hsuan Chen,Xueying Zhan,Xin Zhang,Ziming Zhang,Zhengzhong Tu,Michael Zielewski,Kazunori Yamada,Fangzhou Lin
机构: Tohoku University (东北大学); WPI; Texas A&M University (德克萨斯农工大学); University of Wisconsin-Madison (威斯康星大学麦迪逊分校); UIUC (伊利诺伊大学厄巴纳-香槟分校); Georgia Tech (佐治亚理工学院); MIT (麻省理工学院); University of Southern California (南加州大学); San Diego State University (圣地亚哥州立大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: 15 pages, 5 figures, 6 tables

点击查看摘要

[CV-177] Zero-Shot Video Deraining with Video Diffusion Models WACV2026

链接: https://arxiv.org/abs/2511.18537
作者: Tuomas Varanka,Juan Luis Gonzalez,Hyeongwoo Kim,Pablo Garrido,Xu Yao
机构: University of Oulu(奥卢大学); Flawless AI(无瑕人工智能)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: WACV 2026

点击查看摘要

[CV-178] HiFi-MambaV2: Hierarchical Shared-Routed MoE for High-Fidelity MRI Reconstruction

链接: https://arxiv.org/abs/2511.18534
作者: Pengcheng Fang,Hongli Chen,Guangzhen Yao,Jian Shi,Fangfang Tang,Xiaohao Cai,Shanshan Shan,Feng Liu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-179] DE-KAN: A Kolmogorov Arnold Network with Dual Encoder for accurate 2D Teeth Segmentation

链接: https://arxiv.org/abs/2511.18533
作者: Md Mizanur Rahman Mustakim,Jianwu Li,Sumya Bhuiyan,Mohammad Mehedi Hasan,Bing Han
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-180] Breaking Forgetting: Training-Free Few-Shot Class-Incremental Learning via Conditional Diffusion

链接: https://arxiv.org/abs/2511.18516
作者: Haidong Kang,Ketong Qian,Yi Lu
机构: Northeastern University (东北大学); Donghua University (东华大学); Johns Hopkins University (约翰霍普金斯大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-181] Unified Deep Learning Platform for Dust and Fault Diagnosis in Solar Panels Using Thermal and Visual Imaging

链接: https://arxiv.org/abs/2511.18514
作者: Abishek Karthik,Sreya Mynampati,Pandiyaraju V
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-182] LRDUN: A Low-Rank Deep Unfolding Network for Efficient Spectral Compressive Imaging

链接: https://arxiv.org/abs/2511.18513
作者: He Huang,Yujun Guo,Wei He
机构: LIESMARS, Wuhan University, Wuhan, China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 17 pages, 16 figures,

点击查看摘要

[CV-183] Multimodal Continual Learning with MLLM s from Multi-scenario Perspectives CVPR2026

链接: https://arxiv.org/abs/2511.18507
作者: Kai Jiang,Siqi Huang,Xiangyu Chen,Jiawei Shao,Hongyuan Zhang,Xuelong Li
机构: Northwestern Polytechnical University (西北工业大学); China Telecom (中国电信); University of Hong Kong (香港大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 18 pages, 16 figures. This is a preprint version of a paper submitted to CVPR 2026

点击查看摘要

[CV-184] Extreme Model Compression for Edge Vision-Language Models: Sparse Temporal Token Fusion and Adaptive Neural Compression

链接: https://arxiv.org/abs/2511.18504
作者: Md Tasnin Tanvir,Soumitra Das,Sk Md Abidar Rahaman,Ali Shiri Sichani
机构: University of Information Technology and Sciences (信息科技与科学大学); The University of Burdwan (布德万大学); Tarakeswar Degree College (塔拉克瑟瓦尔学院); University of Missouri, Columbia (密苏里大学哥伦比亚分校)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages, 6 figures

点击查看摘要

[CV-185] Uncertainty Quantification in HSI Reconstruction using Physics-Aware Diffusion Priors and Optics-Encoded Measurements

链接: https://arxiv.org/abs/2511.18473
作者: Juan Romero,Qiang Fu,Matteo Ravasi,Wolfgang Heidrich
机构: King Abdullah University of Science and Technology (KAUST); Shearwater Geoservices
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-186] Robust Posterior Diffusion-based Sampling via Adaptive Guidance Scale

链接: https://arxiv.org/abs/2511.18471
作者: Liav Hen,Tom Tirer,Raja Giryes,Shady Abu-Hussein
机构: Tel Aviv University (特拉维夫大学); Bar-Ilan University (巴伊兰大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-187] Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span NEURIPS2025

链接: https://arxiv.org/abs/2511.18470
作者: Heeseung Yun,Joonil Na,Jaeyeon Kim,Calvin Murdock,Gunhee Kim
机构: Seoul National University (首尔国立大学); Carnegie Mellon University (卡内基梅隆大学); Reality Labs Research at Meta (Meta现实实验室研究)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: NeurIPS 2025 Spotlight

点击查看摘要

[CV-188] SloMo-Fast: Slow-Momentum and Fast-Adaptive Teachers for Source-Free Continual Test-Time Adaptation

链接: https://arxiv.org/abs/2511.18468
作者: Md Akil Raihan Iftee,Mir Sazzat Hossain,Rakibul Hasan Rajib,Tariq Iqbal,Md Mofijul Islam,M Ashraful Amin,Amin Ahsan Ali,AKM Mahbubur Rahman
机构: Center for Computational & Data Sciences, Independent University, Bangladesh; University of Central Florida, USA; University of Virginia, USA; Amazon GenAI, USA
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: 38 pages, 38 tables, 16 figures

点击查看摘要

[CV-189] Alternating Perception-Reasoning for Hallucination-Resistant Video Understanding

链接: https://arxiv.org/abs/2511.18463
作者: Bowei Pu,Chuanbin Liu,Yifan Ge,Peichen Zhou,Yiwei Sun,Zhiyin Lu,Jiankang Wang,Hongtao Xie
机构: University of Science and Technology of China (中国科学技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 32 pages, 36 figures

点击查看摘要

[CV-190] Radiation-Preserving Selective Imaging for Pediatric Hip Dysplasia: A Cross-Modal Ultrasound-Xray Policy with Limited Labels ALT AAAI2026

链接: https://arxiv.org/abs/2511.18457
作者: Duncan Stothers,Ben Stothers,Emily Schaeffer,Kishore Mulpuri
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted (with oral presentation) to the AAAI 2026 AIMedHealth Bridge Program

点击查看摘要

[CV-191] RegDeepLab: A Two-Stage Decoupled Framework for Interpretable Embryo Frag mentation Grading

链接: https://arxiv.org/abs/2511.18454
作者: Ming-Jhe Lee
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 7 pages, 5 figures

点击查看摘要

[CV-192] NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering

链接: https://arxiv.org/abs/2511.18452
作者: Loick Chambon,Paul Couairon,Eloi Zablocki,Alexandre Boulch,Nicolas Thome,Matthieu Cord
机构: Valeo.ai(维宝人工智能); Sorbonne Université(索邦大学); CNRS(法国国家科学研究中心); ISIR(机器人与智能系统研究所); Institut Universitaire de France(法国大学研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Code: this https URL

点击查看摘要

[CV-193] EventBench: Towards Comprehensive Benchmarking of Event-based MLLM s

链接: https://arxiv.org/abs/2511.18448
作者: Shaoyu Liu,Jianing Li,Guanghui Zhao,Yunjian Zhang,Xiangyang Ji
机构: Xidian University (西安电子科技大学); Tsinghua University (清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-194] SineProject: Machine Unlearning for Stable Vision Language Alignment

链接: https://arxiv.org/abs/2511.18444
作者: Arpit Garg,Hemanth Saratchandran,Simon Lucey
机构: Australian Institute for Machine Learning (澳大利亚机器学习研究所); The University of Adelaide (阿德莱德大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: In Submission

点击查看摘要

[CV-195] ReCoGS: Real-time ReColoring for Gaussian Splatting scenes

链接: https://arxiv.org/abs/2511.18441
作者: Lorenzo Rutayisire,Nicola Capodieci,Fabio Pellacini
机构: University of Modena and Reggio Emilia (摩德纳和雷焦艾米利亚大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR)
备注: Project page is available at this https URL

点击查看摘要

[CV-196] Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning

链接: https://arxiv.org/abs/2511.18437
作者: Chi Zhang,Haibo Qiu,Qiming Zhang,Yufei Xu,Zhixiong Zeng,Siqi Yang,Peng Shi,Lin Ma,Jing Zhang
机构: Wuhan University (武汉大学); Meituan Inc (美团); The University of Sydney (悉尼大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-197] When Generative Replay Meets Evolving Deepfakes: Domain-Aware Relative Weighting for Incremental Face Forgery Detection

链接: https://arxiv.org/abs/2511.18436
作者: Hao Shen,Jikang Cheng,Renye Yan,Zhongyuan Wang,Wei Peng,Baojin Huang
机构: Huazhong Agricultural University (华中农业大学); Peking University (北京大学); Wuhan University (武汉大学); Stanford University (斯坦福大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-198] DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation

链接: https://arxiv.org/abs/2511.18434
作者: Yongkun Du,Pinxuan Chen,Xuye Ying,Zhineng Chen
机构: Fudan University (复旦大学); Institute of Trustworthy Embodied AI, Fudan University (复旦大学可信具身人工智能研究所)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-199] LungX: A Hybrid EfficientNet-Vision Transformer Architecture with Multi-Scale Attention for Accurate Pneumonia Detection

链接: https://arxiv.org/abs/2511.18425
作者: Mansur Yerzhanuly
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 13 pages, 3 figures, 1 table

点击查看摘要

[CV-200] CrossJEPA: Cross-Modal Joint-Embedding Predictive Architecture for Efficient 3D Representation Learning from 2D Images

链接: https://arxiv.org/abs/2511.18424
作者: Avishka Perera,Kumal Hewagamage,Saeedha Nazar,Kavishka Abeywardana,Hasitha Gallella,Ranga Rodrigo,Mohamed Afham
机构: University of Moratuwa (莫鲁塔瓦大学); Technische Universität Darmstadt (达姆施塔特工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 24 pages, 10 figures

点击查看摘要

[CV-201] NeuroVascU-Net: A Unified Multi-Scale and Cross-Domain Adaptive Feature Fusion U-Net for Precise 3D Segmentation of Brain Vessels in Contrast-Enhanced T1 MRI

链接: https://arxiv.org/abs/2511.18422
作者: Mohammad Jafari Vayeghan,Niloufar Delfan,Mehdi Tale Masouleh,Mansour Parvaresh Rizi,Behzad Moshiri
机构: University of Tehran (德黑兰大学); York University (约克大学); Iran University of Medical Sciences (伊朗医科大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-202] Categorical Equivariant Deep Learning: Category-Equivariant Neural Networks and Universal Approximation Theorems

链接: https://arxiv.org/abs/2511.18417
作者: Yoshihiro Maruyama
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-203] 4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation

链接: https://arxiv.org/abs/2511.18416
作者: Haonan Wang,Hanyu Zhou,Haoyue Liu,Luxin Yan
机构: Huazhong University of Science and Technology (华中科技大学); National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-204] Self-Empowering VLMs: Achieving Hierarchical Consistency via Self-Elicited Knowledge Distillation

链接: https://arxiv.org/abs/2511.18415
作者: Wei Yang,Yiran Zhu,Zilin Li,Xunjia Zhang,Hongtao Wang
机构: North China Electric Power University (华北电力大学); Donghua University (东华大学)
类目: Multimedia (cs.MM); Computer Vision and Pattern Recognition (cs.CV)
备注: 21 pages, 18 tables, 6 figures

点击查看摘要

[CV-205] ChineseVideoBench: Benchmarking Multi-modal Large Models for Chinese Video Question Answering

链接: https://arxiv.org/abs/2511.18399
作者: Yuxiang Nie,Han Wang,Yongjie Ye,Haiyang Yu,Weitao Jia,Tao Zeng,Hao Feng,Xiang Fei,Yang Li,Xiaohui Lv,Guozhi Tang,Jingqun Tang,Jinghui Lu,Zehui Dai,Jiacong Wang,Dingkang Yang,An-Lan Wang,Can Huang
机构: Bytedance Inc.
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-206] Exploring Weak-to-Strong Generalization for CLIP-based Classification

链接: https://arxiv.org/abs/2511.18396
作者: Jinhao Li,Sarah M. Erfani,Lei Feng,James Bailey,Feng Liu
机构: University of Melbourne (墨尔本大学); Southeast University (东南大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: TMLR

点击查看摘要

[CV-207] SegSplat: Feed-forward Gaussian Splatting and Open-Set Semantic Segmentation

链接: https://arxiv.org/abs/2511.18386
作者: Peter Siegel,Federico Tombari,Marc Pollefeys,Daniel Barath
机构: ETH Zürich (苏黎世联邦理工学院); Google (谷歌); Microsoft (微软)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-208] Can a Second-View Image Be a Language? Geometric and Semantic Cross-Modal Reasoning for X-ray Prohibited Item Detection

链接: https://arxiv.org/abs/2511.18385
作者: Chuang Peng,Renshuai Tao,Zhongwei Ren,Xianglong Liu,Yunchao Wei
机构: Beijing Jiaotong University (北京交通大学); Beihang University (北京航空航天大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 10 pages, 4 figures

点击查看摘要

[CV-209] ViMix-14M: A Curated Multi-Source Video-Text Dataset with Long-Form High-Quality Captions and Crawl-Free Access

链接: https://arxiv.org/abs/2511.18382
作者: Timing Yang,Sucheng Ren,Alan Yuille,Feng Wang
机构: Johns Hopkins University (约翰霍普金斯大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-210] RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba Models

链接: https://arxiv.org/abs/2511.18380
作者: Timing Yang,Guoyizhe Wei,Alan Yuille,Feng Wang
机构: Johns Hopkins University (约翰霍普金斯大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-211] Synthetic Curriculum Reinforces Compositional Text-to-Image Generation

链接: https://arxiv.org/abs/2511.18378
作者: Shijian Wang,Runhao Fu,Siyi Zhao,Qingqin Zhan,Xingjian Wang,Jiarui Jin,Yuan Lu,Hanqian Wu,Cunjian Chen
机构: Southeast University (东南大学); Xiaohongshu Inc. (小红书公司); Monash University (莫纳什大学); Shanghai Jiao Tong University (上海交通大学); Anhui University (安徽大学); Independent Researcher (独立研究者)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-212] MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models

链接: https://arxiv.org/abs/2511.18373
作者: Xiyang Wu,Zongxia Li,Jihui Jin,Guangyao Shi,Gouthaman KV,Vishnu Raj,Nilotpal Sinha,Jingxi Chen,Fan Du,Dinesh Manocha
机构: University of Maryland (马里兰大学); Dolby Laboratories (杜比实验室); University of Southern California (南加州大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-213] MimiCAT: Mimic with Correspondence-Aware Cascade-Transformer for Category-Free 3D Pose Transfer

链接: https://arxiv.org/abs/2511.18370
作者: Zenghao Chai,Chen Tang,Yongkang Wong,Xulei Yang,Mohan Kankanhalli
机构: National University of Singapore (新加坡国立大学); The Chinese University of Hong Kong (香港中文大学); A∗STAR (新加坡科技研究局)
类目: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR)
备注: tech report

点击查看摘要

[CV-214] Alias-free 4D Gaussian Splatting

链接: https://arxiv.org/abs/2511.18367
作者: Zilong Chen,Huan-ang Gao,Delin Qu,Haohan Chi,Hao Tang,Kai Zhang,Hao Zhao
机构: Tsinghua Shenzhen International Graduate School, Tsinghua University (清华大学深圳国际研究生院，清华大学); Institute for AI Industry Research (AIR), Tsinghua University (清华大学人工智能产业研究院); Beijing Academy of Artificial Intelligence, BAAI (北京智源研究院); Fudan University (复旦大学); Peking University (北京大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-215] RANSPORTER: Transferring Visual Semantics from VLM Manifolds

链接: https://arxiv.org/abs/2511.18359
作者: Alexandros Stergiou
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-216] Enhancing UAV Search under Occlusion using Next Best View Planning

链接: https://arxiv.org/abs/2511.18353
作者: Sigrid Helene Strand,Thomas Wiedemann,Bram Burczek,Dmitriy Shutin
机构: German Aerospace Center (Deutsches Zentrum für Luft- und Raumfahrt, DLR); Technische Universität München (TUM)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注: Submitted to IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

点击查看摘要

[CV-217] MagicWand: A Universal Agent for Generation and Evaluation Aligned with User Preference

链接: https://arxiv.org/abs/2511.18352
作者: Zitong Xu,Dake Shen,Yaosong Du,Kexiang Hao,Jinghan Huang,Xiande Huang
机构: Shanghai Jiao Tong University (上海交通大学); De Artificial Intelligence Lab (人工智能实验室); The Chinese University of Hong Kong, Shenzhen (香港中文大学（深圳)）
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-218] FlowPortal: Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement

链接: https://arxiv.org/abs/2511.18346
作者: Wenshuo Gao,Junyi Fan,Jiangyue Zeng,Shuai Yang
机构: Peking University (北京大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project Page: this https URL

点击查看摘要

[CV-219] A Tri-Modal Dataset and a Baseline System for Tracking Unmanned Aerial Vehicles

链接: https://arxiv.org/abs/2511.18344
作者: Tianyang Xu,Jinjie Gu,Xuefeng Zhu,XiaoJun Wu,Josef Kittler
机构: Jiangnan University (江南大学); University of Surrey (萨里大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-220] Auxiliary Gene Learning: Spatial Gene Expression Estimation by Auxiliary Gene Selection AAAI

链接: https://arxiv.org/abs/2511.18336
作者: Kaito Shiku,Kazuya Nishimura,Shinnosuke Matsuo,Yasuhiro Kojima,Ryoma Bise
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Genomics (q-bio.GN)
备注: Accepted to Association for the Advancement of Artificial Intelligence (AAAI) 2026

点击查看摘要

[CV-221] ConsistCompose: Unified Multimodal Layout Control for Image Composition

链接: https://arxiv.org/abs/2511.18333
作者: Xuanke Shi,Boxuan Li,Xiaoyang Han,Zhongang Cai,Lei Yang,Dahua Lin,Quan Wang
机构: SenseTime Research (商汤科技研究部)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 22 pages, 17 figures

点击查看摘要

[CV-222] SciPostLayoutTree: A Dataset for Structural Analysis of Scientific Posters

链接: https://arxiv.org/abs/2511.18329
作者: Shohei Tanaka,Atsushi Hashimoto,Yoshitaka Ushiku
机构: OMRON SINICX Corporation (欧姆龙Sinicx公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-223] General vs Domain-Specific CNNs: Understanding Pretraining Effects on Brain MRI Tumor Classification

链接: https://arxiv.org/abs/2511.18326
作者: Helia Abedini,Saba Rahimi,Reza Vaziri
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-224] Learning Visually Interpretable Oscillator Networks for Soft Continuum Robots from Video

链接: https://arxiv.org/abs/2511.18322
作者: Henrik Krauss,Johann Licher,Naoya Takeishi,Annika Raatz,Takehisa Yairi
机构: The University of Tokyo (东京大学); Leibniz University Hannover (汉诺威莱布尼茨大学); Research Center for Advanced Science and Technology (先进科学与技术研究中心)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-225] Optimal Pose Guidance for Stereo Calibration in 3D Deformation Measurement

链接: https://arxiv.org/abs/2511.18317
作者: Dongcai Tan,Shunkun Liang,Bin Li,Banglei Guan,Ang Su,Yuan Lin,Dapeng Zhang,Minggang Wan,Zibin Liu,Chenglong Wang,Jiajian Zhu,Zhang Li,Yang Shang,Qifeng Yu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-226] Stro-VIGRU: Defining the Vision Recurrent-Based Baseline Model for Brain Stroke Classification

链接: https://arxiv.org/abs/2511.18316
作者: Subhajeet Das,Pritam Paul,Rohit Bahadur,Sohan Das
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Presented at the International Conference on Computational Intelligence and Data Communication, Accepted for publication in the Taylor and Francis Conference Proceedings

点击查看摘要

[CV-227] ScriptViT: Vision Transformer-Based Personalized Handwriting Generation

链接: https://arxiv.org/abs/2511.18307
作者: Sajjan Acharya,Rajendra Baskota
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-228] DiVE-k: Differential Visual Reasoning for Fine-grained Image Recognition

链接: https://arxiv.org/abs/2511.18305
作者: Raja Kumar,Arka Sadhu,Ram Nevatia
机构: University of Southern California (南加州大学); Meta
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-229] SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes

链接: https://arxiv.org/abs/2511.18290
作者: Jungho Lee,Minhyeok Lee,Sunghun Yang,Minseok Kang,Sangyoun Lee
机构: Yonsei University (延世大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Project Page: this https URL

点击查看摘要

[CV-230] RIDENT: A Trimodal Cascade Generative Framework for Drug and RNA-Conditioned Cellular Morphology Synthesis

链接: https://arxiv.org/abs/2511.18287
作者: Rui Peng,Ziru Liu,Lingyuan Ye,Yuxing Lu,Boxin Shi,Jinzhuo Wang
机构: Peking University (北京大学); Tsinghua University (清华大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Quantitative Methods (q-bio.QM)
备注:

点击查看摘要

[CV-231] RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System AAAI2026

链接: https://arxiv.org/abs/2511.18286
作者: Runwei Guan,Rongsheng Hu,Shangshu Chen,Ningyuan Xiao,Xue Xia,Jiayang Liu,Beibei Chen,Ziren Tang,Ningwei Ouyang,Shaofeng Liang,Yuxuan Fan,Wanjie Sun,Yutao Yue
机构: Hong Kong University of Science and Technology (Guangzhou)(香港科技大学（广州）); Institute of Automation, Chinese Academy of Sciences (中国科学院自动化研究所); Shanghai Jiao Tong University (上海交通大学); Tsinghua University (清华大学); Zhejiang University (浙江大学); Beijing Institute of Technology (北京理工大学); Harbin Institute of Technology (哈尔滨工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages, 6 figures, accepted by AAAI 2026. The model is also called Dream, to the other me in the world forever

点击查看摘要

[CV-232] Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation CVPR2026

链接: https://arxiv.org/abs/2511.18281
作者: Yara Bahram,Melodie Desbos,Mohammadhadi Shateri,Eric Granger
机构: LIVIA, Dept. of Systems Engineering, ETS Montreal, Canada(加拿大蒙特利尔工程学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Under review paper at CVPR 2026

点击查看摘要

[CV-233] From Tables to Signals: Revealing Spectral Adaptivity in TabPFN

链接: https://arxiv.org/abs/2511.18278
作者: Jianqiao Zheng,Cameron Gordon,Yiping Ji,Hemanth Saratchandran,Simon Lucey
机构: Australian Institute for Machine Learning (澳大利亚机器学习研究所); University of Adelaide (阿德莱德大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-234] Point-to-Point: Sparse Motion Guidance for Controllable Video Editing

链接: https://arxiv.org/abs/2511.18277
作者: Yeji Song,Jaehyun Lee,Mijin Koo,JunHoo Lee,Nojun Kwak
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-235] Vision Token Masking Alone Cannot Prevent PHI Leakage in Medical Document OCR: A Systematic Evaluation

链接: https://arxiv.org/abs/2511.18272
作者: Richard J. Young
机构: Deepneuro.AI(Deepneuro.AI); University of Nevada, Las Vegas(内华达大学拉斯维加斯分校)
类目: Computer Vision and Pattern Recognition (cs.CV); Cryptography and Security (cs.CR)
备注: 24 pages, 11 figures, 2 tables

点击查看摘要

[CV-236] Beyond Words and Pixels: A Benchmark for Implicit World Knowledge Reasoning in Generative Models

链接: https://arxiv.org/abs/2511.18271
作者: Tianyang Han,Junhao Su,Junjie Hu,Peizhen Yang,Hengyu Shi,Junfeng Luo,Jialin Gao
机构: MeiGen AI Team, Meituan(美团); Fudan University (复旦大学); D4D^{4} Lab; HHMI Janelia Research Campus
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-237] SatSAM2: Motion-Constrained Video Object Tracking in Satellite Imagery using Promptable SAM2 and Kalman Priors

链接: https://arxiv.org/abs/2511.18264
作者: Ruijie Fan,Junyan Ye,Huan Chen,Zilong Huang,Xiaolei Wang,Weijia Li
机构: Sun Yat-Sen University (中山大学); Shanghai AI Laboratory (上海人工智能实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-238] MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation

链接: https://arxiv.org/abs/2511.18262
作者: Tao Shen,Xin Wan,Taicai Chen,Rui Zhang,Junwen Pan,Dawei Lu,Fanding Lei,Zhilin Lu,Yunfei Yang,Chen Cheng,Qi She,Chang Liu,Zhenbang Sun
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-239] Sequence-Adaptive Video Prediction in Continuous Streams using Diffusion Noise Optimization

链接: https://arxiv.org/abs/2511.18255
作者: Sina Mokhtarzadeh Azar,Emad Bahrami,Enrico Pallotta,Gianpiero Francesca,Radu Timofte,Juergen Gall
机构: University of Bonn (波恩大学); Toyota Motor Europe (丰田汽车欧洲公司); University of Wuerzburg (维尔茨堡大学); Lamarr Institute for Machine Learning and Artificial Intelligence (拉马尔机器学习与人工智能研究所)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-240] UniFlow: Towards Zero-Shot LiDAR Scene Flow for Autonomous Vehicles via Cross-Domain Generalization

链接: https://arxiv.org/abs/2511.18254
作者: Siyi Li,Qingwen Zhang,Ishan Khatri,Kyle Vedder,Deva Ramanan,Neehar Peri
机构: University of Pennsylvania (宾夕法尼亚大学); KTH Royal Institute of Technology (皇家理工学院); Carnegie Mellon University (卡内基梅隆大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project Page: this https URL

点击查看摘要

[CV-241] Coherent Multi-Agent Trajectory Forecasting in Team Sports with CausalTraj AAAI2026

链接: https://arxiv.org/abs/2511.18248
作者: Wei Zhen Teoh
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages, 3 figures, accepted to the AI4TS Workshop at AAAI 2026

点击查看摘要

[CV-242] EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning

链接: https://arxiv.org/abs/2511.18242
作者: Yogesh Kulkarni,Pooyan Fazli
机构: Arizona State University (亚利桑那州立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-243] Parallel qMRI Reconstruction from 4x Accelerated Acquisitions

链接: https://arxiv.org/abs/2511.18232
作者: Mingi Kang
机构: Bowdoin College (鲍登学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-244] Using MLIR Transform to Design Sliced Convolution Algorithm

链接: https://arxiv.org/abs/2511.18222
作者: Victor Ferrari,Marcio Pereira,Lucas Alvarenga,Gustavo Leite,Guido Araujo
机构: IBM Research; Celera Systems; Instituto de Computação, Universidade Estadual de Campinas (坎皮纳斯州立大学计算机学院), Brazil
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Performance (cs.PF)
备注:

点击查看摘要

[CV-245] Large-Scale Pre-training Enables Multimodal AI Differentiation of Radiation Necrosis from Brain Metastasis Progression on Routine MRI

链接: https://arxiv.org/abs/2511.18208
作者: Ahmed Gomaa,Annette Schwarz,Ludwig Singer,Arnd Dörfler,Matthias Stefan May,Pluvio Stephan,Ishita Sheth,Juliane Szkitsak,Katharina Breininger,Yixing Huang,Benjamin Frey,Oliver Schnell,Daniel Delev,Roland Coras,Daniel Höfler,Philipp Schubert,Jenny Stritzelberger,Sabine Semrau,Andreas Maier,Dieter H Heiland,Udo S. Gaipl,Andrea Wittig,Rainer Fietkau,Christoph Bert,Stefanie Corradini,Florian Putz
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-246] Generating Synthetic Human Blastocyst Images for In-Vitro Fertilization Blastocyst Grading

链接: https://arxiv.org/abs/2511.18204
作者: Pavan Narahari,Suraj Rajendran,Lorena Bori,Jonas E. Malmsten,Qiansheng Zhan,Zev Rosenwaks,Nikica Zaninovic,Iman Hajirasouliha
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: The manuscript is 23 pages, with five main figures and one table. The supplemental material includes 23 pages with fourteen figures and four tables

点击查看摘要

[CV-247] InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity

链接: https://arxiv.org/abs/2511.18200
作者: Haoming Wang,Qiyao Xue,Wei Gao
机构: University of Pittsburgh (匹兹堡大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-248] ARIAL: An Agent ic Framework for Document VQA with Precise Answer Localization

链接: https://arxiv.org/abs/2511.18192
作者: Ahmad Mohammadshirazi,Pinaki Prasad Guha Neogi,Dheeraj Kulshrestha,Rajiv Ramnath
机构: Ohio State University (俄亥俄州立大学); Flairsoft
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-249] Early Lung Cancer Diagnosis from Virtual Follow-up LDCT Generation via Correlational Autoencoder and Latent Flow Matching

链接: https://arxiv.org/abs/2511.18185
作者: Yutong Wu,Yifan Wang,Qining Zhang,Chuan Zhou,Lei Ying
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 3 figures

点击查看摘要

[CV-250] Unified Spherical Frontend: Learning Rotation-Equivariant Representations of Spherical Images from Any Camera

链接: https://arxiv.org/abs/2511.18174
作者: Mukai Yu,Mosam Dabhi,Liuyue Xie,Sebastian Scherer,László A. Jeni
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-251] EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses

链接: https://arxiv.org/abs/2511.18173
作者: Enrico Pallotta,Sina Mokhtarzadeh Azar,Lars Doorenbos,Serdar Ozsoy,Umar Iqbal,Juergen Gall
机构: University of Bonn (波恩大学); Lamarr Institute for Machine Learning and Artificial Intelligence (拉马尔机器学习与人工智能研究所); NVIDIA (英伟达)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-252] Nested Unfolding Network for Real-World Concealed Object Segmentation

链接: https://arxiv.org/abs/2511.18164
作者: Chunming He,Rihan Zhang,Dingming Zhang,Fengyang Xiao,Deng-Ping Fan,Sina Farsiu
机构: Duke University (杜克大学); Nankai University (南开大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 6 figures, 14 tables

点击查看摘要

[CV-253] Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design

链接: https://arxiv.org/abs/2511.18163
作者: Pasquale De Marinis,Uzay Kaymak,Rogier Brussee,Gennaro Vessio,Giovanna Castellano
机构: University of Bari Aldo Moro (巴里阿尔多·莫罗大学); Jheronimus Academy of Data Science (JADS) (数据科学耶罗尼穆斯学院); Eindhoven University of Technology (TU/e) (埃因霍温理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-254] UnfoldLDM: Deep Unfolding-based Blind Image Restoration with Latent Diffusion Priors

链接: https://arxiv.org/abs/2511.18152
作者: Chunming He,Rihan Zhang,Zheng Chen,Bowen Yang,CHengyu Fang,Yunlong Lin,Fengyang Xiao,Sina Farsiu
机构: Duke University (杜克大学); Shanghai Jiao Tong University (上海交通大学); Peking University (北京大学); Tsinghua University (清华大学); Xiamen University (厦门大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 6 figures, 11 tables

点击查看摘要

[CV-255] AVERY: Adaptive VLM Split Computing through Embodied Self-Awareness for Efficient Disaster Response Systems

链接: https://arxiv.org/abs/2511.18151
作者: Rajat Bhattacharjya,Sing-Yao Wu,Hyunwoo Oh,Chaewon Nam,Suyeon Koo,Mohsen Imani,Elaheh Bozorgzadeh,Nikil Dutt
机构: University of California, Irvine (加州大学欧文分校); Kookmin University (国民大学)
类目: Distributed, Parallel, and Cluster Computing (cs.DC); Hardware Architecture (cs.AR); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI)
备注: 8 pages, 5 figures. Paper is currently under review. Authors’ version posted for personal use and not for redistribution

点击查看摘要

[CV-256] Observer Actor: Active Vision Imitation Learning with Sparse View Gaussian Splatting

链接: https://arxiv.org/abs/2511.18140
作者: Yilong Wang,Cheng Qian,Ruomeng Fan,Edward Johns
机构: 未知
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Videos are available on our project webpage at this https URL

点击查看摘要

[CV-257] Compact neural networks for astronomy with optimal transport bias correction

链接: https://arxiv.org/abs/2511.18139
作者: Shuhuan Wang,Yuzhen Xie,Jiayi Li
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 18 pages, 5 figures, 3 tables. Research article

点击查看摘要

[CV-258] SCALER: SAM-Enhanced Collaborative Learning for Label-Deficient Concealed Object Segmentation

链接: https://arxiv.org/abs/2511.18136
作者: Chunming He,Rihan Zhang,Longxiang Tang,Ziyun Yang,Kai Li,Deng-Ping Fan,Sina Farsiu
机构: Duke University (杜克大学); Harvard University (哈佛大学); Apple; Meta; Nankai University (南开大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 4 figures, 6 tables

点击查看摘要

[CV-259] Video4Edit: Viewing Image Editing as a Degenerate Temporal Process

链接: https://arxiv.org/abs/2511.18131
作者: Xiaofan Li,Yanpeng Sun,Chenming Wu,Fan Duan,YuAn Wang,Weihao Bo,Yumeng Zhang,Dingkang Liang
机构: Baidu Inc. (百度公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 5 figures

点击查看摘要

[CV-260] SFHand: A Streaming Framework for Language-guided 3D Hand Forecasting and Embodied Manipulation

链接: https://arxiv.org/abs/2511.18127
作者: Ruicong Liu,Yifei Huang,Liangyang Ouyang,Caixin Kang,Yoichi Sato
机构: The University of Tokyo (东京大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-261] VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging

链接: https://arxiv.org/abs/2511.18121
作者: Ming Zhong,Yuanlei Wang,Liuzhou Zhang,Arctanx An,Renrui Zhang,Hao Liang,Ming Lu,Ying Shen,Wentao Zhang
机构: Zhejiang University (浙江大学); Peking University (北京大学); Sun Yat-sen University (中山大学); CUHK (香港中文大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-262] MVS-TTA: Test-Time Adaptation for Multi-View Stereo via Meta-Auxiliary Learning

链接: https://arxiv.org/abs/2511.18120
作者: Hannuo Zhang,Zhixiang Chi,Yang Wang,Xinxin Zuo
机构: Gina Cody School of Engineering and Computer Science, Concordia University (康考迪亚大学); The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto (多伦多大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 7 figures

点击查看摘要

[CV-263] PromptMoE: Generalizable Zero-Shot Anomaly Detection via Visually-Guided Prompt Mixtures AAAI2026

链接: https://arxiv.org/abs/2511.18116
作者: Yuheng Shao,Lizhang Wang,Changhao Li,Peixian Chen,Qinyuan Liu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 14 pages, 8 figures. Accepted to AAAI 2026

点击查看摘要

[CV-264] Muskie: Multi-view Masked Image Modeling for 3D Vision Pre-training

链接: https://arxiv.org/abs/2511.18115
作者: Wenyu Li,Sidun Liu,Peng Qiao,Yong Dou,Tongrui Hu
机构: National University of Defense Technology (国防科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-265] AdaPerceiver: Transformers with Adaptive Width Depth and Tokens

链接: https://arxiv.org/abs/2511.18105
作者: Purvish Jajal,Nick John Eliopoulos,Benjamin Shiue-Hal Chou,George K. Thiruvathukal,Yung-Hsiang Lu,James C. Davis
机构: Purdue University (普渡大学); Loyola University Chicago (洛约拉大学芝加哥分校)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-266] Consolidating Diffusion-Generated Video Detection with Unified Multimodal Forgery Learning

链接: https://arxiv.org/abs/2511.18104
作者: Xiaohong Liu,Xiufeng Song,Huayu Zheng,Lei Bai,Xiaoming Liu,Guangtao Zhai
机构: Shanghai Jiao Tong University (上海交通大学); Shanghai Artificial Intelligence Laboratory (上海人工智能实验室); Michigan State University (密歇根州立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Code and dataset are available at this https URL

点击查看摘要

[CV-267] Spotlight: Identifying and Localizing Video Generation Errors Using VLMs

链接: https://arxiv.org/abs/2511.18102
作者: Aditya Chinchure,Sahithya Ravi,Pushkar Shukla,Vered Shwartz,Leonid Sigal
机构: The University of British Columbia (不列颠哥伦比亚大学); Vector Institute of AI; The Wharton School, University of Pennsylvania (宾夕法尼亚大学沃顿商学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-268] Versatile Recompression-Aware Perceptual Image Super-Resolution

链接: https://arxiv.org/abs/2511.18090
作者: Mingwei He,Tongda Xu,Xingtong Ge,Ming Sun,Chao Zhou,Yan Wang
机构: Tsinghua University (清华大学); AGUS Tech; HKUST (香港科技大学); Kuaishou Technology (快手科技)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-269] ogether Then Apart: Revisiting Multimodal Survival Analysis via a Min-Max Perspective

链接: https://arxiv.org/abs/2511.18089
作者: Wenjing Liu,Qin Ren,Wen Zhang,Yuewei Lin,Chenyu You
机构: Stony Brook University (石溪大学); Brookhaven National Laboratory (布鲁克海文国家实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-270] Less Is More: An Explainable AI Framework for Lightweight Malaria Classification

链接: https://arxiv.org/abs/2511.18083
作者: Md Abdullah Al Kafi,Raka Moni,Sumit Kumar Banshal
机构: Daffodil International University (达福国际大学); Alliance University (联盟大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-271] ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models

链接: https://arxiv.org/abs/2511.18082
作者: Wencheng Ye,Tianshi Wang,Lei Zhu,Fengling Li,Guoli Yang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-272] VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object Detection AAAI2026

链接: https://arxiv.org/abs/2511.18075
作者: Jianhang Yao,Yongbin Zheng,Siqi Lu,Wanying Xu,Peng Sun
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 15 pages, 8 figures, accepted by AAAI 2026

点击查看摘要

[CV-273] pFedBBN: A Personalized Federated Test-Time Adaptation with Balanced Batch Normalization for Class-Imbalanced Data

链接: https://arxiv.org/abs/2511.18066
作者: Md Akil Raihan Iftee,Syed Md. Ahnaf Hasan,Mir Sazzat Hossain,Rakibul Hasan Rajib,Amin Ahsan Ali,AKM Mahbubur Rahman,Sajib Mistry,Monowar Bhuyan
机构: Center for Computational & Data Sciences (CCDS), Independent University, Bangladesh; University of Central Florida, USA; Curtin University, Australia; Umeå University, Sweden
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: 25 pages, 7 tables, 21 figures

点击查看摘要

[CV-274] A Lightweight Interpretable Deep Learning System for Automated Detection of Cervical Adenocarcinoma In Situ (AIS)

链接: https://arxiv.org/abs/2511.18063
作者: Gabriela Fernandes
机构: SUNY Buffalo (纽约州立大学布法罗分校)
类目: Computer Vision and Pattern Recognition (cs.CV); Tissues and Organs (q-bio.TO)
备注:

点击查看摘要

[CV-275] Hierarchical Semi-Supervised Active Learning for Remote Sensing

链接: https://arxiv.org/abs/2511.18058
作者: Wei Huang,Zhitong Xiong,Chenying Liu,Xiao Xiang Zhu
机构: Technical University of Munich (慕尼黑工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Under review

点击查看摘要

[CV-276] UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios

链接: https://arxiv.org/abs/2511.18050
作者: Tian Ye,Song Fei,Lei Zhu
机构: HKUST(GZ); HKUST
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project Page: this https URL

点击查看摘要

[CV-277] Hybrid Event Frame Sensors: Modeling Calibration and Simulation

链接: https://arxiv.org/abs/2511.18037
作者: Yunfan Lu,Nico Messikommer,Xiaogang Xu,Liming Chen,Yuhan Chen,Nikola Zubic,Davide Scaramuzza,Hui Xiong
机构: AI Thrust HKUST(GZ); Robotics and Perception Group, University of Zurich; CUHK; AlpsenTek
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-278] MambaX: Image Super-Resolution with State Predictive Control

链接: https://arxiv.org/abs/2511.18028
作者: Chenyu Li,Danfeng Hong,Bing Zhang,Zhaojie Pan,Naoto Yokoya,Jocelyn Chanussot
机构: Southeast University (东南大学); Chinese Academy of Sciences (中国科学院); University of Chinese Academy of Sciences (中国科学院大学); School of Mathematics, Southeast University (东南大学数学学院); University of Tokyo (东京大学); Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK (格勒诺布尔阿尔卑斯大学, 法国国家信息与自动化研究院, 法国国家科学研究中心, 格勒诺布尔理工学院, 数学与计算机科学实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-279] Modeling Retinal Ganglion Cells with Neural Differential Equations AAAI-26

链接: https://arxiv.org/abs/2511.18014
作者: Kacper Dobek,Daniel Jankowski,Krzysztof Krawiec
机构: Poznan University of Technology (波兹南理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Accepted to the AAAI-26 Student Abstract and Poster Program, with supplementary material

点击查看摘要

[CV-280] State and Scene Enhanced Prototypes for Weakly Supervised Open-Vocabulary Object Detection

链接: https://arxiv.org/abs/2511.18012
作者: Jiaying Zhou,Qingchao Chen
机构: National Institute of Health Data Science (国家健康数据科学研究所); Peking University (北京大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-281] RoadBench: Benchmarking MLLM s on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios

链接: https://arxiv.org/abs/2511.18011
作者: Jun Zhang,Jie Feng,Long Chen,Junhui Wang,Zhicheng Liu,Depeng Jin,Yong Li
机构: Tsinghua University (清华大学); Alibaba Group (阿里巴巴集团)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: The code and data are publicly available at: this https URL

点击查看摘要

[CV-282] Is Complete Labeling Necessary? Understanding Active Learning in Longitudinal Medical Imaging IJCNN

链接: https://arxiv.org/abs/2511.18007
作者: Siteng Ma,Honghui Du,Prateek Mathur,Brendan S. Kelly,Ronan P. Killeen,Aonghus Lawlor,Ruihai Dong
机构: University College Dublin (都柏林大学); Insight Centre for Data Analytics (数据解析研究所); St Vincent’s University Hospital (圣文森特大学医院); Great Ormond Street Hospital for Children (大奥蒙德街儿童医院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: This paper has been accepted at International Joint Conference on Neural Networks (IJCNN) 2025

点击查看摘要

[CV-283] RAISECity: A Multimodal Agent Framework for Reality-Aligned 3D World Generation at City-Scale

链接: https://arxiv.org/abs/2511.18005
作者: Shengyuan Wang,Zhiheng Zheng,Yu Shang,Lixuan He,Yangcheng Yu,Fan Hangyu,Jie Feng,Qingmin Liao,Yong Li
机构: College of AI, Tsinghua University, Beijing, China (清华大学人工智能学院); Shenzhen International Graduate School, Tsinghua University, Beijing, China (清华大学深圳国际研究生院); Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China (清华大学电子工程系，北京清华信息科学与技术国家实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: The code will be made publicly available soon at: this https URL

点击查看摘要

[CV-284] SD-PSFNet: Sequential and Dynamic Point Spread Function Network for Image Deraining AAAI2026

链接: https://arxiv.org/abs/2511.17993
作者: Jiayu Wang,Haoyu Bian,Haoran Sun,Shaoning Zeng
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 12 pages, 7 figures, Published in AAAI 2026

点击查看摘要

[CV-285] HyM-UNet: Synergizing Local Texture and Global Context via Hybrid CNN-Mamba Architecture for Medical Image Segmentation

链接: https://arxiv.org/abs/2511.17988
作者: Haodong Chen,Xianfei Han,Qwen
机构: Beijing University of Posts and Communications (北京邮电大学); Alibaba Cloud AI Labs (阿里云人工智能实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Information Retrieval (cs.IR)
备注:

点击查看摘要

[CV-286] Plan-X: Instruct Video Generation via Semantic Planning

链接: https://arxiv.org/abs/2511.17986
作者: Lun Huang,You Xie,Hongyi Xu,Tianpei Gu,Chenxu Zhang,Guoxian Song,Zenan Li,Xiaochen Zhao,Linjie Luo,Guillermo Sapiro
机构: Duke University (杜克大学); Princeton University (普林斯顿大学); ByteDance Intelligent Creation (字节跳动智能创作); Apple (苹果)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: The project page is at this https URL

点击查看摘要

[CV-287] FeRA: Frequency-Energy Constrained Routing for Effective Diffusion Adaptation Fine-Tuning

链接: https://arxiv.org/abs/2511.17979
作者: Bo Yin,Xiaobin Hu,Xingyu Zhou,Peng-Tao Jiang,Yue Liao,Junwei Zhu,Jiangning Zhang,Ying Tai,Chengjie Wang,Shuicheng Yan
机构: National University of Singapore (新加坡国立大学); University of Electronic Science and Technology of China (电子科技大学); vivo; Tencent Youtu Lab (腾讯优图实验室); Nanjing University (南京大学); Zhejiang University (浙江大学); Shanghai Jiao Tong University (上海交通大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-288] Adversarial Pseudo-replay for Exemplar-free Class-incremental Learning WACV2026

链接: https://arxiv.org/abs/2511.17973
作者: Hiroto Honda
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to WACV 2026

点击查看摘要

[CV-289] CADTrack: Learning Contextual Aggregation with Deformable Alignment for Robust RGBT Tracking AAAI2026

链接: https://arxiv.org/abs/2511.17967
作者: Hao Li,Yuhao Wang,Xiantao Hu,Wenning Hao,Pingping Zhang,Dong Wang,Huchuan Lu
机构: 1. University of Science and Technology of China (中国科学技术大学); 2. Chinese Academy of Sciences (中国科学院); 3. Tsinghua University (清华大学); 4. Harbin Institute of Technology (哈尔滨工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by AAAI2026. More modifications may be performed

点击查看摘要

[CV-290] Signal: Selective Interaction and Global-local Alignment for Multi-Modal Object Re-Identification AAAI2026

链接: https://arxiv.org/abs/2511.17965
作者: Yangyang Liu,Yuhao Wang,Pingping Zhang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注: Accepted by AAAI2026. More modifications may be performed

点击查看摘要

[CV-291] X-ReID: Multi-granularity Information Interaction for Video-Based Visible-Infrared Person Re-Identification AAAI2026

链接: https://arxiv.org/abs/2511.17964
作者: Chenyang Yu,Xuehu Liu,Pingping Zhang,Huchuan Lu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by AAAI2026. More modifications may be performed

点击查看摘要

[CV-292] VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment

链接: https://arxiv.org/abs/2511.17962
作者: Ziheng Jia,Linhan Cao,Jinliang Han,Zicheng Zhang,Jiaying Qian,Jiarui Wang,Zijian Chen,Guangtao Zhai,Xiongkuo Min
机构: Shanghai Jiaotong University (上海交通大学); Shanghai Artificial Intelligence Laboratory (上海人工智能实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-293] HEAL: Learning-Free Source Free Unsupervised Domain Adaptation for Cross-Modality Medical Image Segmentation BMVC2025

链接: https://arxiv.org/abs/2511.17958
作者: Yulong Shi,Jiapeng Li,Lin Qi
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by The 36th British Machine Vision Conference (BMVC 2025)

点击查看摘要

[CV-294] Multi-speaker Attention Alignment for Multimodal Social Interaction

链接: https://arxiv.org/abs/2511.17952
作者: Liangyang Ouyang,Yifei Huang,Mingfang Zhang,Caixin Kang,Ryosuke Furuta,Yoichi Sato
机构: The University of Tokyo (东京大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-295] st-Time Temporal Sampling for Efficient MLLM Video Understanding

链接: https://arxiv.org/abs/2511.17945
作者: Kaibin Wang,Mingbao Lin
机构: SenseTime(商汤科技); Rakuten(乐天)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-296] SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent System

链接: https://arxiv.org/abs/2511.17943
作者: Zhiyu Xu,Weilong Yan,Yufei Shi,Xin Meng,Tao He,Huiping Zhuang,Ming Li,Hehe Fan
机构: Jinan University (暨南大学); National University of Singapore (新加坡国立大学); Nanyang Technological University (南洋理工大学); Peking University (北京大学); University of Electronic Science and Technology of China (电子科技大学); South China University of Technology (华南理工大学); Guangming Laboratory (光明实验室); Zhejiang University (浙江大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-297] V2X-RECT: An Efficient V2X Trajectory Prediction Framework via Redundant Interaction Filtering and Tracking Error Correction

链接: https://arxiv.org/abs/2511.17941
作者: Xiangyan Kong,Xuecheng Wu,Xiongwei Zhao,Xiaodong Li,Yunyun Shi,Gang Wang,Dingkang Yang,Yang Liu,Hong Chen,Yulong Gao
机构: Harbin Institute of Technology (哈尔滨工业大学); Xi’an Jiaotong University (西安交通大学); Harbin Institute of Technology (Shenzhen) (哈尔滨工业大学（深圳）); Fudan University (复旦大学); Tongji University (同济大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-298] Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion NEURIPS2025

链接: https://arxiv.org/abs/2511.17932
作者: Yan Xu,Yixing Wang,Stella X. Yu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR)
备注: Accepted to NeurIPS 2025

点击查看摘要

[CV-299] UniRSCD: A Unified Novel Architectural Paradigm for Remote Sensing Change Detection

链接: https://arxiv.org/abs/2511.17930
作者: Yuan Qu,Zhipeng Zhang,Chaojun Xu,Qiao Wan,Mengying Xie,Yuzeng Chen,Zhenqi Liu,Yanfei Zhong
机构: Southwest University (西南大学); Shanghai Jiaotong University (上海交通大学); Wuhan University (武汉大学); Chongqing University (重庆大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-300] MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection

链接: https://arxiv.org/abs/2511.17929
作者: Hui Lu,Yi Yu,Shijian Lu,Deepu Rajan,Boon Poh Ng,Alex C. Kot,Xudong Jiang
机构: Rapid-Rich Object Search Lab, Interdisciplinary Graduate Programme, Nanyang Technological University (南洋理工大学); College of Computing and Data Science, Nanyang Technological University (南洋理工大学); School of Electrical and Electronic Engineering, Nanyang Technological University (南洋理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-301] PA-FAS: Towards Interpretable and Generalizable Multimodal Face Anti-Spoofing via Path-Augmented Reinforcement Learning AAAI2026

链接: https://arxiv.org/abs/2511.17927
作者: Yingjie Ma,Xun Lin,Yong Xu,Weicheng Xie,Zitong Yu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Accepted by AAAI 2026 (Oral)

点击查看摘要

[CV-302] Switch-JustDance: Benchmarking Whole Body Motion Tracking Policies Using a Commercial Console Game

链接: https://arxiv.org/abs/2511.17925
作者: Jeonghwan Kim,Wontaek Kim,Yidan Lu,Jin Cheng,Fatemeh Zargarbashi,Zicheng Zeng,Zekun Qi,Zhiyang Dou,Nitish Sontakke,Donghoon Baek,Sehoon Ha,Tianyu Li
机构: Georgia Tech (佐治亚理工学院); HKU (香港大学); ETH Zurich (苏黎世联邦理工学院); SCUT (华南理工大学); THU (清华大学); MIT (麻省理工学院); PNDbotics
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-303] Animated Territorial Data Extractor (ATDE): A Computer-Vision Method for Extracting Territorial Data from Animated Historical Maps

链接: https://arxiv.org/abs/2511.17920
作者: Hamza Alshamy,Isaiah Woram,Advay Mishra,Zihan Xia,Pascal Wallisch
机构: New York University (纽约大学)
类目: Computers and Society (cs.CY); Computer Vision and Pattern Recognition (cs.CV)
备注: 11 pages, 5 figures

点击查看摘要

[CV-304] Frequency-Adaptive Sharpness Regularization for Improving 3D Gaussian Splatting Generalization

链接: https://arxiv.org/abs/2511.17918
作者: Youngsik Yun,Dongjun Gu,Youngjung Uh
机构: Yonsei University (延世大学); UNIST (韩国科学技术院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-305] Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation NEURIPS2025

链接: https://arxiv.org/abs/2511.17914
作者: Chenyang Jiang,Hang Zhao,Xinyu Zhang,Zhengcen Li,Qiben Shan,Shaocong Wu,Jingyong Su
机构: Harbin Institute of Technology, Shenzhen (哈尔滨工业大学深圳校区); Pengcheng Laboratory (鹏城实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 10 pages, accepted by NeurIPS 2025

点击查看摘要

[CV-306] CUS-GS: A Compact Unified Structured Gaussian Splatting Framework for Multimodal Scene Representation

链接: https://arxiv.org/abs/2511.17904
作者: Yuhang Ming,Chenxin Fang,Xingyuan Yu,Fan Zhang,Weichen Dai,Wanzeng Kong,Guofeng Zhang
机构: Hangzhou Dianzi University (杭州电子科技大学); Zhejiang University (浙江大学); University of Bristol (布里斯托大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: 15 pages, 8 figures, 4 tables

点击查看摘要

[CV-307] Decoupled Audio-Visual Dataset Distillation

链接: https://arxiv.org/abs/2511.17890
作者: Wenyuan Li,Guang Li,Keisuke Maeda,Takahiro Ogawa,Miki Haseyama
机构: Hokkaido University (北海道大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Multimedia (cs.MM)
备注:

点击查看摘要

[CV-308] MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots

链接: https://arxiv.org/abs/2511.17889
作者: Ting Huang,Dongjian Li,Rui Yang,Zeyu Zhang,Zida Yang,Hao Tang
机构: Peking University (北京大学)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-309] MINDiff: Mask-Integrated Negative Attention for Controlling Overfitting in Text-to-Image Personalization ICCV2025

链接: https://arxiv.org/abs/2511.17888
作者: Seulgi Jeong,Jaeil Kim
机构: Kyungpook National University (庆北国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at ICCV 2025 Personalization in Generative AI Workshop

点击查看摘要

[CV-310] FastMMoE: Accelerating Multimodal Large Language Models through Dynamic Expert Activation and Routing-Aware Token Pruning

链接: https://arxiv.org/abs/2511.17885
作者: Guoyang Xia,Yifeng Ding,Fengfa Li,Lei Ren,Wei Chen,Fangxiang Feng,Xiaojie Wang
机构: Beijing University of Posts and Telecommunications (北京邮电大学); Li Auto (理想汽车)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-311] ArticFlow: Generative Simulation of Articulated Mechanisms

链接: https://arxiv.org/abs/2511.17883
作者: Jiong Lin,Jinchen Ruan,Hod Lipson
机构: Creative Machines Lab, Columbia University (哥伦比亚大学创意机器实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: 8 pages, 8 figures

点击查看摘要

[CV-312] MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Use

链接: https://arxiv.org/abs/2511.17881
作者: Ahmad Mohammadshirazi,Pinaki Prasad Guha Neogi,Dheeraj Kulshrestha,Rajiv Ramnath
机构: Ohio State University (俄亥俄州立大学); Flairsoft; Columbus, Ohio, US
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-313] Less is More: Data-Efficient Adaptation for Controllable Text-to-Video Generation

链接: https://arxiv.org/abs/2511.17844
作者: Shihan Cheng,Nilesh Kulkarni,David Hyde,Dmitriy Smirnov
机构: Vanderbilt University (范德比尔特大学); Netflix (奈飞)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-314] JigsawComm: Joint Semantic Feature Encoding and Transmission for Communication-Efficient Cooperative Perception

链接: https://arxiv.org/abs/2511.17843
作者: Chenyi Wang,Zhaowei Li,Ming F. Li,Wujie Wen
机构: University of Arizona (亚利桑那大学); North Carolina State University (北卡罗来纳州立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-315] Show Me: Unifying Instructional Image and Video Generation with Diffusion Models WACV2026

链接: https://arxiv.org/abs/2511.17839
作者: Yujiang Pu,Zhanbo Huang,Vishnu Boddeti,Yu Kong
机构: Michigan State University (密歇根州立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by WACV 2026

点击查看摘要

[CV-316] oward explainable AI approaches for breast imaging: adapting foundation models to diverse populations

链接: https://arxiv.org/abs/2511.17828
作者: Guilherme J. Cavalcante,José Gabriel A. Moreira,Gabriel A.B. do Nascimento,Vincent Dong,Alex Nguyen,Thaís G. do Rêgo,Yuri Malheiros,Telmo M. Silva Filho,Carla R. Zeballos Torrez,James C. Gee,Anne Marie McCarthy,Andrew D. A. Maidment,Bruno Barufaldi
机构: University of Pennsylvania (宾夕法尼亚大学); Federal University of Paraíba (帕拉伊巴联邦大学); University of Bristol (布里斯托大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 5 pages, 3 figures

点击查看摘要

[CV-317] QAL: A Loss for Recall Precision Balance in 3D Reconstruction WACV2026

链接: https://arxiv.org/abs/2511.17824
作者: Pranay Meshram,Yash Turkar,Kartikeya Singh,Praveen Raj Masilamani,Charuvahan Adhivarahan,Karthik Dantu
机构: University at Buffalo, The State University of New York, Buffalo, NY, USA
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: Accepted to WACV 2026. Camera-ready version to appear

点击查看摘要

[CV-318] Importance-Weighted Non-IID Sampling for Flow Matching Models

链接: https://arxiv.org/abs/2511.17812
作者: Xinshuang Liu,Runfa Blark Li,Shaoxiu Wei,Truong Nguyen
机构: University of California, San Diego (加州大学圣地亚哥分校)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-319] REXO: Indoor Multi-View Radar Object Detection via 3D Bounding Box Diffusion AAAI2026

链接: https://arxiv.org/abs/2511.17806
作者: Ryoma Yataka,Pu Perry Wang,Petros Boufounos,Ryuhei Takahashi
机构: MERL (Multi-Objective Research Laboratory); ITC (Institute for Technology and Communication)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Signal Processing (eess.SP)
备注: 26 pages, Accepted to AAAI 2026; Code to be released

点击查看摘要

[CV-320] A Stitch in Time: Learning Procedural Workflow via Self-Supervised Plackett-Luce Ranking

链接: https://arxiv.org/abs/2511.17805
作者: Chengan Che,Chao Wang,Xinyue Chen,Sophia Tsoka,Luis C. Garcia-Peraza-Herrera
机构: King’s College London (伦敦国王学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 18 pages

点击查看摘要

[CV-321] Pillar-0: A New Frontier for Radiology Foundation Models

链接: https://arxiv.org/abs/2511.17803
作者: Kumar Krishna Agrawal,Longchao Liu,Long Lian,Michael Nercessian,Natalia Harguindeguy,Yufu Wu,Peter Mikhael,Gigin Lin,Lecia V. Sequist,Florian Fintelmann,Trevor Darrell,Yutong Bai,Maggie Chung,Adam Yala
机构: 1. Massachusetts Institute of Technology (麻省理工学院); 2. Stanford University (斯坦福大学); 3. Google (谷歌); 4. University of California, Berkeley (加州大学伯克利分校); 5. Stanford University (斯坦福大学); 6. Google (谷歌); 7. Dana-Farber Cancer Institute (达纳-法伯癌症研究所); 8. University of Zurich (苏黎世大学); 9. ETH Zurich (苏黎世联邦理工学院); 10. University of California, San Francisco (加州大学旧金山分校)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-322] Attention Guided Alignment in Efficient Vision-Language Models NEURIPS2025

链接: https://arxiv.org/abs/2511.17793
作者: Shweta Mahajan,Hoang Le,Hyojin Park,Farzad Farhadzadeh,Munawar Hayat,Fatih Porikli
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop on Efficient Reasoning

点击查看摘要

[CV-323] arget-Bench: Can World Models Achieve Mapless Path Planning with Semantic Targets?

链接: https://arxiv.org/abs/2511.17792
作者: Dingrui Wang,Hongyuan Ye,Zhihao Liang,Zhexiao Sun,Zhaowei Lu,Yuchen Zhang,Yuyu Zhao,Yuan Gao,Marvin Seegert,Finn Schäfer,Haotong Qin,Wei Li,Luigi Palmieri,Felix Jahncke,Mattia Piccinini,Johannes Betz
机构: TUM; Bosch AI Center; ETH; NJU
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: 10 pages

点击查看摘要

[CV-324] Deepfake Geography: Detecting AI-Generated Satellite Images

链接: https://arxiv.org/abs/2511.17766
作者: Mansur Yerzhanuly
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 18 pages, 8 figures

点击查看摘要

[CV-325] Latent Dirichlet Transformer VAE for Hyperspectral Unmixing with Bundled Endmembers

链接: https://arxiv.org/abs/2511.17757
作者: Giancarlo Giannetti,Faisal Z. Qureshi
机构: Ontario Tech University (安大略理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-326] CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentation WACV2026

链接: https://arxiv.org/abs/2511.17755
作者: Prantik Howlader,Hoang Nguyen-Canh,Srijan Das,Jingyi Xu,Hieu Le,Dimitris Samaras
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: WACV 2026 accepted

点击查看摘要

[CV-327] SPIDER: Spatial Image CorresponDence Estimator for Robust Calibration

链接: https://arxiv.org/abs/2511.17750
作者: Zhimin Shao,Abhay Yadav,Rama Chellappa,Cheng Peng
机构: Johns Hopkins University (约翰霍普金斯大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-328] AEGIS: Preserving privacy of 3D Facial Avatars with Adversarial Perturbations

链接: https://arxiv.org/abs/2511.17747
作者: Dawid Wolkiewicz,Anastasiya Pechko,Przemysław Spurek,Piotr Syga
机构: Wroclaw University of Science and Technology (弗罗茨瓦夫理工大学); Jagiellonian University (雅盖隆大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-329] owards Open-Ended Visual Scientific Discovery with Sparse Autoencoders

链接: https://arxiv.org/abs/2511.17735
作者: Samuel Stevens,Jacob Beattie,Tanya Berger-Wolf,Yu Su
机构: The Ohio State University (俄亥俄州立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-330] VisReason : A Large-Scale Dataset for Visual Chain-of-Thought Reasoning

链接: https://arxiv.org/abs/2511.17731
作者: Lingxiao Li,Yifan Wang,Xinyan Gao,Chen Tang,Xiangyu Yue,Chenyu You
机构: Stony Brook University (石溪大学); Boston University (波士顿大学); MMLab, CUHK (香港中文大学多媒体实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-331] he Potential and Limitations of Vision-Language Models for Human Motion Understanding: A Case Study in Data-Driven Stroke Rehabilitation

链接: https://arxiv.org/abs/2511.17727
作者: Victor Li,Naveenraj Kamalakannan,Avinash Parnandi,Heidi Schambra,Carlos Fernandez-Granda
机构: New York University Langone Health (纽约大学朗格尼健康); New York University (纽约大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-332] AngioDG: Interpretable Channel-informed Feature-modulated Single-source Domain Generalization for Coronary Vessel Segmentation in X-ray Angiography

链接: https://arxiv.org/abs/2511.17724
作者: Mohammad Atwany,Mojtaba Lashgari,Robin P. Choudhury,Vicente Grau,Abhirup Banerjee
机构: Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford (牛津大学工程科学系生物医学工程研究所); Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford (牛津大学心血管医学系)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-333] Can Vision-Language Models Count? A Synthetic Benchmark and Analysis of Attention-Based Interventions

链接: https://arxiv.org/abs/2511.17722
作者: Saurav Sengupta,Nazanin Moradinasab,Jiebei Liu,Donald E. Brown
机构: University of Virginia (弗吉尼亚大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-334] Understanding Counting Mechanisms in Large Language and Vision-Language Models

链接: https://arxiv.org/abs/2511.17699
作者: Hosein Hasani,Amirmohammad Izadi,Fatemeh Askari,Mobin Bagherian,Sadegh Mohammadian,Mohammad Izadi,Mahdieh Soleymani Baghshah
机构: Sharif University of Technology (谢里夫理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-335] Vision-Motion-Reference Alignment for Referring Multi-Object Tracking via Multi-Modal Large Language Models

链接: https://arxiv.org/abs/2511.17681
作者: Weiyi Lv,Ning Zhang,Hanyang Sun,Haoran Jiang,Kai Zhao,Jing Xiao,Dan Zeng
机构: Shanghai University (上海大学); PAII Inc.
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-336] Person Recognition in Aerial Surveillance: A Decade Survey

链接: https://arxiv.org/abs/2511.17674
作者: Kien Nguyen,Feng Liu,Clinton Fookes,Sridha Sridharan,Xiaoming Liu,Arun Ross
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at T-BIOM

点击查看摘要

[CV-337] MedPEFT-CL: Dual-Phase Parameter-Efficient Continual Learning with Medical Semantic Adapter and Bidirectional Memory Consolidation WACV2026

链接: https://arxiv.org/abs/2511.17668
作者: Ziyuan Gao
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by WACV 2026 (round 2)

点击查看摘要

[CV-338] CubeletWorld: A New Abstraction for Scalable 3D Modeling

链接: https://arxiv.org/abs/2511.17664
作者: Azlaan Mustafa Samad,Hoang H. Nguyen,Lukas Berg,Henrik Müller,Yuan Xue,Daniel Kudenko,Zahra Ahmadi
机构: L3S Research Center (L3S 研究中心); Leibniz University Hannover (汉诺威莱布尼茨大学); University of Tennessee at Chattanooga (田纳西大学查塔努加分校); PLRI Medical Informatics Institute (PLRI 医学信息研究所), Hannover Medical School (汉诺威医学院)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Computers and Society (cs.CY)
备注: 10 pages, 5 figures

点击查看摘要

[CV-339] Explainable Deep Learning for Brain Tumor Classification: Comprehensive Benchmarking with Dual Interpretability and Lightweight Deployment

链接: https://arxiv.org/abs/2511.17655
作者: Md. Mohaiminul Islam,Md. Mofazzal Hossen,Maher Ali Rusho,Nahiyan Nazah Ridita,Zarin Tasnia Shanta,Md. Simanto Haider,Ahmed Faizul Haque Dhrubo,Md. Khurshid Jahan,Mohammad Abdul Qayum
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注: This paper contains 17 pages, 4 tables, and 19 figures. This Paper is already accepted in IEEE Computational Intelligence Magazine (CIM)

点击查看摘要

[CV-340] SWITCH: Benchmarking Modeling and Handling of Tangible Interfaces in Long-horizon Embodied Scenarios

链接: https://arxiv.org/abs/2511.17649
作者: Jieru Lin,Zhiwei Yu,Börje F. Karlsson
机构: Harbin Institute of Technology (哈尔滨工业大学); Beijing Academy of Artificial Intelligence (北京人工智能研究院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Robotics (cs.RO)
备注:

点击查看摘要

[CV-341] Fluid Grey 2: How Well Does Generative Adversarial Network Learn Deeper Topology Structure in Architecture That Matches Images?

链接: https://arxiv.org/abs/2511.17643
作者: Yayan Qiu,Sean Hanna
机构: 未知
类目: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-342] SRE: Channel-Aware Typical Set Refinement for Out-of-Distribution Detection

链接: https://arxiv.org/abs/2511.17636
作者: Weijun Gao,Rundong He,Jinyang Dong,Yongshun Gong
机构: Shandong University (山东大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-343] Upstream Probabilistic Meta-Imputation for Multimodal Pediatric Pancreatitis Classification

链接: https://arxiv.org/abs/2511.17635
作者: Max A. Nelson,Elif Keles,Eminenur Sen Tasci,Merve Yazol,Halil Ertugrul Aktas,Ziliang Hong,Andrea Mia Bejar,Gorkem Durak,Oznur Leman Boyunaga,Ulas Bagci
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 5 pages, 5 figures

点击查看摘要

[CV-344] Efficient Score Pre-computation for Diffusion Models via Cross-Matrix Krylov Projection

链接: https://arxiv.org/abs/2511.17634
作者: Kaikwan Lau,Andrew S. Na,Justin W.L. Wan
机构: University of Waterloo (滑铁卢大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-345] BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks? AAAI2026

链接: https://arxiv.org/abs/2511.17633
作者: DoYoung Kim,Jin-Seop Lee,Noo-ri Kim,SungJoon Lee,Jee-Hyong Lee
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Paper accepted to AAAI 2026

点击查看摘要

[CV-346] Rethinking the Encoding and Annotating of 3D Bounding Box: Corner-Aware 3D Object Detection from Point Clouds

链接: https://arxiv.org/abs/2511.17619
作者: Qinghao Meng,Junbo Yin,Jianbing Shen,Yunde Jia
机构: Beijing Institute of Technology (北京理工大学); King Abdullah University of Science and Technology (KAUST, 阿卜杜拉国王科技大学); University of Macau (澳门大学); Shenzhen MSU-BIT University (深圳北理莫斯科大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 5 figures, 2 tables

点击查看摘要

[CV-347] Foundational Question Generation for Video Question Answering via an Embedding-Integrated Approach

链接: https://arxiv.org/abs/2511.17618
作者: Ju-Young Oh
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: [Master’s thesis, Korea University, 2025]

点击查看摘要

[CV-348] Plug-and-Play Multi-Concept Adaptive Blending for High-Fidelity Text-to-Image Synthesis

链接: https://arxiv.org/abs/2511.17615
作者: Young-Beom Woo
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: [Master’s thesis, Korea University, 2025]

点击查看摘要

[CV-349] HSMix: Hard and Soft Mixing Data Augmentation for Medical Image Segmentation

链接: https://arxiv.org/abs/2511.17614
作者: Danyang Sun,Fadi Dornaika,Nagore Barrena
机构: University of the Basque Country (巴斯克大学); IKERBASQUE (巴斯克基金会)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-350] Unified Low-Light Traffic Image Enhancement via Multi-Stage Illumination Recovery and Adaptive Noise Suppression

链接: https://arxiv.org/abs/2511.17612
作者: Siddiqua Namrah
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Master’s thesis, Korea University, 2025

点击查看摘要

[CV-351] 3D Ground Truth Reconstruction from Multi-Camera Annotations Using UKF

链接: https://arxiv.org/abs/2511.17609
作者: Linh Van Ma,Unse Fatima,Tepy Sokun Chriv,Haroon Imran,Moongu Jeon
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: International Conference on Control, Automation and Information Sciences (ICCAIS) 2025, October 27 - 29, 2025 | Jeju, Korea

点击查看摘要

[CV-352] BCWildfire: A Long-term Multi-factor Dataset and Deep Learning Benchmark for Boreal Wildfire Risk Prediction AAAI-26

链接: https://arxiv.org/abs/2511.17597
作者: Zhengsen Xu,Sibo Cheng,Hongjie He,Lanying Wang,Wentao Sun,Jonathan Li,Lincoln Linlin Xu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: This paper has been accepted by AAAI-26

点击查看摘要

[CV-353] Reconstruction-Driven Multimodal Representation Learning for Automated Media Understanding

链接: https://arxiv.org/abs/2511.17596
作者: Yassir Benhammou,Suman Kalyan,Sujay Kumar
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 8 pages, 5 figures, 4 tables

点击查看摘要

[CV-354] PaSE: Prototype-aligned Calibration and Shapley-based Equilibrium for Multimodal Sentiment Analysis AAAI2026

链接: https://arxiv.org/abs/2511.17585
作者: Kang He,Boyu Chen,Yuzhe Ding,Fei Li,Chong Teng,Donghong Ji
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by AAAI 2026

点击查看摘要

[CV-355] Learning Straight Flows: Variational Flow Matching for Efficient Generation

链接: https://arxiv.org/abs/2511.17583
作者: Chenrui Ma,Xi Xiao,Tianyang Wang,Xiao Wang,Yanning Shen
机构: University of California, Irvine (加州大学欧文分校); University of Alabama at Birmingham (阿拉巴马大学伯明翰分校); Oak Ridge National Laboratory (橡树岭国家实验室)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-356] EgoCogNav: Cognition-aware Human Egocentric Navigation

链接: https://arxiv.org/abs/2511.17581
作者: Zhiwen Qiu,Ziang Liu,Wenqian Niu,Tapomayukh Bhattacharjee,Saleh Kalantari
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: 11 pages, 4 figures

点击查看摘要

[CV-357] Multimodal AI for Body Fat Estimation: Computer Vision and Anthropometry with DEXA Benchmarks

链接: https://arxiv.org/abs/2511.17576
作者: Rayan Aldajani
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 2 pages, 2 figures, accepted at IEEE CASCON 2025

点击查看摘要

[CV-358] mporal-adaptive Weight Quantization for Spiking Neural Networks

链接: https://arxiv.org/abs/2511.17567
作者: Han Zhang,Qingyan Meng,Jiaqi Wang,Baiyu Chen,Zhengyu Ma,Xiaopeng Fan
机构: Harbin Institute of Technology (哈尔滨工业大学); Pengcheng Laboratory (鹏城实验室); Institute of Automation, Chinese Academy of Sciences (中国科学院自动化研究所); Institute of Computing and Intelligence (ICI), Harbin Institute of Technology, Shenzhen (哈尔滨工业大学深圳计算与智能研究院); Suzhou Research Institute, Harbin Institute of Technology (哈尔滨工业大学苏州研究院)
类目: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-359] Classification of Transient Astronomical Object Light Curves Using LSTM Neural Networks

链接: https://arxiv.org/abs/2511.17564
作者: Guilherme Grancho D. Fernandes,Marco A. Barroca,Mateus dos Santos,Rafael S. Oliveira
机构: 未知
类目: Machine Learning (cs.LG); Instrumentation and Methods for Astrophysics (astro-ph.IM); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: 12 pages, 11 figures, 2 tables

点击查看摘要

[CV-360] Deep Learning-based Lightweight RGB Object Tracking for Augmented Reality Devices

链接: https://arxiv.org/abs/2511.17508
作者: Alice Smith,Bob Johnson,Xiaoyu Zhu,Carol Lee
机构: Northern Illinois University (北方伊利诺伊大学)
类目: Human-Computer Interaction (cs.HC); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-361] Saving Foundation Flow-Matching Priors for Inverse Problems

链接: https://arxiv.org/abs/2511.16520
作者: Yuxiang Wan,Ryan Devera,Wenjie Zhang,Ju Sun
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV); Signal Processing (eess.SP)
备注:

点击查看摘要

[CV-362] Rad-GS: Radar-Vision Integration for 3D Gaussian Splatting SLAM in Outdoor Environments

链接: https://arxiv.org/abs/2511.16091
作者: Renxiang Xiao,Wei Liu,Yuanfan Zhang,Yushuai Chen,Jinming Chen,Zilu Wang,Liang Hu
机构: Harbin Institute of Technology, Shenzhen (哈尔滨工业大学深圳校区)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-363] BOOD: Boundary-based Out-Of-Distribution Data Generation ICML

链接: https://arxiv.org/abs/2508.00350
作者: Qilin Liao,Shuo Yang,Bo Zhao,Ping Luo,Hengshuang Zhao
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: 14 pages, 8 figures, To be published in the Proceedings of the International Conference on Machine Learning (ICML) 2025

点击查看摘要

[CV-364] Neural B-Frame Coding: Tackling Domain Shift Issues with Lightweight Online Motion Resolution Adaptation

链接: https://arxiv.org/abs/2511.18724
作者: Sang NguyenQuang,Xiem HoangVan,Wen-Hsiao Peng
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注: Accepted by TCAS-II: Express Briefs

点击查看摘要

[CV-365] Shape-Adapting Gated Experts: Dynamic Expert Routing for Colonoscopic Lesion Segmentation

链接: https://arxiv.org/abs/2511.18493
作者: Gia Huy Thai,Hoang-Nguyen Vu,Anh-Minh Phan,Quang-Thinh Ly,Tram Dinh,Thi-Ngoc-Truc Nguyen,Nhat Ho
机构: University of Science, VNU-HCM (胡志明市国家大学科学大学); Trivita AI; University of Technology, VNU-HCM (胡志明市国家大学技术大学); Michigan State University (密歇根州立大学); Phu Nhuan High School (富嫩高中); The University of Texas at Austin (德克萨斯大学奥斯汀分校)
类目: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-366] Linear Algebraic Approaches to Neuroimaging Data Compression: A Comparative Analysis of Matrix and Tensor Decomposition Methods for High-Dimensional Medical Images

链接: https://arxiv.org/abs/2511.18197
作者: Jaeho Kim,Daniel David,Ana Vizitiv
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

人工智能

[AI-0] Prompt Less Smile More: MTP with Semantic Engineering in Lieu of Prompt Engineering

链接: https://arxiv.org/abs/2511.19427
作者: Jayanaka L. Dantanarayana,Savini Kashmira,Thakee Nathees,Zichen Zhang,Krisztian Flautner,Lingjia Tang,Jason Mars
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-1] SLMFix: Leverag ing Small Language Models for Error Fixing with Reinforcement Learning

链接: https://arxiv.org/abs/2511.19422
作者: David Jiahao Fu,Aryan Gupta,Aaron Councilman,David Grove,Yu-Xiong Wang,Vikram Adve
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI); Programming Languages (cs.PL)
备注:

点击查看摘要

[AI-2] Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme

链接: https://arxiv.org/abs/2511.19390
作者: Rudy Morel,Francesco Pio Ramunno,Jeff Shen,Alberto Bietti,Kyunghyun Cho,Miles Cranmer,Siavash Golkar,Olexandr Gugnin,Geraud Krawezik,Tanya Marwah,Michael McCabe,Lucas Meyer,Payel Mukhopadhyay,Ruben Ohana,Liam Parker,Helen Qu,François Rozet,K.D. Leka,François Lanusse,David Fouhey,Shirley Ho
机构: 未知
类目: Machine Learning (cs.LG); Solar and Stellar Astrophysics (astro-ph.SR); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
备注:

点击查看摘要

[AI-3] Leverag ing LLM s for reward function design in reinforcement learning control tasks

链接: https://arxiv.org/abs/2511.19355
作者: Franklin Cardenoso,Wouter Caarls
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO)
备注:

点击查看摘要

[AI-4] Explicit Tonal Tension Conditioning via Dual-Level Beam Search for Symbolic Music Generation

链接: https://arxiv.org/abs/2511.19342
作者: Maral Ebrahimzadeh,Gilberto Bernardes,Sebastian Stober
机构: 未知
类目: ound (cs.SD); Artificial Intelligence (cs.AI)
备注: 12 pages, 2 Figures, Accepted at the 17th International Symposium on Computer Music Multidisciplinary Research (CMMR) 2025

点击查看摘要

[AI-5] Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning NEURIPS2025

【速读】：该论文旨在解决生成式 AI (Generative AI) 在基因组语言模型（genomic language models, gLMs）中的潜在滥用风险问题，特别是针对可通过微调（fine-tuning）恢复对有害病原体相关任务的预测能力这一安全隐患。其关键解决方案在于实证评估了在预训练数据中排除病毒序列后，通过使用110种危害人类的病毒序列对gLM Evo 2进行微调，是否仍能显著恢复其对病毒相关任务的性能；结果表明，微调后的模型不仅在未见过的病毒序列上表现出更低的困惑度（perplexity），还能识别出SARS-CoV-2的免疫逃逸变异株（AUROC达0.6），尽管训练过程中未接触任何SARS-CoV-2序列，这说明单纯的数据过滤策略不足以防范gLMs的潜在滥用风险，亟需建立更系统的安全框架与针对性的评估及缓解措施。

链接: https://arxiv.org/abs/2511.19299
作者: James R. M. Black,Moritz S. Hanke,Aaron Maiwald,Tina Hernandez-Boussard,Oliver M. Crook,Jaspreet Pannu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Biosecurity Safeguards for Generative AI

点击查看摘要

Abstract:Novel deep learning architectures are increasingly being applied to biological data, including genetic sequences. These models, referred to as genomic language mod- els (gLMs), have demonstrated impressive predictive and generative capabilities, raising concerns that such models may also enable misuse, for instance via the generation of genomes for human-infecting viruses. These concerns have catalyzed calls for risk mitigation measures. The de facto mitigation of choice is filtering of pretraining data (i.e., removing viral genomic sequences from training datasets) in order to limit gLM performance on virus-related tasks. However, it is not currently known how robust this approach is for securing open-source models that can be fine-tuned using sensitive pathogen data. Here, we evaluate a state-of-the-art gLM, Evo 2, and perform fine-tuning using sequences from 110 harmful human-infecting viruses to assess the rescue of misuse-relevant predictive capabilities. The fine- tuned model exhibited reduced perplexity on unseen viral sequences relative to 1) the pretrained model and 2) a version fine-tuned on bacteriophage sequences. The model fine-tuned on human-infecting viruses also identified immune escape variants from SARS-CoV-2 (achieving an AUROC of 0.6), despite having no expo- sure to SARS-CoV-2 sequences during fine-tuning. This work demonstrates that data exclusion might be circumvented by fine-tuning approaches that can, to some degree, rescue misuse-relevant capabilities of gLMs. We highlight the need for safety frameworks for gLMs and outline further work needed on evaluations and mitigation measures to enable the safe deployment of gLMs.
zh

[AI-6] Data Flows and Colonial Regimes in Africa: A Critical Analysis of the Colonial Futurities Embedded in AI Ecosystems

【速读】：该论文试图解决非洲语境下人工智能（AI）与大数据所引发的隐性结构性问题，特别是数字基础设施和平台如何通过推荐算法重构区域数字社会，并可能加剧算法殖民主义（algorithmic colonialism）及性别偏见，从而对地区可持续发展目标构成挑战。解决方案的关键在于采纳具有“回应能力”（response-ability）的商业模式，并承认AI存在多元社会-物质世界（alternative socio-material worlds of AI），以推动更具包容性和公平性的技术发展路径。

链接: https://arxiv.org/abs/2511.19283
作者: Ndaka. A,Avila-Acosta. F,Mbula-Ndaka. H,Amera. C,Chauke. S,Majiwa. E
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
备注: 12 pages

点击查看摘要

Abstract:This chapter seeks to frame the elemental and invisible problems of AI and big data in the African context by examining digital sites and infrastructure through the lens of power and interests. It will present reflections on how these sites are using AI recommendation algorithms to recreate new digital societies in the region, how they have the potential to propagate algorithmic colonialism and negative gender norms, and what this means for the regional sustainable development agenda. The chapter proposes adopting business models that embrace response-ability and consider the existence of alternative socio-material worlds of AI. These reflections will mainly come from ongoing discussions with Kenyan social media users in this authors’ user space talks, personal experiences and six months of active participant observations done by the authors.
zh

[AI-7] Dynamic Multi-Species Bird Soundscape Generation with Acoustic Patterning and 3D Spatialization

链接: https://arxiv.org/abs/2511.19275
作者: Ellie L. Zhang,Duoduo Liao,Callie C. Liao
机构: 未知
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS); Signal Processing (eess.SP)
备注: Accepted by IEEE Big Data 2025

点击查看摘要

[AI-8] Interpreting GFlowNets for Drug Discovery: Extracting Actionable Insights for Medicinal Chemistry NEURIPS2025

链接: https://arxiv.org/abs/2511.19264
作者: Amirtha Varshini A S,Duminda S. Ranasinghe,Hok Hei Tam
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Biomolecules (q-bio.BM)
备注: 13 pages, 7 figures. Accepted for presentation at NeurIPS 2025 WiML Workshop and Molecular Machine Learning Conference (MoML) 2025

点击查看摘要

[AI-9] Solar-GECO: Perovskite Solar Cell Property Prediction with Geometric-Aware Co-Attention NEURIPS2025

链接: https://arxiv.org/abs/2511.19263
作者: Lucas Li,Jean-Baptiste Puel,Florence Carton,Dounya Barrit,Jhony H. Giraldo
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Accepted at the AI for Accelerated Materials Design (AI4Mat) Workshop at NeurIPS 2025. 14 pages, 4 figures

点击查看摘要

[AI-10] Psychometric Tests for AI Agents and Their Moduli Space

链接: https://arxiv.org/abs/2511.19262
作者: Przemyslaw Chojecki
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Statistics Theory (math.ST)
备注:

点击查看摘要

[AI-11] Medusa: Cross-Modal Transferable Adversarial Attacks on Multimodal Medical Retrieval-Augmented Generation KDD2026

链接: https://arxiv.org/abs/2511.19257
作者: Yingjia Shang,Yi Liu,Huimin Wang,Furong Li,Wenfang Sun,Wu Chengyu,Yefeng Zheng
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Accepted at KDD 2026 First Cycle (full version). Authors marked with * contributed equally. Yi Liu is the lead author

点击查看摘要

[AI-12] SimDiff: Simpler Yet Better Diffusion Model for Time Series Point Forecasting AAAI2026

链接: https://arxiv.org/abs/2511.19256
作者: Hang Ding,Xue Wang,Tian Zhou,Tao Yao
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Accepted by AAAI 2026

点击查看摘要

[AI-13] MAESTRO: Multi-Agent Environment Shaping through Task and Reward Optimization

链接: https://arxiv.org/abs/2511.19253
作者: Boyuan Wu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Preprint. 16 pages, 6 figures. Preliminary version; extended experiments and analysis forthcoming

点击查看摘要

[AI-14] Local Entropy Search over Descent Sequences for Bayesian Optimization

链接: https://arxiv.org/abs/2511.19241
作者: David Stenger,Armin Lindicke,Alexander von Rohr,Sebastian Trimpe
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
备注:

点击查看摘要

[AI-15] SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Control

链接: https://arxiv.org/abs/2511.19236
作者: Yuxuan Wang,Haobin Jiang,Shiqing Yao,Ziluo Ding,Zongqing Lu
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注: 23 pages, 8 figures, 11 tables

点击查看摘要

[AI-16] Adversarial Attack-Defense Co-Evolution for LLM Safety Alignment via Tree-Group Dual-Aware Search and Optimization

链接: https://arxiv.org/abs/2511.19218
作者: Xurui Li,Kaisong Song,Rui Zhu,Pin-Yu Chen,Haixu Tang
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-17] LLM -Based Agent ic Negotiation for 6G: Addressing Uncertainty Neglect and Tail-Event Risk

【速读】：该论文旨在解决第六代移动通信（6G）智能自主网络中因“不确定性忽视偏差”（uncertainty neglect bias）导致的信任问题，即基于大语言模型（LLM）的智能体在决策时仅依赖平均值而忽略极端事件的尾部风险（tail risk），从而引发服务质量（SLA）保障失效。解决方案的关键在于提出一种无偏、风险感知的代理协商框架：首先利用数字孪生（Digital Twin, DT）预测全量延迟分布，并通过极值理论中的条件风险价值（Conditional Value-at-Risk, CVaR）对尾部风险进行形式化评估；其次要求智能体量化其DT预测的认知不确定性（epistemic uncertainty），并通过元验证机制传播该不确定性信息，以避免基于不可靠数据做出决策。该方法从根本上将代理目标从均值推理转向尾部推理，显著提升了网络切片资源分配的鲁棒性与可信赖性。

链接: https://arxiv.org/abs/2511.19175
作者: Hatim Chergui,Farhad Rezazadeh,Mehdi Bennis,Merouane Debbah
机构: 未知
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
备注: Link to open-source non-commercial code available

点击查看摘要

Abstract:A critical barrier to the trustworthiness of sixth-generation (6G) agentic autonomous networks is the uncertainty neglect bias; a cognitive tendency for large language model (LLM)-powered agents to make high-stakes decisions based on simple averages while ignoring the tail risk of extreme events. This paper proposes an unbiased, risk-aware framework for agentic negotiation, designed to ensure robust resource allocation in 6G network slicing. Specifically, agents leverage Digital Twins (DTs) to predict full latency distributions, which are then evaluated using a formal framework from extreme value theory, namely, Conditional Value-at-Risk (CVaR). This approach fundamentally shifts the agent’s objective from reasoning over the mean to reasoning over the tail, thereby building a statistically-grounded buffer against worst-case outcomes. Furthermore, our framework ensures full uncertainty awareness by requiring agents to quantify epistemic uncertainty – confidence in their own DTs predictions – and propagate this meta-verification to make robust decisions, preventing them from acting on unreliable data. We validate this framework in a 6G inter-slice negotiation use-case between an eMBB and a URLLC agent. The results demonstrate the profound failure of the biased, mean-based baseline, which consistently fails its SLAs with a 25% rate. Our unbiased, CVaR-aware agent successfully mitigates this bias, eliminating SLA violations and reducing the URLLC and eMBB p99.999 latencies by around 11%. We show this reliability comes at the rational and quantifiable cost of slightly reduced energy savings to 17%, exposing the false economy of the biased approach. This work provides a concrete methodology for building the trustworthy autonomous systems required for 6G.
zh

[AI-18] Information Physics of Intelligence: Unifying Logical Depth and Entropy under Thermodynamic Constraints

链接: https://arxiv.org/abs/2511.19156
作者: Jianfeng Xu,Zeyan Li
机构: 未知
类目: Information Theory (cs.IT); Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO)
备注:

点击查看摘要

[AI-19] EEG-VLM: A Hierarchical Vision-Language Model with Multi-Level Feature Alignment and Visually Enhanced Language-Guided Reasoning for EEG Image-Based Sleep Stage Prediction

链接: https://arxiv.org/abs/2511.19155
作者: Xihe Qiu,Gengchen Ma,Haoyu Wang,Chen Zhan,Xiaoyu Tan,Shuo Li
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-20] Uncertainty-Aware Deep Learning Framework for Remaining Useful Life Prediction in Turbofan Engines with Learned Aleatoric Uncertainty

链接: https://arxiv.org/abs/2511.19124
作者: Krishang Sharma
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 10 pages, 2 figures, 3 tables. Submitted to arXiv

点击查看摘要

[AI-21] AI Consciousness and Existential Risk

链接: https://arxiv.org/abs/2511.19115
作者: Rufin VanRullen
机构: 未知
类目: Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注:

点击查看摘要

[AI-22] he Core in Max-Loss Non-Centroid Clustering Can Be Empty

链接: https://arxiv.org/abs/2511.19107
作者: Robert Bredereck,Eva Deltl,Leon Kellerhals,Jannik Peters
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Science and Game Theory (cs.GT); Machine Learning (stat.ML)
备注:

点击查看摘要

[AI-23] Extracting Robust Register Automata from Neural Networks over Data Sequences

链接: https://arxiv.org/abs/2511.19100
作者: Chih-Duo Hong,Hongjian Jiang,Anthony W. Lin,Oliver Markgraf,Julian Parsert,Tony Tan
机构: 未知
类目: Artificial Intelligence (cs.AI); Formal Languages and Automata Theory (cs.FL); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-24] EnfoPath: Energy-Informed Analysis of Generative Trajectories in Flow Matching

链接: https://arxiv.org/abs/2511.19087
作者: Ziyun Li,Ben Dai,Huancheng Hu,Henrik Boström,Soon Hoe Lim
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: EurIPS 2025 Workshop on Principles of Generative Modeling (PriGM)

点击查看摘要

[AI-25] Mitigating Participation Imbalance Bias in Asynchronous Federated Learning

链接: https://arxiv.org/abs/2511.19066
作者: Xiangyu Chang,Manyi Yao,Srikanth V. Krishnamurthy,Christian R. Shelton,Anirban Chakraborty,Ananthram Swami,Samet Oymak,Amit Roy-Chowdhury
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-26] Large Language Model-Assisted Planning of Electric Vehicle Charging Infrastructure with Real-World Case Study

链接: https://arxiv.org/abs/2511.19055
作者: Xinda Zheng,Canchen Jiang,Hao Wang
机构: 未知
类目: ystems and Control (eess.SY); Artificial Intelligence (cs.AI); Optimization and Control (math.OC)
备注:

点击查看摘要

[AI-27] OrdMoE: Preference Alignment via Hierarchical Expert Group Ranking in Multimodal Mixture-of-Experts LLM s

链接: https://arxiv.org/abs/2511.19023
作者: Yuting Gao,Weihao Chen,Lan Wang,Ruihan Xu,Qingpei Guo
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-28] Introducing Visual Scenes and Reasoning : A More Realistic Benchmark for Spoken Language Understanding

链接: https://arxiv.org/abs/2511.19005
作者: Di Wu,Liting Jiang,Ruiyu Fang,Bianjing,Hongyan Xie,Haoxiang Su,Hao Huang,Zhongjiang He,Shuangyong Song,Xuelong Li
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-29] Dynamic Mixture of Experts Against Severe Distribution Shifts

链接: https://arxiv.org/abs/2511.18987
作者: Donghu Kim
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-30] FastForward Pruning: Efficient LLM Pruning via Single-Step Reinforcement Learning

链接: https://arxiv.org/abs/2511.18977
作者: Xin Yuan,Siqi Li,Jiateng Wei,Chengrui Zhu,Yanming Wu,Qingpeng Li,Jiajun Lv,Xiaoke Lan,Jun Chen,Yong Liu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 5 pages, 2 figures, 4 tables

点击查看摘要

[AI-31] LLM -CSEC: Empirical Evaluation of Security in C/C Code Generated by Large Language Models

链接: https://arxiv.org/abs/2511.18966
作者: Muhammad Usman Shahid,Chuadhry Mujeeb Ahmed,Rajiv Ranjan
机构: 未知
类目: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
备注:

点击查看摘要

[AI-32] Synthesizing Visual Concepts as Vision-Language Programs

链接: https://arxiv.org/abs/2511.18964
作者: Antonia Wüst,Wolfgang Stammer,Hikaru Shindo,Lukas Helff,Devendra Singh Dhami,Kristian Kersting
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-33] Learning to Compress Graphs via Dual Agents for Consistent Topological Robustness Evaluation

链接: https://arxiv.org/abs/2511.18958
作者: Qisen Chai,Yansong Wang,Junjie Huang,Tao Jia
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-34] Active Inference is a Subtype of Variational Inference

链接: https://arxiv.org/abs/2511.18955
作者: Wouter W. L. Nuijten,Mykola Lukashchuk
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: Accepted to the EIML Workshop 2025 at EurIPS (non-archival)

点击查看摘要

[AI-35] Defending Large Language Models Against Jailbreak Exploits with Responsible AI Considerations NEURIPS2024

链接: https://arxiv.org/abs/2511.18933
作者: Ryan Wong(1),Hosea David Yu Fei Ng(1),Dhananjai Sharma(1),Glenn Jun Jie Ng(1),Kavishvaran Srinivasan(1) ((1) National University of Singapore)
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注: 20 pages including appendix; technical report; NeurIPS 2024 style

点击查看摘要

[AI-36] Learning Solution Operators for Partial Differential Equations via Monte Carlo-Type Approximation NEURIPS2025

链接: https://arxiv.org/abs/2511.18930
作者: Salah Eddine Choutri,Prajwal Chauhan,Othmane Mazhar,Saif Eddin Jabari
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: NeurIPS 2025 Workshop on Machine Learning and the Physical Sciences

点击查看摘要

[AI-37] MoodBench 1.0: An Evaluation Benchmark for Emotional Companionship Dialogue Systems

链接: https://arxiv.org/abs/2511.18926
作者: Haifeng Jing,Yujie Hou,Junfei Liu,Rui Xie,alan Xu,Jinlong Ma,Qichun Deng
机构: 未知
类目: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注: 26 pages, 7 figures

点击查看摘要

[AI-38] LLM -Driven Kernel Evolution: Automating Driver Updates in Linux

链接: https://arxiv.org/abs/2511.18924
作者: Arina Kharlamova,Jiawen Liu,Tianyi Zhang,Xinrui Yang,Humaid Alqasimi,Youcheng Sun,Chun Jason Xue
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-39] VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL

链接: https://arxiv.org/abs/2511.18902
作者: Zengjie Hu,Jiantao Qiu,Tianyi Bai,Haojin Yang,Binhang Yuan,Qi Jing,Conghui He,Wentao Zhang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-40] Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models NEURIPS2025

链接: https://arxiv.org/abs/2511.18890
作者: Yonggan Fu,Xin Dong,Shizhe Diao,Matthijs Van keirsbilck,Hanrong Ye,Wonmin Byeon,Yashaswi Karnati,Lucas Liebenwein,Hannah Zhang,Nikolaus Binder,Maksim Khadkevich,Alexander Keller,Jan Kautz,Yingyan Celine Lin,Pavlo Molchanov
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Accepted by NeurIPS 2025

点击查看摘要

[AI-41] Accelerating Reinforcement Learning via Error-Related Human Brain Signals

链接: https://arxiv.org/abs/2511.18878
作者: Suzie Kim,Hye-Bin Shin,Hyo-Jeong Jang
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-42] Periodic Asynchrony: An Effective Method for Accelerating On-Policy Reinforcement Learning

链接: https://arxiv.org/abs/2511.18871
作者: Jian Lu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-43] Multidimensional Music Aesthetic Evaluation via Semantically Consistent C-Mixup Augmentation

链接: https://arxiv.org/abs/2511.18869
作者: Shuyang Liu,Yuan Jin,Rui Lin,Shizhe Chen,Junyu Dai,Tao Jiang
机构: 未知
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS)
备注:

点击查看摘要

[AI-44] KernelBand: Boosting LLM -based Kernel Optimization with a Hierarchical and Hardware-aware Multi-armed Bandit

链接: https://arxiv.org/abs/2511.18868
作者: Dezhi Ran,Shuxiao Xie,Mingfang Ji,Ziyue Hua,Mengzhou Wu,Yuan Cao,Yuzhe Guo,Yu Hao,Linyi Li,Yitao Hu,Tao Xie
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Work in progress

点击查看摘要

[AI-45] me Travel: LLM -Assisted Semantic Behavior Localization with Git Bisect

链接: https://arxiv.org/abs/2511.18854
作者: Yujing Wang,Weize Hong
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注: submitted to Git Bisect SCALCOM 2025 Calgary (to be published)

点击查看摘要

[AI-46] Pre-Filtering Code Suggestions using Developer Behavioral Telemetry to Optimize LLM -Assisted Programming

链接: https://arxiv.org/abs/2511.18849
作者: Mohammad Nour Al Awad,Sergey Ivanov,Olga Tikhonova
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注: \c{opyright} 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses

点击查看摘要

[AI-47] WaveTuner: Comprehensive Wavelet Subband Tuning for Time Series Forecasting

链接: https://arxiv.org/abs/2511.18846
作者: Yubo Wang,Hui He,Chaoxi Niu,Zhendong Niu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-48] UNeMo: Collaborative Visual-Language Reasoning and Navigation via a Multimodal World Model

链接: https://arxiv.org/abs/2511.18845
作者: Changxin Huang,Lv Tang,Zhaohuan Zhan,Lisha Yu,Runhao Zeng,Zun Liu,Zhengjie Wang,Jianqiang Li
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-49] Optimizing LLM Code Suggestions: Feedback-Driven Timing with Lightweight State Bounds

链接: https://arxiv.org/abs/2511.18842
作者: Mohammad Nour Al Awad,Sergey Ivanov,Olga Tikhonova
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注: \c{opyright} 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses

点击查看摘要

[AI-50] Federated style aware transformer aggregation of representations

链接: https://arxiv.org/abs/2511.18841
作者: Mincheol Jeon,Euinam Huh
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC)
备注:

点击查看摘要

[AI-51] Addressing Situated Teaching Needs: A Multi-Agent Framework for Automated Slide Adaptation

链接: https://arxiv.org/abs/2511.18840
作者: Binglin Liu,Yucheng Wang,Zheyuan Zhang,Jiyuan Lu,Shen Yang,Daniel Zhang-Li,Huiqin Liu,Jifan Yu
机构: 未知
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-52] NEZHA: A Zero-sacrifice and Hyperspeed Decoding Architecture for Generative Recommendations

链接: https://arxiv.org/abs/2511.18793
作者: Yejing Wang,Shengyu Zhou,Jinyu Lu,Ziwei Liu,Langming Liu,Maolin Wang,Wenlin Zhang,Feng Li,Wenbo Su,Pengjie Wang,Jian Xu,Xiangyu Zhao
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-53] Re-Key-Free Risky-Free: Adaptable Model Usage Control

链接: https://arxiv.org/abs/2511.18772
作者: Zihan Wang,Zhongkui Ma,Xinguo Feng,Chuan Yan,Dongge Liu,Ruoxi Sun,Derui Wang,Minhui Xue,Guangdong Bai
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-54] HERMES: Towards Efficient and Verifiable Mathematical Reasoning in LLM s

链接: https://arxiv.org/abs/2511.18760
作者: Azim Ospanov,Zijin Feng,Jiacheng Sun,Haoli Bai,Xin Shen,Farzan Farnia
机构: 未知
类目: Artificial Intelligence (cs.AI); Formal Languages and Automata Theory (cs.FL)
备注:

点击查看摘要

[AI-55] A Problem-Oriented Taxonomy of Evaluation Metrics for Time Series Anomaly Detection

链接: https://arxiv.org/abs/2511.18739
作者: Kaixiang Yang,Jiarong Liu,Yupeng Song,Shuanghua Yang,Yujue Zhou
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML)
备注:

点击查看摘要

[AI-56] N2N: A Parallel Framework for Large-Scale MILP under Distributed Memory

链接: https://arxiv.org/abs/2511.18723
作者: Longfei Wang,Junyan Liu,Fan Zhang,Jiangwen Wei,Yuanhua Tang,Jie Sun,Xiaodong Luo
机构: 未知
类目: Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Optimization and Control (math.OC)
备注: 18 pages, 2 figures

点击查看摘要

[AI-57] AIRHILT: A Human-in-the-Loop Testbed for Multimodal Conflict Detection in Aviation

链接: https://arxiv.org/abs/2511.18718
作者: Omar Garib,Jayaprakash D. Kambhampaty,Olivia J. Pinon Fischer,Dimitri N. Mavris
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注: 9 pages, 4 figures, 1 table, 1 algorithm

点击查看摘要

[AI-58] HuggingR4: A Progressive Reasoning Framework for Discovering Optimal Model Companions

链接: https://arxiv.org/abs/2511.18715
作者: Shaoyin Ma,Jie Song,Huiqiong Wang,Li Sun,Mingli Song
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: 19 pages, 4 figures

点击查看摘要

[AI-59] MAGMA-Edu: Multi-Agent Generative Multimodal Framework for Text-Diagram Educational Question Generation

链接: https://arxiv.org/abs/2511.18714
作者: Zhenyu Wu,Jian Li,Hua Huang
机构: 未知
类目: Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注:

点击查看摘要

[AI-60] Low-Rank GEMM: Efficient Matrix Multiplication via Low-Rank Approximation with FP8 Acceleration

链接: https://arxiv.org/abs/2511.18674
作者: Alfredo Metere
机构: 未知
类目: Performance (cs.PF); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-61] FHE-Agent : Automating CKKS Configuration for Practical Encrypted Inference via an LLM -Guided Agent ic Framework

链接: https://arxiv.org/abs/2511.18653
作者: Nuo Xu,Zhaoting Gong,Ran Ran,Jinwei Tang,Wujie Wen,Caiwen Ding
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-62] Lean 5.0: A Predictive Human-AI and Ethically Grounded Paradigm for Construction Management

链接: https://arxiv.org/abs/2511.18651
作者: Atena Khoshkonesh,Mohsen Mohammadagha,Navid Ebrahimi,Narges Sadeghigolshan
机构: 未知
类目: Computational Engineering, Finance, and Science (cs.CE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-63] Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost

链接: https://arxiv.org/abs/2511.18643
作者: Haojun Xia,Xiaoxia Wu,Jisen Li,Robert Wu,Junxiong Wang,Jue Wang,Chenxi Li,Aman Singhal,Alay Dilipbhai Shah,Alpay Ariyak,Donglin Zhuang,Zhongzhu Zhou,Ben Athiwaratkun,Zhen Zheng,Shuaiwen Leon Song
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-64] Bridging Philosophy and Machine Learning: A Structuralist Framework for Classifying Neural Network Representations

链接: https://arxiv.org/abs/2511.18633
作者: Yildiz Culcu
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 7 pages, 1 figure, 1 table. Developed from the author’s bachelor thesis but substantially revised and reformulated for research publication

点击查看摘要

[AI-65] KAN vs LSTM Performance in Time Series Forecasting STOC

链接: https://arxiv.org/abs/2511.18613
作者: Tabish Ali Rather,S M Mahmudul Hasan Joy,Nadezda Sukhorukova,Federico Frascoli
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: This paper compares Kolmogorov-Arnold Networks (KANs) and LSTMs for forecasting stock prices, highlighting that LSTMs provide superior predictive accuracy while KANs offer better interpretability and efficiency in limited-resource settings. Practical findings and future research directions are discussed

点击查看摘要

[AI-66] Universality in Collective Intelligence on the Rubiks Cube

链接: https://arxiv.org/abs/2511.18609
作者: David Krakauer,Gülce Kardeş,Joshua Grochow
机构: 未知
类目: Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC)
备注:

点击查看摘要

[AI-67] An Analysis of Constraint-Based Multi-Agent Pathfinding Algorithms

链接: https://arxiv.org/abs/2511.18604
作者: Hannah Lee,James D. Motes,Marco Morales,Nancy M. Amato
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
备注:

点击查看摘要

[AI-68] Strategic Decision Framework for Enterprise LLM Adoption

链接: https://arxiv.org/abs/2511.18589
作者: Michael Trusov,Minha Hwang,Zainab Jamal,Swarup Chandra
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注: 14 pages, 1 key figure

点击查看摘要

[AI-69] Foundations of Artificial Intelligence Frameworks: Notion and Limits of AGI

链接: https://arxiv.org/abs/2511.18517
作者: Khanh Gia Bui
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 49 pages, 4 pictures

点击查看摘要

[AI-70] Evaluating perturbation robustnessof generative systems that use COBOL code inputs ICSE

链接: https://arxiv.org/abs/2511.18488
作者: Samuel Ackerman,Wesam Ibraheem,Orna Raz,Marcel Zalmanovici
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注: 16 pages (8 main, 8 appendix). Accepted to AI-SQE (ICSE, 2026): The 1st International Workshop on AI for Software Quality Evaluation: Judgment, Metrics, Benchmarks, and Beyond

点击查看摘要

[AI-71] ORIGAMISPACE: Benchmarking Multimodal LLM s in Multi-Step Spatial Reasoning with Mathematical Constraints

链接: https://arxiv.org/abs/2511.18450
作者: Rui Xu,Dakuan Lu,Zicheng Zhao,Xiaoyu Tan,Xintao Wang,Siyu Yuan,Jiangjie Chen,Yinghui Xu
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-72] A Multimodal Conversational Agent for Tabular Data Analysis

链接: https://arxiv.org/abs/2511.18405
作者: Mohammad Nour Al Awad,Sergey Ivanov,Olga Tikhonova,Ivan Khodnenko
机构: 未知
类目: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Information Retrieval (cs.IR)
备注: \c{opyright} 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses

点击查看摘要

[AI-73] Pre-training Graph Neural Networks on 2D and 3D Molecular Structures by using Multi-View Conditional Information Bottleneck

链接: https://arxiv.org/abs/2511.18404
作者: Van Thuy Hoang,O-Joun Lee
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-74] Natural Emergent Misalignment from Reward Hacking in Production RL

链接: https://arxiv.org/abs/2511.18397
作者: Monte MacDiarmid,Benjamin Wright,Jonathan Uesato,Joe Benton,Jon Kutasov,Sara Price,Naia Bouscal,Sam Bowman,Trenton Bricken,Alex Cloud,Carson Denison,Johannes Gasteiger,Ryan Greenblatt,Jan Leike,Jack Lindsey,Vlad Mikulik,Ethan Perez,Alex Rodrigues,Drake Thomas,Albert Webson,Daniel Ziegler,Evan Hubinger
机构: 未知
类目: Artificial Intelligence (cs.AI); Software Engineering (cs.SE)
备注:

点击查看摘要

[AI-75] Scaling Implicit Fields via Hypernetwork-Driven Multiscale Coordinate Transformations

链接: https://arxiv.org/abs/2511.18387
作者: Plein Versace
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-76] NSTR: Neural Spectral Transport Representation for Space-Varying Frequency Fields

链接: https://arxiv.org/abs/2511.18384
作者: Plein Versace
机构: 未知
类目: ound (cs.SD); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-77] Progressive Localisation in Localist LLM s

链接: https://arxiv.org/abs/2511.18375
作者: Joachim Diederich
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-78] Wireless Power Transfer and Intent-Driven Network Optimization in AAVs-assisted IoT for 6G Sustainable Connectivity

链接: https://arxiv.org/abs/2511.18368
作者: Yue Hu,Xiaoming He,Rui Yuan,Shahid Mumtaz
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-79] KGpipe: Generation and Evaluation of Pipelines for Data Integration into Knowledge Graphs

链接: https://arxiv.org/abs/2511.18364
作者: Marvin Hofer,Erhard Rahm
机构: 未知
类目: Artificial Intelligence (cs.AI); Databases (cs.DB); Machine Learning (cs.LG)
备注: 15 KG pipelines (9 single source, 6 multi source)

点击查看摘要

[AI-80] oward an AI-Native Internet: Rethinking the Web Architecture for Semantic Retrieval

链接: https://arxiv.org/abs/2511.18354
作者: Muhammad Bilal,Zafar Qazi,Marco Canini
机构: 未知
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
备注:

点击查看摘要

[AI-81] Clinician-in-the-Loop Smart Home System to Detect Urinary Tract Infection Flare-Ups via Uncertainty-Aware Decision Support AAAI-26

链接: https://arxiv.org/abs/2511.18334
作者: Chibuike E. Ugwu,Roschelle Fritz,Diane J. Cook,Janardhan Rao Doppa
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Accepted for publication at IAAI-26 / AAAI-26

点击查看摘要

[AI-82] Weakly-supervised Latent Models for Task-specific Visual-Language Control

链接: https://arxiv.org/abs/2511.18319
作者: Xian Yeow Lee,Lasitha Vidyaratne,Gregory Sin,Ahmed Farahat,Chetan Gupta
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Systems and Control (eess.SY)
备注:

点击查看摘要

[AI-83] AnyExperts: On-Demand Expert Allocation for Multimodal Language Models with Mixture of Expert

链接: https://arxiv.org/abs/2511.18314
作者: Yuting Gao,Wang Lan,Hengyuan Zhao,Linjiang Huang,Si Liu,Qingpei Guo
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-84] he Catastrophic Paradox of Human Cognitive Frameworks in Large Language Model Evaluation: A Comprehensive Empirical Analysis of the CHC-LLM Incompatibility

链接: https://arxiv.org/abs/2511.18302
作者: Mohan Reddy
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-85] Cross-Disciplinary Knowledge Retrieval and Synthesis: A Compound AI Architecture for Scientific Discovery

链接: https://arxiv.org/abs/2511.18298
作者: Svitlana Volkova,Peter Bautista,Avinash Hiriyanna,Gabriel Ganberg,Isabel Erickson,Zachary Klinefelter,Nick Abele,Hsien-Te Kao,Grant Engberson
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-86] Deep Learning Decision Support System for Open-Pit Mining Optimisation: GPU-Accelerated Planning Under Geological Uncertainty

链接: https://arxiv.org/abs/2511.18296
作者: Iman Rahimi
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: 67 pages

点击查看摘要

[AI-87] MultiDiffNet: A Multi-Objective Diffusion Framework for Generalizable Brain Decoding

链接: https://arxiv.org/abs/2511.18294
作者: Mengchun Zhang,Kateryna Shapovalenko,Yucheng Shao,Eddie Guo,Parusha Pradhan
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Neurons and Cognition (q-bio.NC)
备注:

点击查看摘要

[AI-88] Steering Latent Traits Not Learned Facts: An Empirical Study of Activation Control Limits

链接: https://arxiv.org/abs/2511.18284
作者: Tetiana Bas,Krystian Novak
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-89] Clinician-Directed Large Language Model Software Generation for Therapeutic Interventions in Physical Rehabilitation

链接: https://arxiv.org/abs/2511.18274
作者: Edward Kim,Yuri Cho,Jose Eduardo E. Lima,Julie Muccini,Jenelle Jindal,Alison Scheid,Erik Nelson,Seong Hyun Park,Yuchen Zeng,Alton Sturgis,Caesar Li,Jackie Dai,Sun Min Kim,Yash Prakash,Liwen Sun,Isabella Hu,Hongxuan Wu,Daniel He,Wiktor Rajca,Cathra Halabi,Maarten Lansberg,Bjoern Hartmann,Sanjit A. Seshia
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-90] LLM Reasoning for Cold-Start Item Recommendation

链接: https://arxiv.org/abs/2511.18261
作者: Shijun Li,Yu Wang,Jin Wang,Ying Li,Joydeep Ghosh,Anne Cocos
机构: 未知
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-91] Hybrid Agent ic AI and Multi-Agent Systems in Smart Manufacturing

链接: https://arxiv.org/abs/2511.18258
作者: Mojtaba A. Farahani,Md Irfan Khan,Thorsten Wuest
机构: 未知
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-92] Developing an AI Course for Synthetic Chemistry Students

链接: https://arxiv.org/abs/2511.18244
作者: Zhiling Zheng
机构: 未知
类目: Artificial Intelligence (cs.AI); Materials Science (cond-mat.mtrl-sci); Physics Education (physics.ed-ph)
备注: 17 pages, 3 figures

点击查看摘要

[AI-93] Can LLM s Help Allocate Public Health Resources? A Case Study on Childhood Lead Testing

链接: https://arxiv.org/abs/2511.18239
作者: Mohamed Afane,Ying Wang,Juntao Chen
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-94] A Novel and Practical Universal Adversarial Perturbations against Deep Reinforcement Learning based Intrusion Detection Systems

链接: https://arxiv.org/abs/2511.18223
作者: H. Zhang,L. Zhang,G. Epiphaniou,C. Maple
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注: 13 pages, 7 Figures,

点击查看摘要

[AI-95] Enhancing Large Language Models for Automated Homework Assessment in Undergraduate Circuit Analysis

链接: https://arxiv.org/abs/2511.18221
作者: Liangliang Chen,Huiru Xie,Zhihao Qin,Yiming Guo,Jacqueline Rohde,Ying Zhang
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注: Accepted to 2025 Frontiers in Education (FIE) Conference

点击查看摘要

[AI-96] he Workflow as Medium: A Framework for Navigating Human-AI Co-Creation

链接: https://arxiv.org/abs/2511.18182
作者: Lee Ackerman
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
备注: 57 pages, 13 images, 6 tables

点击查看摘要

[AI-97] MOMA-AC: A preference-driven actor-critic framework for continuous multi-objective multi-agent reinforcement learning

链接: https://arxiv.org/abs/2511.18181
作者: Adam Callaghan,Karl Mason,Patrick Mannion
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 23 pages, 5 figures

点击查看摘要

[AI-98] BPMN to PDDL: Translating Business Workflows for AI Planning

链接: https://arxiv.org/abs/2511.18171
作者: Jasper Nie,Christian Muise,Victoria Armstrong
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: 8 pages, 3 figures. Code and generated PDDL outputs available at this https URL

点击查看摘要

[AI-99] owards a General Framework for HTN Modeling with LLM s ICAPS ICAPS25

链接: https://arxiv.org/abs/2511.18165
作者: Israel Puerta-Merino,Carlos Núñez-Molina,Pablo Mesejo,Juan Fernández-Olivares
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注: 10 pages, 5 figures, to be published in the Workshop on Planning in the Era of LLMs ( LM4Plan - this https URL ) and the Workshop on Hierarchical Planning ( HPlan - this https URL ), both in the International Conference on Automated Planning and Scheduling (ICAPS) 2025

点击查看摘要

[AI-100] Graph Neural Networks vs Convolutional Neural Networks for Graph Domination Number Prediction

链接: https://arxiv.org/abs/2511.18150
作者: Randy Davila,Beyzanur Ispir
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Combinatorics (math.CO)
备注:

点击查看摘要

[AI-101] A New Error Temporal Difference Algorithm for Deep Reinforcement Learning in Microgrid Optimization

链接: https://arxiv.org/abs/2511.18093
作者: Fulong Yao,Wanqing Zhao,Matthew Forshaw
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Have been accepted by 2024 9th International Conference on Renewable Energy and Conservation (ICREC 2024)

点击查看摘要

[AI-102] Continually Evolving Skill Knowledge in Vision Language Action Model

链接: https://arxiv.org/abs/2511.18085
作者: Yuxuan Wu,Guangming Wang,Zhiheng Yang,Maoqing Yao,Brian Sheil,Hesheng Wang
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-103] he Alignment Paradox of Medical Large Language Models in Infertility Care: Decoupling Algorithmic Improvement from Clinical Decision-making Quality

链接: https://arxiv.org/abs/2511.18084
作者: Dou Liu,Ying Long,Sophia Zuoqiu,Kaipeng Xie,Runze Yang,Di Liu,Kang Li,Yiting Lin,Hanyi Liu,Rong Yin,Tian Tang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 22 pages 5 figures

点击查看摘要

[AI-104] Diffusion-based Surrogate Model for Time-varying Underwater Acoustic Channels

链接: https://arxiv.org/abs/2511.18078
作者: Kexin Li,Mandar Chitre
机构: 未知
类目: ound (cs.SD); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-105] Fidelity-Aware Recommendation Explanations via Stochastic Path Integration

链接: https://arxiv.org/abs/2511.18047
作者: Oren Barkan,Yahlly Schein,Yehonatan Elisha,Veronika Bogina,Mikhail Baklanov,Noam Koenigstein
机构: 未知
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-106] MASTEST: A LLM -Based Multi-Agent System For RESTful API Tests

链接: https://arxiv.org/abs/2511.18038
作者: Xiaoke Han,Hong Zhu
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 14 Page of main text plus 4 pages of appendix

点击查看摘要

[AI-107] Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems

链接: https://arxiv.org/abs/2511.18024
作者: Dor Arviv,Yehonatan Elisha,Oren Barkan,Noam Koenigstein
机构: 未知
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-108] Save Revisit Retain: A Scalable Framework for Enhancing User Retention in Large-Scale Recommender Systems

链接: https://arxiv.org/abs/2511.18013
作者: Weijie Jiang,Armando Ordorica,Jaewon Yang,Olafur Gudmundsson,Yucheng Tu,Huizhong Duan
机构: 未知
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-109] Reward Engineering for Spatial Epidemic Simulations: A Reinforcement Learning Platform for Individual Behavioral Learning

链接: https://arxiv.org/abs/2511.18000
作者: Radman Rakhshandehroo,Daniel Coombs
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Populations and Evolution (q-bio.PE)
备注: 35 pages, 15 figures and 14 tables

点击查看摘要

[AI-110] How Far Can LLM s Emulate Human Behavior?: A Strategic Analysis via the Buy-and-Sell Negotiation Game

链接: https://arxiv.org/abs/2511.17990
作者: Mingyu Jeon,Jaeyoung Suh,Suwan Cho,Dohyeon Kim
机构: 未知
类目: Artificial Intelligence (cs.AI); Computer Science and Game Theory (cs.GT)
备注:

点击查看摘要

[AI-111] Privacy Auditing of Multi-domain Graph Pre-trained Model under Membership Inference Attacks AAAI2026

链接: https://arxiv.org/abs/2511.17989
作者: Jiayi Luo,Qingyun Sun,Yuecen Wei,Haonan Yuan,Xingcheng Fu,Jianxin Li
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
备注: Accepted by AAAI 2026(Oral)

点击查看摘要

[AI-112] Escaping Optimization Stagnation: Taking Steps Beyond Task Arithmetic via Difference Vectors

链接: https://arxiv.org/abs/2511.17987
作者: Jinping Wang,Zhiqiang Gao,Dinggen Zhang,Zhiwu Xie
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-113] owards Effective Stealthy and Persistent Backdoor Attacks Targeting Graph Foundation Models AAAI2026

链接: https://arxiv.org/abs/2511.17982
作者: Jiayi Luo,Qingyun Sun,Lingjuan Lyu,Ziwei Zhang,Haonan Yuan,Xingcheng Fu,Jianxin Li
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注: Accepted by AAAI 2026

点击查看摘要

[AI-114] Comprehensive Design Space Exploration for Tensorized Neural Network Hardware Accelerators

链接: https://arxiv.org/abs/2511.17971
作者: Jinsong Zhang,Minghe Li,Jiayi Tian,Jinming Lu,Zheng Zhang
机构: 未知
类目: Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-115] Hybrid LSTM and PPO Networks for Dynamic Portfolio Optimization

链接: https://arxiv.org/abs/2511.17963
作者: Jun Kevin,Pujianto Yugopuspito
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Portfolio Management (q-fin.PM)
备注: 12 pages, 8 figures, 2 tables, accepted at 2025 8th Artificial Intelligence and Cloud Computing Conference

点击查看摘要

[AI-116] owards Automating Data Access Permissions in AI Agents

链接: https://arxiv.org/abs/2511.17959
作者: Yuhao Wu,Ke Yang,Franziska Roesner,Tadayoshi Kohno,Ning Zhang,Umar Iqbal
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
备注: Accepted by the IEEE Symposium on Security and Privacy (SP) 2026

点击查看摘要

[AI-117] Leverag ing Evidence-Guided LLM s to Enhance Trustworthy Depression Diagnosis

链接: https://arxiv.org/abs/2511.17947
作者: Yining Yuan,J. Ben Tamo,Micky C. Nnamdi,Yifei Wang,May D. Wang
机构: 未知
类目: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
备注:

点击查看摘要

[AI-118] Neural Graph Navigation for Intelligent Subgraph Matching AAAI2026

链接: https://arxiv.org/abs/2511.17939
作者: Yuchen Ying,Yiyang Dai,Wenda Li,Wenjie Huang,Rui Wang,Tongya Zheng,Yu Wang,Hanyang Yuan,Mingli Song
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Under review at AAAI 2026

点击查看摘要

[AI-119] Alignment Faking - the Train - Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria

链接: https://arxiv.org/abs/2511.17937
作者: Kartik Garg,Shourya Mishra,Kartikeya Sinha,Ojaswi Pratap Singh,Ayush Chopra,Kanishk Rai,Ammar Sheikh,Raghav Maheshwari,Aman Chadha,Vinija Jain,Amitava Das
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-120] ChemVTS-Bench: Evaluating Visual-Textual-Symbolic Reasoning of Multimodal Large Language Models in Chemistry

链接: https://arxiv.org/abs/2511.17909
作者: Zhiyuan Huang,Baichuan Yang,Zikun He,Yanhong Wu,Fang Hongyu,Zhenhe Liu,Lin Dongsheng,Bing Su
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-121] AnimAgents : Coordinating Multi-Stage Animation Pre-Production with Human-Multi-Agent Collaboration

链接: https://arxiv.org/abs/2511.17906
作者: Wen-Fan Wang,Chien-Ting Lu,Jin Ping Ng,Yi-Ting Chiu,Ting-Ying Lee,Miaosen Wang,Bing-Yu Chen,Xiang ‘Anthony’ Chen
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-122] Statistically-Guided Dual-Domain Meta-Learning with Adaptive Multi-Prototype Aggregation for Distributed Fiber Optic Sensing

链接: https://arxiv.org/abs/2511.17902
作者: Yifan He,Haodong Zhang,Qiuheng Song,Lin Lei,Zhenxuan Zeng,Haoyang He,Hongyan Wu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
备注:

点击查看摘要

[AI-123] raining Emergent Joint Associations: A Reinforcement Learning Approach to Creative Thinking in Language Models

链接: https://arxiv.org/abs/2511.17876
作者: Mukul Singh,Ananya Singha,Aishni Parab,Pronita Mehrotra,Sumit Gulwani
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-124] QuickLAP: Quick Language-Action Preference Learning for Autonomous Driving Agents

链接: https://arxiv.org/abs/2511.17855
作者: Jordan Abi Nader,David Lee,Nathaniel Dennler,Andreea Bobu
机构: 未知
类目: Artificial Intelligence (cs.AI); Robotics (cs.RO)
备注:

点击查看摘要

[AI-125] A Low-Code Methodology for Developing AI Kiosks: a Case Study with the DIZEST Platform

链接: https://arxiv.org/abs/2511.17853
作者: SunMin Moon,Jangwon Gim,Chaerin Kim,Yeeun Kim,YoungJoo Kim,Kang Choi
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注: 5 pages, 2 figures, conference, 2 tables

点击查看摘要

[AI-126] Learning to Debug: LLM -Organized Knowledge Trees for Solving RTL Assertion Failures

链接: https://arxiv.org/abs/2511.17833
作者: Yunsheng Bai,Haoxing Ren
机构: 未知
类目: Artificial Intelligence (cs.AI); Software Engineering (cs.SE)
备注:

点击查看摘要

[AI-127] Unified Class and Domain Incremental Learning with Mixture of Experts for Indoor Localization

链接: https://arxiv.org/abs/2511.17829
作者: Akhil Singampalli,Sudeep Pasricha
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-128] APRIL: Annotations for Policy evaluation with Reliable Inference from LLM s

链接: https://arxiv.org/abs/2511.17818
作者: Aishwarya Mandyam,Kalyani Limaye,Barbara E. Engelhardt,Emily Alsentzer
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-129] Episodic Memory in Agent ic Frameworks: Suggesting Next Tasks

链接: https://arxiv.org/abs/2511.17775
作者: Sandro Rama Fiorini,Leonardo G. Azevedo,Raphael M. Thiago,Valesca M. de Sousa,Anton B. Labate,Viviane Torres da Silva
机构: 未知
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-130] AI- and Ontology-Based Enhancements to FMEA for Advanced Systems Engineering: Current Developments and Future Directions

链接: https://arxiv.org/abs/2511.17743
作者: Haytham Younus,Sohag Kabir,Felician Campean,Pascal Bonnaud,David Delaux
机构: 未知
类目: Artificial Intelligence (cs.AI); Systems and Control (eess.SY)
备注: This manuscript is based on research undertaken by our doctoral student at the University of Bradford. The associated PhD thesis has been formally submitted to the University and is currently awaiting final examination. The review article is being shared on arXiv to make the review accessible to the research community while the thesis examination process is ongoing

点击查看摘要

[AI-131] M3-Bench: Multi-Modal Multi-Hop Multi-Threaded Tool-Using MLLM Agent Benchmark

链接: https://arxiv.org/abs/2511.17729
作者: Yang Zhou,Mingyu Zhao,Zhenting Wang,Difei Gu,Bangwei Guo,Ruosong Ye,Ligong Han,Can Jin,Dimitris N. Metaxas
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-132] Learning the Value of Value Learning

链接: https://arxiv.org/abs/2511.17714
作者: Alex John London,Aydin Mohseni
机构: 未知
类目: Artificial Intelligence (cs.AI); Computer Science and Game Theory (cs.GT)
备注: 27 pages, 6 figures, mathematical appendix

点击查看摘要

[AI-133] Liberating Logic in the Age of AI: Going Beyond Programming with Computational Thinking

链接: https://arxiv.org/abs/2511.17696
作者: Douglas C. Schmidt,Dan Runfola
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
备注: 15 pages and 17 figures

点击查看摘要

[AI-134] ARISE: Agent ic Rubric-Guided Iterative Survey Engine for Automated Scholarly Paper Generation

链接: https://arxiv.org/abs/2511.17689
作者: Zi Wang,Xingqiao Wang,Sangah Lee,Xiaowei Xu
机构: 未知
类目: Digital Libraries (cs.DL); Artificial Intelligence (cs.AI)
备注: 20 pages including an appendix, 7 figures and 6 tables

点击查看摘要

[AI-135] Enhancing Adversarial Transferability through Block Stretch and Shrink

链接: https://arxiv.org/abs/2511.17688
作者: Quan Liu,Feng Ye,Chenhao Lu,Shuming Zhen,Guanliang Huang,Lunzhe Chen,Xudong Ke
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: code will be releace

点击查看摘要

[AI-136] Datacenters in the Desert: Feasibility and Sustainability of LLM Inference in the Middle East

链接: https://arxiv.org/abs/2511.17683
作者: Lara Hassan,Mohamed ElZeftawy,Abdulrahman Mahmoud
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
备注: 3 pages, 1 figure

点击查看摘要

[AI-137] Research and Prototyping Study of an LLM -Based Chatbot for Electromagnetic Simulations

链接: https://arxiv.org/abs/2511.17680
作者: Albert Piwonski,Mirsad Hadžiefendić
机构: 未知
类目: Computational Engineering, Finance, and Science (cs.CE); Artificial Intelligence (cs.AI)
备注: This paper has been submitted to COMPEL for possible publication, published by Emerald Publishing Limited

点击查看摘要

[AI-138] Chatbots to strengthen democracy: An interdisciplinary seminar to train identifying argumentation techniques of science denial

链接: https://arxiv.org/abs/2511.17678
作者: Ingo Siegert,Jan Nehring,Aranxa Márquez Ampudia,Matthias Busch,Stefan Hillmann
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注: 6 pages, 4 figures

点击查看摘要

[AI-139] Cognitive Inception: Agent ic Reasoning against Visual Deceptions by Injecting Skepticism

链接: https://arxiv.org/abs/2511.17672
作者: Yinjie Zhao,Heng Zhao,Bihan Wen,Joey Tianyi Zhou
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-140] Empa: An AI-Powered Virtual Mentor for Developing Global Collaboration Skills in HPC Education

链接: https://arxiv.org/abs/2511.17669
作者: Ashish,Aparajita Jaiswal,Sudip Vhaduri,Niveditha Nerella,Shubham Jha
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-141] Evaluating Adversarial Vulnerabilities in Modern Large Language Models

链接: https://arxiv.org/abs/2511.17666
作者: Tom Perel
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-142] AI-based framework to predict animal and pen feed intake in feedlot beef cattle

链接: https://arxiv.org/abs/2511.17663
作者: Alex S. C. Maia,John B. Hall,Hugo F. M. Milan,Izabelle A. M. A. Teixeira
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-143] Frugality in second-order optimization: floating-point approximations for Newtons method

链接: https://arxiv.org/abs/2511.17660
作者: Giuseppe Carrino,Elena Loli Piccolomini,Elisa Riccietti,Theo Mary
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Optimization and Control (math.OC)
备注: Master Thesis for the Artificial Intelligence course at University of Bologna

点击查看摘要

[AI-144] Dialogue Diplomats: An End-to-End Multi-Agent Reinforcement Learning System for Automated Conflict Resolution and Consensus Building

链接: https://arxiv.org/abs/2511.17654
作者: Deepak Bolleddu
机构: 未知
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-145] MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba for Complex Parametric Sequence ICCV2025

链接: https://arxiv.org/abs/2511.17647
作者: Liyuan Deng,Yunpeng Bai,Yongkang Dai,Xiaoshui Huang,Hongping Gan,Dongshuo Huang,Hao jiacheng,Yilei Shi
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: ICCV 2025 Conference

点击查看摘要

[AI-146] Hybrid Neuro-Symbolic Models for Ethical AI in Risk-Sensitive Domains

链接: https://arxiv.org/abs/2511.17644
作者: Chaitanya Kumar Kolli
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: 6 pages, 6 figures

点击查看摘要

[AI-147] Model-to-Model Knowledge Transmission (M2KT): A Data-Free Framework for Cross-Model Understanding Transfer

链接: https://arxiv.org/abs/2511.17638
作者: Pratham Sorte
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 8 pages including figures, prepared in IEEE conference style. Preprint. Work in progress

点击查看摘要

[AI-148] Can we use LLM s to bootstrap reinforcement learning? – A case study in digital health behavior change

链接: https://arxiv.org/abs/2511.17630
作者: Nele Albers,Esra Cemre Su de Groot,Loes Keijsers,Manon H. Hillegers,Emiel Krahmer
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注:

点击查看摘要

[AI-149] M2OE2-GL: A Family of Probabilistic Load Forecasters That Scales to Massive Customers

链接: https://arxiv.org/abs/2511.17623
作者: Haoran Li,Zhe Cheng,Muhao Guo,Yang Weng,Yannan Sun,Victor Tran,John Chainaranont
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 5 pages

点击查看摘要

[AI-150] Neurocircuitry-Inspired Hierarchical Graph Causal Attention Networks for Explainable Depression Identification ICLR2026

链接: https://arxiv.org/abs/2511.17622
作者: Weidao Chen,Yuxiao Yang,Yueming Wang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Under review for ICLR 2026

点击查看摘要

[AI-151] nsor Gauge Flow Models

链接: https://arxiv.org/abs/2511.17616
作者: Alexander Strunk,Roland Assam
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Differential Geometry (math.DG)
备注:

点击查看摘要

[AI-152] Energy-based Autoregressive Generation for Neural Population Dynamics

链接: https://arxiv.org/abs/2511.17606
作者: Ningling Ge,Sicheng Dai,Yu Zhu,Shan Yu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-153] BrainHGT: A Hierarchical Graph Transformer for Interpretable Brain Network Analysis

链接: https://arxiv.org/abs/2511.17604
作者: Jiajun Ma,Yongchao Zhang,Chao Zhang,Zhao Lv,Shengbing Pei
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-154] Beyond Surface-Level Similarity: Hierarchical Contamination Detection for Synthetic Training Data in Foundation Models

链接: https://arxiv.org/abs/2511.17602
作者: Sushant Mehta
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-155] From Projection to Prediction: Beyond Logits for Scalable Language Models

链接: https://arxiv.org/abs/2511.17599
作者: Jianbing Dong,Jianbin Chang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 17 pages, 2 figures, 4 algorithms

点击查看摘要

[AI-156] Boosting Reinforcement Learning in 3D Visuospatial Tasks Through Human-Informed Curriculum Design

链接: https://arxiv.org/abs/2511.17595
作者: Markus D. Solbach,John K. Tsotsos
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 12 pages, 11 figures, 5 tables

点击查看摘要

[AI-157] GigaEvo: An Open Source Optimization Framework Powered By LLM s And Evolution Algorithms

链接: https://arxiv.org/abs/2511.17592
作者: Valentin Khrulkov,Andrey Galichin,Denis Bashkirov,Dmitry Vinichenko,Oleg Travkin,Roman Alferov,Andrey Kuznetsov,Ivan Oseledets
机构: 未知
类目: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-158] SHAP Distance: An Explainability-Aware Metric for Evaluating the Semantic Fidelity of Synthetic Tabular Data

链接: https://arxiv.org/abs/2511.17590
作者: Ke Yu,Shigeru Ishikura,Yukari Usukura,Yuki Shigoku,Teruaki Hayashi
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (stat.ML)
备注: IEEE Bigdata

点击查看摘要

[AI-159] Emotion and Intention Guided Multi-Modal Learning for Sticker Response Selection

链接: https://arxiv.org/abs/2511.17587
作者: Yuxuan Hu,Jian Chen,Yuhao Wang,Zixuan Li,Jing Xiong,Pengyue Jia,Wei Wang,Chengming Li,Xiangyu Zhao
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-160] Hierarchical Adaptive Consensus Network: A Dynamic Framework for Scalable Consensus in Collaborative Multi-Agent AI Systems

链接: https://arxiv.org/abs/2511.17586
作者: Rathin Chandra Shit,Sharmila Subudhi
机构: 未知
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI)
备注: Submitted to Elsevier

点击查看摘要

[AI-161] LLM -Powered Text-Attributed Graph Anomaly Detection via Retrieval-Augmented Reasoning

链接: https://arxiv.org/abs/2511.17584
作者: Haoyan Xu,Ruizhi Qian,Zhengtao Yao,Ziyi Liu,Li Li,Yuqi Li,Yanshu Li,Wenqing Zheng,Daniele Rosa,Daniel Barcklow,Senthil Kumar,Jieyu Zhao,Yue Zhao
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-162] GateRA: Token-Aware Modulation for Parameter-Efficient Fine-Tuning AAAI2026

链接: https://arxiv.org/abs/2511.17582
作者: Jie Ou,Shuaihong Jiang,Yingjun Du,Cees G. M. Snoek
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Accepted by AAAI 2026

点击查看摘要

[AI-163] A novel strategy for multi-resource load balancing in agent -based systems

链接: https://arxiv.org/abs/2511.17580
作者: Leszek Sliwko,Aleksander Zgrzywa
机构: 未知
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Software Engineering (cs.SE)
备注:

点击查看摘要

[AI-164] Multi-Value Alignment for LLM s via Value Decorrelation and Extrapolation AAAI26

链接: https://arxiv.org/abs/2511.17579
作者: Hefei Xu,Le Wu,Chen Cheng,Hao Liu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: accepted by AAAI26 oral; 12 pages

点击查看摘要

[AI-165] Constructing Political Coordinates: Aggregating Over the Opposition for Diverse News Recommendation

链接: https://arxiv.org/abs/2511.17574
作者: Eamon Earl,Chen Ding,Richard Valenzano,Drai Paulen-Patterson
机构: 未知
类目: ocial and Information Networks (cs.SI); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注: Due to appear in the proceedings of the 2025 IEEE International Conference on Big Data

点击查看摘要

[AI-166] Binary BPE: A Family of Cross-Platform Tokenizers for Binary Analysis

链接: https://arxiv.org/abs/2511.17573
作者: Michael J. Bommarito II
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
备注: 17 pages, 3 figures, 9 tables. Paper source available at this https URL ; tokenizers available at this https URL - mjbommar/binary-tokenizer-001-{4k,8k,16k,32k,64k}

点击查看摘要

[AI-167] An improved clustering-based multi-swarm PSO using local diversification and topology information

链接: https://arxiv.org/abs/2511.17571
作者: Yves Matanga,Yanxia Sun,Zenghui Wang
机构: 未知
类目: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-168] Enhancing Robustness of Offline Reinforcement Learning Under Data Corruption via Sharpness-Aware Minimization AAAI2026

链接: https://arxiv.org/abs/2511.17568
作者: Le Xu,Jiayu Chen
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Accepted as an Oral Presentation at the AAAI 2026 Student Abstract and Poster Program (SAPP)

点击查看摘要

[AI-169] Dynamic Weight Adaptation in Spiking Neural Networks Inspired by Biological Homeostasis

链接: https://arxiv.org/abs/2511.17563
作者: Yunduo Zhou,Bo Dong,Chang Li,Yuanchen Wang,Xuefeng Yin,Yang Wang,Xin Yang
机构: 未知
类目: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-170] Gate-level boolean evolutionary geometric attention neural networks

链接: https://arxiv.org/abs/2511.17550
作者: Xianshuai Shi,Jianfeng Zhu,Leibo Liu
机构: 未知
类目: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-171] Evo* 2025 – Late-Breaking Abstracts Volume

链接: https://arxiv.org/abs/2511.17543
作者: A.M. Mora,A.I. Esparcia-Alcázar,M.S. Cruz
机构: 未知
类目: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI)
备注: LBAs accepted in Evo* 2025. Part of the Conference Proceedings

点击查看摘要

[AI-172] Leibnizs Monadology as Foundation for the Artificial Age Score: A Formal Architecture for Al Memory Evaluation

链接: https://arxiv.org/abs/2511.17541
作者: Seyma Yaman Kayadibi
机构: 未知
类目: Artificial Intelligence (cs.AI); Information Theory (cs.IT); Logic in Computer Science (cs.LO)
备注:

点击查看摘要

[AI-173] HiFiNet: Hierarchical Fault Identification in Wireless Sensor Networks via Edge-Based Classification and Graph Aggregation

链接: https://arxiv.org/abs/2511.17537
作者: Nguyen Van Son,Nguyen Tri Nghia,Nguyen Thi Hanh,Huynh Thi Thanh Binh
机构: 未知
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-174] Denoising Refinement Diffusion Models for Simultaneous Generation of Multi-scale Mobile Network Traffic

链接: https://arxiv.org/abs/2511.17532
作者: Xiaoqian Qi,Haoye Chai,Sichang Liu,Lei Yue,Raoyuan Pan,Yue Wang,Yong Li
机构: 未知
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-175] Evaluating Device-First Continuum AI (DFC-AI) for Autonomous Operations in the Energy Sector

链接: https://arxiv.org/abs/2511.17528
作者: Siavash M. Alamouti,Fay Arjomandi,Michel Burger,Bashar Altakrouri
机构: 未知
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI)
备注: 14 pages, 4 figures, 6 tables

点击查看摘要

[AI-176] RadioMapMotion: A Dataset and Baseline for Proactive Spatio-Temporal Radio Environment Prediction

链接: https://arxiv.org/abs/2511.17526
作者: Honggang Jia,Nan Cheng,Xiucheng Wang
机构: 未知
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-177] Safe Farming: Development of a Prevention System to Mitigate Vertebrates Crop Raiding

链接: https://arxiv.org/abs/2511.17520
作者: Razi Iqbal
机构: 未知
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET)
备注:

点击查看摘要

[AI-178] SAJD: Self-Adaptive Jamming Attack Detection in AI/ML Integrated 5G O-RAN Networks

链接: https://arxiv.org/abs/2511.17519
作者: Md Habibur Rahman,Md Sharif Hossen,Nathan H. Stephenson,Vijay K. Shah,Aloizio Da Silva
机构: 未知
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI)
备注: 6 pages, 5 figures, IEEE Military Communications Conference

点击查看摘要

[AI-179] Embedding Generative AI into Systems Analysis and Design Curriculum: Framework Case Study and Cross-Campus Empirical Evidence

链接: https://arxiv.org/abs/2511.17515
作者: Mahmoud Elkhodr,Ergun Gide
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: ~12,000 words; 4 figures; 6 tables; multi-site study (across 4 Australian campuses)

点击查看摘要

[AI-180] XAI-on-RAN: Explainable AI-native and GPU-Accelerated RAN Towards 6G NEURIPS2025

链接: https://arxiv.org/abs/2511.17514
作者: Osman Tugay Basaran,Falko Dressler
机构: 未知
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI)
备注: 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: AI and ML for Next-Generation Wireless Communications and Networking (AI4NextG)

点击查看摘要

[AI-181] A Multidisciplinary Design and Optimization (MDO) Agent Driven by Large Language Models

链接: https://arxiv.org/abs/2511.17511
作者: Bingkun Guo,Wentian Li,Xiaojian Liu,Jiaqi Luo,Zibin Yu,Dalong Dong,Shuyou Zhang,Yiming Zhang
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-182] Beyond Awareness: Investigating How AI and Psychological Factors Shape Human Self-Confidence Calibration

链接: https://arxiv.org/abs/2511.17509
作者: Federico Maria Cau,Lucio Davide Spano
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-183] he use of artificial intelligence in music creation: between interface and appropriation

链接: https://arxiv.org/abs/2511.17507
作者: Arnaud Zeller(LISEC),Emmanuelle Chevry Pebayle(Tecamp;Co, LISEC)
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: in French language

点击查看摘要

[AI-184] AURA: Adaptive Unified Reasoning and Automation with LLM -Guided MARL for NextG Cellular Networks

链接: https://arxiv.org/abs/2511.17506
作者: Narjes Nourzad,Mingyu Zong,Bhaskar Krishnamachari
机构: 未知
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-185] RTMol: Rethinking Molecule-text Alignment in a Round-trip View

链接: https://arxiv.org/abs/2511.12135
作者: Letian Chen,Runhan Shi,Gufeng Yu,Yang Yang
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Biomolecules (q-bio.BM)
备注:

点击查看摘要

[AI-186] Beyond Protein Language Models: An Agent ic LLM Framework for Mechanistic Enzyme Design

链接: https://arxiv.org/abs/2511.19423
作者: Bruno Jacob,Khushbu Agarwal,Marcel Baer,Peter Rice,Simone Raugei
机构: 未知
类目: Quantitative Methods (q-bio.QM); Artificial Intelligence (cs.AI)
备注: 10 pages, 4 figures

点击查看摘要

[AI-187] Neural Architecture Search for Quantum Autoencoders

链接: https://arxiv.org/abs/2511.19246
作者: Hibah Agha,Samuel Yen-Chi Chen,Huan-Hsin Tseng,Shinjae Yoo
机构: 未知
类目: Quantum Physics (quant-ph); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
备注:

点击查看摘要

[AI-188] orsion-Space Diffusion for Protein Backbone Generation with Geometric Refinement

链接: https://arxiv.org/abs/2511.19184
作者: Lakshaditya Singh,Adwait Shelke,Divyansh Agrawal
机构: 未知
类目: Biomolecules (q-bio.BM); Artificial Intelligence (cs.AI)
备注: 5 pages, 4 figures

点击查看摘要

[AI-189] Physics-informed Neural Operator Learning for Nonlinear Grad-Shafranov Equation

链接: https://arxiv.org/abs/2511.19114
作者: Siqi Ding,Zitong Zhang,Guoyang Shi,Xingyu Li,Xiang Gu,Yanan Xu,Huasheng Xie,Hanyue Zhao,Yuejiang Shi,Tianyuan Liu
机构: 未知
类目: Plasma Physics (physics.plasm-ph); Artificial Intelligence (cs.AI)
备注: 42 pages, 17 figures, 8 tables,

点击查看摘要

[AI-190] Enhancing low energy reconstruction and classification in KM3NeT/ORCA with transformers

链接: https://arxiv.org/abs/2511.18999
作者: Iván Mozún Mateo(on behalf of the KM3NeT collaboration)
机构: 未知
类目: High Energy Physics - Experiment (hep-ex); Instrumentation and Methods for Astrophysics (astro-ph.IM); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-191] MOCLIP: A Foundation Model for Large-Scale Nanophotonic Inverse Design

链接: https://arxiv.org/abs/2511.18980
作者: S. Rodionov,A. Burguete-Lopez,M. Makarenko,Q. Wang,F. Getman,A. Fratalocchi
机构: 未知
类目: Optics (physics.optics); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-192] Solving a Research Problem in Mathematical Statistics with AI Assistance

链接: https://arxiv.org/abs/2511.18828
作者: Edgar Dobriban
机构: 未知
类目: atistics Theory (math.ST); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-193] Barriers to AI Adoption: Image Concerns at Work

链接: https://arxiv.org/abs/2511.18582
作者: David Almog
机构: 未知
类目: General Economics (econ.GN); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注:

点击查看摘要

[AI-194] Re(Visiting) Time Series Foundation Models in Finance

链接: https://arxiv.org/abs/2511.18578
作者: Eghbal Rahimikia,Hao Ni,Weiguan Wang
机构: 未知
类目: Computational Finance (q-fin.CP); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Portfolio Management (q-fin.PM); Pricing of Securities (q-fin.PR)
备注:

点击查看摘要

[AI-195] MEDIC: a network for monitoring data quality in collider experiments

链接: https://arxiv.org/abs/2511.18172
作者: Juvenal Bassa,Arghya Chattopadhyay,Sudhir Malik,Mario Escabi Rivera
机构: 未知
类目: High Energy Physics - Experiment (hep-ex); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 17 pages, 1 appendix

点击查看摘要

[AI-196] Reinforcement Learning for Portfolio Optimization with a Financial Goal and Defined Time Horizons

链接: https://arxiv.org/abs/2511.18076
作者: Fermat Leukam,Rock Stephane Koffi,Prudence Djagba
机构: 未知
类目: Portfolio Management (q-fin.PM); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-197] Hierarchical biomarker thresholding: a model-agnostic framework for stability

链接: https://arxiv.org/abs/2511.18030
作者: O. Debeaupuis
机构: 未知
类目: Methodology (stat.ME); Artificial Intelligence (cs.AI); Statistics Theory (math.ST)
备注:

点击查看摘要

机器学习

[LG-0] Learning Robust Social Strategies with Large Language Models

链接: https://arxiv.org/abs/2511.19405
作者: Dereck Piche,Mohammed Muqeeth,Milad Aghajohari,Juan Duque,Michael Noukhovitch,Aaron Courville
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-1] PTF Testing Lower Bounds for Non-Gaussian Component Analysis

链接: https://arxiv.org/abs/2511.19398
作者: Ilias Diakonikolas,Daniel M. Kane,Sihan Liu,Thanasis Pittas
类目: Data Structures and Algorithms (cs.DS); Information Theory (cs.IT); Machine Learning (cs.LG); Statistics Theory (math.ST); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-2] Efficiency vs. Fidelity: A Comparative Analysis of Diffusion Probabilistic Models and Flow Matching on Low-Resource Hardware

链接: https://arxiv.org/abs/2511.19379
作者: Srishti Gupta,Yashasvee Taiwade
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-3] LLM -Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systems

链接: https://arxiv.org/abs/2511.19368
作者: Tianyang Duan,Zongyuan Zhang,Zheng Lin,Songxiao Guo,Xiuxian Guan,Guangyu Wu,Zihan Fang,Haotian Meng,Xia Du,Ji-Zhe Zhou,Heming Cui,Jun Luo,Yue Gao
类目: Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI)
*备注: 15 pages, 9 figures

点击查看摘要

[LG-4] Neural surrogates for designing gravitational wave detectors

链接: https://arxiv.org/abs/2511.19364
作者: Carlos Ruiz-Gonzalez,Sören Arlt,Sebastian Lehner,Arturs Berzins,Yehonathan Drori,Rana X Adhikari,Johannes Brandstetter,Mario Krenn
类目: Machine Learning (cs.LG); Instrumentation and Methods for Astrophysics (astro-ph.IM); General Relativity and Quantum Cosmology (gr-qc); Quantum Physics (quant-ph)
*备注: 20 pages, 7 figures, 4 tables

点击查看摘要

[LG-5] Enhancing Conformal Prediction via Class Similarity

链接: https://arxiv.org/abs/2511.19359
作者: Ariel Fargion,Lahav Dabah,Tom Tirer
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-6] Annotation-Free Class-Incremental Learning

链接: https://arxiv.org/abs/2511.19344
作者: Hari Chandana Kuchibhotla,K S Ananth,Vineeth N Balasubramanian
类目: Machine Learning (cs.LG)
*备注: 18 pages, 6 figures

点击查看摘要

[LG-7] argeted Manipulation: Slope-Based Attacks on Financial Time-Series Data

链接: https://arxiv.org/abs/2511.19330
作者: Dominik Luszczynski
类目: Machine Learning (cs.LG)
*备注: 13 pages, 6 figures, 4 tables, preprint; Total including Appendix: 21 pages, 11 figures, 7 tables

点击查看摘要

[LG-8] Understanding the Staged Dynamics of Transformers in Learning Latent Structure

链接: https://arxiv.org/abs/2511.19328
作者: Rohan Saha,Farzane Aminmansour,Alona Fyshe
类目: Machine Learning (cs.LG)
*备注: Preprint

点击查看摘要

[LG-9] Closing Gaps in Emissions Monitoring with Climate TRACE

链接: https://arxiv.org/abs/2511.19277
作者: Brittany V. Lancellotti,Jordan M. Malof,Aaron Davitt,Gavin McCormick,Shelby Anderson,Pol Carbó-Mestre,Gary Collins,Verity Crane,Zoheyr Doctor,George Ebri,Kevin Foster,Trey M. Gowdy,Michael Guzzardi,John Heal,Heather Hunter,David Kroodsma,Khandekar Mahammad Galib,Paul J. Markakis,Gavin McDonald,Daniel P. Moore,Eric D. Nguyen,Sabina Parvu,Michael Pekala,Christine D. Piatko,Amy Piscopo,Mark Powell,Krsna Raniga,Elizabeth P. Reilly,Michael Robinette,Ishan Saraswat,Patrick Sicurello,Isabella Söldner-Rembold,Raymond Song,Charlotte Underwood,Kyle Bradbury
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-10] Scalable Bayesian Network Structure Learning Using Tsetlin Machine to Constrain the Search Space

链接: https://arxiv.org/abs/2511.19273
作者: Kunal Dumbre,Lei Jiao,Ole-Christoffer Granmo
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-11] ny-TSM: Efficiently Training a Lightweight SOTA Time Series Foundation Model

链接: https://arxiv.org/abs/2511.19272
作者: Felix Birkel
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-12] Leverag ing Spatiotemporal Graph Neural Networks for Multi-Store Sales Forecasting

链接: https://arxiv.org/abs/2511.19267
作者: Manish Singh,Arpita Dayama
类目: Machine Learning (cs.LG)
*备注: 6 pages, 4 figures, 1 table

点击查看摘要

[LG-13] Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks

链接: https://arxiv.org/abs/2511.19265
作者: Bianka Kowalska,Halina Kwaśnicka
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-14] Empirical Comparison of Forgetting Mechanisms for UCB-based Algorithms on a Data-Driven Simulation Platform

链接: https://arxiv.org/abs/2511.19240
作者: Minxin Chen
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-15] From Raw Features to Effective Embeddings: A Three-Stage Approach for Multimodal Recipe Recommendation

链接: https://arxiv.org/abs/2511.19176
作者: Jeeho Shin,Kyungho Kim,Kijung Shin
类目: Machine Learning (cs.LG); Information Retrieval (cs.IR)
*备注:

点击查看摘要

[LG-16] First-order Sobolev Reinforcement Learning

链接: https://arxiv.org/abs/2511.19165
作者: Fabian Schramm,Nicolas Perrin-Gilbert,Justin Carpentier
类目: Machine Learning (cs.LG); Robotics (cs.RO)
*备注: Workshop paper at Differentiable Systems and Scientific Machine Learning, EurIPS 2025

点击查看摘要

[LG-17] BioArtlas: Computational Clustering of Multi-Dimensional Complexity in Bioart

链接: https://arxiv.org/abs/2511.19162
作者: Joonhyung Bae
类目: Information Retrieval (cs.IR); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG); Multimedia (cs.MM)
*备注:

点击查看摘要

[LG-18] Masked Diffusion Models are Secretly Learned-Order Autoregressive Models

链接: https://arxiv.org/abs/2511.19152
作者: Prateek Garg,Bhavya Kohli,Sunita Sarawagi
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: Accepted at EurIPS 2025 Workshop on Principles of Generative Modeling (PriGM)

点击查看摘要

[LG-19] Edge-Based Predictive Data Reduction for Smart Agriculture: A Lightweight Approach to Efficient IoT Communication

链接: https://arxiv.org/abs/2511.19103
作者: Dora Krekovic,Mario Kusek,Ivana Podnar Zarko,Danh Le-Phuoc
类目: Machine Learning (cs.LG)
*备注: Accepted for presentation and publication in the proceedings of the IEEE Annual Congress on Artificial Intelligence of Things (IEEE AIoT 2025)

点击查看摘要

[LG-20] Optimization of Deep Learning Models for Dynamic Market Behavior Prediction

链接: https://arxiv.org/abs/2511.19090
作者: Shenghan Zhao,Yuzhen Lin,Ximeng Yang,Qiaochu Lu,Haozhong Xue,Gaozhe Jiang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-21] Resolving Node Identifiability in Graph Neural Processes via Laplacian Spectral Encodings

链接: https://arxiv.org/abs/2511.19037
作者: Zimo Yan,Zheng Xie,Chang Liu,Yuan Wang
类目: Machine Learning (cs.LG); Probability (math.PR)
*备注:

点击查看摘要

[LG-22] 3D Dynamic Radio Map Prediction Using Vision Transformers for Low-Altitude Wireless Networks

链接: https://arxiv.org/abs/2511.19019
作者: Nguyen Duc Minh Quang,Chang Liu,Huy-Trung Nguyen,Shuangyang Li,Derrick Wing Kwan Ng,Wei Xiang
类目: Machine Learning (cs.LG)
*备注: 7 pages, 4 figures, submitted to IEEE ICC 2026

点击查看摘要

[LG-23] MIST: Mutual Information Via Supervised Training

链接: https://arxiv.org/abs/2511.18945
作者: German Gritsai,Megan Richards,Maxime Méloux,Kyunghyun Cho,Maxime Peyrard
类目: Machine Learning (cs.LG); Information Theory (cs.IT)
*备注:

点击查看摘要

[LG-24] Geometry-Aware Deep Congruence Networks for Manifold Learning in Cross-Subject Motor Imagery

链接: https://arxiv.org/abs/2511.18940
作者: Sanjeev Manivannan(1),Chandrashekar Lakshminarayan(1) ((1) Indian Institute of Technology Madras)
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 10 pages, 2 figures

点击查看摘要

[LG-25] Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning

链接: https://arxiv.org/abs/2511.18887
作者: Hyeong-Gun Joo,Songnam Hong,Seunghwan Lee,Dong-Joon Shin
类目: Machine Learning (cs.LG)
*备注: currently submitted and awaiting review at the IEEE Internet of Things Journal

点击查看摘要

[LG-26] Auto-ML Graph Neural Network Hypermodels for Outcome Prediction in Event-Sequence Data

链接: https://arxiv.org/abs/2511.18835
作者: Fang Wang,Lance Kosca,Adrienne Kosca,Marko Gacesa,Ernesto Damiani
类目: Machine Learning (cs.LG)
*备注: 6 pages

点击查看摘要

[LG-27] Leverag ing Duration Pseudo-Embeddings in Multilevel LSTM and GCN Hypermodels for Outcome-Oriented PPM

链接: https://arxiv.org/abs/2511.18830
作者: Fang Wang,Paolo Ceravolo,Ernesto Damiani
类目: Machine Learning (cs.LG)
*备注: 12 pages

点击查看摘要

[LG-28] owards Characterizing Knowledge Distillation of PPG Heart Rate Estimation Models ALT NEURIPS2025

链接: https://arxiv.org/abs/2511.18829
作者: Kanav Arora,Girish Narayanswamy,Shwetak Patel,Richard Li
类目: Machine Learning (cs.LG)
*备注: To be published in: 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Learning from Time Series for Health

点击查看摘要

[LG-29] Doubly Wild Refitting: Model-Free Evaluation of High Dimensional Black-Box Predictions under Convex Losses

链接: https://arxiv.org/abs/2511.18789
作者: Haichen Hu,David Simchi-Levi
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-30] Hypergraph Contrastive Learning for both Homophilic and Heterophilic Hypergraphs

链接: https://arxiv.org/abs/2511.18783
作者: Renchu Guan,Xuyang Li,Yachao Zhang,Wei Pang,Fausto Giunchiglia,Ximing Li,Yonghao Liu,Xiaoyue Feng
类目: Machine Learning (cs.LG); Social and Information Networks (cs.SI)
*备注:

点击查看摘要

[LG-31] SAOT: An Enhanced Locality-Aware Spectral Transformer for Solving PDEs AAAI2026

链接: https://arxiv.org/abs/2511.18777
作者: Chenhong Zhou,Jie Chen,Zaifeng Yang
类目: Machine Learning (cs.LG)
*备注: Accepted to AAAI 2026 (Main Technical Track)

点击查看摘要

[LG-32] OceanForecastBench: A Benchmark Dataset for Data-Driven Global Ocean Forecasting

链接: https://arxiv.org/abs/2511.18732
作者: Haoming Jia,Yi Han,Xiang Wang,Huizan Wang,Wei Wu,Jianming Zheng,Peikun Xiao
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-33] Large-Scale In-Game Outcome Forecasting for Match Team and Players in Football using an Axial Transformer Neural Network

链接: https://arxiv.org/abs/2511.18730
作者: Michael Horton,Patrick Lucey
类目: Machine Learning (cs.LG)
*备注: 25 pages, 7 figures, 1 table

点击查看摘要

[LG-34] Reinforcement Learning for Self-Healing Material Systems

链接: https://arxiv.org/abs/2511.18728
作者: Maitreyi Chatterjee,Devansh Agarwal,Biplab Chatterjee
类目: Machine Learning (cs.LG)
*备注: Accepted to INCOM 2026. This is the camera-ready version

点击查看摘要

[LG-35] LogSyn: A Few-Shot LLM Framework for Structured Insight Extraction from Unstructured General Aviation Maintenance Logs

链接: https://arxiv.org/abs/2511.18727
作者: Devansh Agarwal,Maitreyi Chatterjee,Biplab Chatterjee
类目: Machine Learning (cs.LG)
*备注: Accepted in Proceedings of the 3rd INCOM 2026

点击查看摘要

[LG-36] owards Realistic Guarantees: A Probabilistic Certificate for SmoothLLM

链接: https://arxiv.org/abs/2511.18721
作者: Adarsh Kumarappan,Ayushi Mehrotra
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-37] When and What to Recommend: Joint Modeling of Timing and Content for Active Sequential Recommendation

链接: https://arxiv.org/abs/2511.18717
作者: Jin Chai,Xiaoxiao Ma,Jian Yang,Jia Wu
类目: Information Retrieval (cs.IR); Machine Learning (cs.LG)
*备注: 10 pages, 5 figures. Submitted to arXiv

点击查看摘要

[LG-38] QuantKAN: A Unified Quantization Framework for Kolmogorov Arnold Networks

链接: https://arxiv.org/abs/2511.18689
作者: Kazi Ahmed Asif Fuad,Lizhong Chen
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-39] Multi-Agent Cross-Entropy Method with Monotonic Nonlinear Critic Decomposition

链接: https://arxiv.org/abs/2511.18671
作者: Yan Wang,Ke Deng,Yongli Ren
类目: Machine Learning (cs.LG); Multiagent Systems (cs.MA)
*备注:

点击查看摘要

[LG-40] Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic

链接: https://arxiv.org/abs/2511.18660
作者: Mostafa Mozafari,Farooq Ahmad Wani,Maria Sofia Bucarelli,Fabrizio Silvestri
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-41] he Locally Deployable Virtual Doctor: LLM Based Human Interface for Automated Anamnesis and Database Conversion

链接: https://arxiv.org/abs/2511.18632
作者: Jan Benedikt Ruhland,Doguhan Bahcivan,Jan-Peter Sowa,Ali Canbay,Dominik Heider
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-42] FOS: A Large-Scale Temporal Graph Benchmark for Scientific Interdisciplinary Link Prediction

链接: https://arxiv.org/abs/2511.18631
作者: Kiyan Rezaee,Morteza Ziabakhsh,Niloofar Nikfarjam,Mohammad M. Ghassemi,Yazdan Rezaee Jouryabi,Sadegh Eskandari,Reza Lashgari
类目: Machine Learning (cs.LG)
*备注: 21 pages, 10 figures

点击查看摘要

[LG-43] Bayesian-based Online Label Shift Estimation with Dynamic Dirichlet Priors

链接: https://arxiv.org/abs/2511.18615
作者: Jiawei Hu,Javier A. Barria
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 13 pages, submitted to IEEE journal for possible publication

点击查看摘要

[LG-44] CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning WACV-26

链接: https://arxiv.org/abs/2511.18611
作者: Mengdi Wang,Efe Bozkir,Enkelejda Kasneci
类目: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注: The IEEE/CVF Winter Conference on Applications of Computer Vision 2026 (WACV-26)

点击查看摘要

[LG-45] How to Train Your Latent Control Barrier Function: Smooth Safety Filtering Under Hard-to-Model Constraints

链接: https://arxiv.org/abs/2511.18606
作者: Kensuke Nakamura,Arun L. Bishop,Steven Man,Aaron M. Johnson,Zachary Manchester,Andrea Bajcsy
类目: Robotics (cs.RO); Machine Learning (cs.LG)
*备注: 3 figures, 10 tables, 22 pages

点击查看摘要

[LG-46] Generative Myopia: Why Diffusion Models Fail at Structure

链接: https://arxiv.org/abs/2511.18593
作者: Milad Siami
类目: Machine Learning (cs.LG); Systems and Control (eess.SY); Spectral Theory (math.SP)
*备注:

点击查看摘要

[LG-47] SAMBA: Toward a Long-Context EEG Foundation Model via Spatial Embedding and Differential Mamba

链接: https://arxiv.org/abs/2511.18571
作者: Jiazhen Hong,Geoffrey Mackellar,Soheila Ghane
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-48] In Search of Goodness: Large Scale Benchmarking of Goodness Functions for the Forward-Forward Algorithm

链接: https://arxiv.org/abs/2511.18567
作者: Arya Shah,Vaibhav Tripathi
类目: Machine Learning (cs.LG)
*备注: 24 pages, 5 tables, 17 figures

点击查看摘要

[LG-49] Online Smoothed Demand Management

链接: https://arxiv.org/abs/2511.18554
作者: Adam Lechowicz,Nicolas Christianson,Mohammad Hajiesmaili,Adam Wierman,Prashant Shenoy
类目: Data Structures and Algorithms (cs.DS); Machine Learning (cs.LG); Systems and Control (eess.SY)
*备注: 69 pages, 12 figures

点击查看摘要

[LG-50] Hyperspectral Variational Autoencoders for Joint Data Compression and Component Extraction

链接: https://arxiv.org/abs/2511.18521
作者: Core Francisco Park,Manuel Perez-Carrasco,Caroline Nowlan,Cecilia Garraffo
类目: Machine Learning (cs.LG); Earth and Planetary Astrophysics (astro-ph.EP); Instrumentation and Methods for Astrophysics (astro-ph.IM)
*备注:

点击查看摘要

[LG-51] CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection

链接: https://arxiv.org/abs/2511.18519
作者: Xinlin Zhuang,Yichen Li,Xiwei Liu,Haolin Yang,Yifan Lu,Ziyun Zou,Yulong Li,Huifa Li,Dongliang Chen,Qinglei Wang,Weiyang Liu,Ying Qian,Jiangming Shi,Imran Razzak
类目: Machine Learning (cs.LG)
*备注: preprint, under-review

点击查看摘要

[LG-52] RRaPINNs: Residual Risk-Aware Physics Informed Neural Networks

链接: https://arxiv.org/abs/2511.18515
作者: Ange-Clément Akazan,Issa Karambal,Jean Medard Ngnotchouye,Abebe Geletu Selassie. W
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-53] Real-Time Personalized Content Adaptation through Matrix Factorization and Context-Aware Federated Learning

链接: https://arxiv.org/abs/2511.18489
作者: Sai Puppala,Ismail Hossain,Md Jahangir Alam,Sajedul Talukder
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-54] Adaptive Mesh-Quantization for Neural PDE Solvers

链接: https://arxiv.org/abs/2511.18474
作者: Winfried van den Dool,Maksim Zhdanov,Yuki M. Asano,Max Welling
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-55] DHAuDS: A Dynamic and Heterogeneous Audio Benchmark for Test-Time Adaptation

链接: https://arxiv.org/abs/2511.18421
作者: Weichuang Shao,Iman Yi Liao,Tomas Henrique Bode Maul,Tissa Chandesa
类目: ound (cs.SD); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-56] Future Is Unevenly Distributed: Forecasting Ability of LLM s Depends on What Were Asking

链接: https://arxiv.org/abs/2511.18394
作者: Chinmay Karkar,Paras Chopra
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-57] DynamiX: Dynamic Resource eXploration for Personalized Ad-Recommendations

链接: https://arxiv.org/abs/2511.18331
作者: Sohini Roychowdhury,Adam Holeman,Mohammad Amin,Feng Wei,Bhaskar Mehta,Srihari Reddy
类目: Machine Learning (cs.LG); Software Engineering (cs.SE)
*备注: 9 pages, 3 Tables, 5 images. this https URL

点击查看摘要

[LG-58] Crash-Consistent Checkpointing for AI Training on macOS/APFS

链接: https://arxiv.org/abs/2511.18323
作者: Juha Jeon
类目: Operating Systems (cs.OS); Machine Learning (cs.LG)
*备注: 18 pages, 6 figures. Independent mini-research report; not submitted to a conference or journal

点击查看摘要

[LG-59] DiM-TS: Bridge the Gap between Selective State Space Models and Time Series for Generative Modeling

链接: https://arxiv.org/abs/2511.18312
作者: Zihao Yao,Jiankai Zuo,Yaying Zhang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-60] Hierarchical Deep Research with Local-Web RAG : Toward Automated System-Level Materials Discovery NEURIPS2025

链接: https://arxiv.org/abs/2511.18303
作者: Rui Ding,Rodrigo Pires Ferreira,Yuxin Chen,Junhong Chen
类目: Machine Learning (cs.LG)
*备注: A preliminary version appeared in The AI for Accelerated Materials Discovery (AI4Mat) Workshop at NeurIPS 2025

点击查看摘要

[LG-61] GROOT: Graph Edge Re-growth and Partitioning for the Verification of Large Designs in Logic Synthesis

链接: https://arxiv.org/abs/2511.18297
作者: Kiran Thorat,Hongwu Peng,Yuebo Luo,Xi Xie,Shaoyi Huang,Amit Hasan,Jiahui Zhao,Yingjie Li,Zhijie Shi,Cunxi Yu,Caiwen Ding
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-62] ADF-LoRA: Alternating Low-Rank Aggregation for Decentralized Federated Fine-Tuning

链接: https://arxiv.org/abs/2511.18291
作者: Xiaoyu Wang,Xiaotian Li,Zhixiang Zhou,Chen Li,Yong Liu
类目: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注: 10 Pages

点击查看摘要

[LG-63] A Fair OR-ML Framework for Resource Substitution in Large-Scale Networks

链接: https://arxiv.org/abs/2511.18269
作者: Ved Mohan,El Mehdi Er Raqabi,Pascal Van Hentenryck
类目: Machine Learning (cs.LG); Optimization and Control (math.OC)
*备注:

点击查看摘要

[LG-64] Reduced-Basis Deep Operator Learning for Parametric PDEs with Independently Varying Boundary and Source Data

链接: https://arxiv.org/abs/2511.18260
作者: Yueqi Wang,Guang Lin
类目: Machine Learning (cs.LG); Numerical Analysis (math.NA)
*备注:

点击查看摘要

[LG-65] ail Distribution of Regret in Optimistic Reinforcement Learning

链接: https://arxiv.org/abs/2511.18247
作者: Sajad Khodadadian,Mehrdad Moharrami
类目: Machine Learning (cs.LG); Optimization and Control (math.OC)
*备注: 18 pages, 0 figures

点击查看摘要

[LG-66] Adaptive Conformal Prediction for Quantum Machine Learning

链接: https://arxiv.org/abs/2511.18225
作者: Douglas Spencer,Samual Nicholls,Michele Caprio
类目: Machine Learning (cs.LG); Machine Learning (stat.ML); Other Statistics (stat.OT)
*备注: 26 pages, 5 figures

点击查看摘要

[LG-67] Deep Gaussian Process Proximal Policy Optimization

链接: https://arxiv.org/abs/2511.18214
作者: Matthijs van der Lende,Juan Cardenas-Cartagena
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-68] yping Reinvented: Towards Hands-Free Input via sEMG

链接: https://arxiv.org/abs/2511.18213
作者: Kunwoo Lee,Dhivya Sreedhar,Pushkar Saraf,Chaeeun Lee,Kateryna Shapovalenko
类目: Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-69] ProHD: Projection-Based Hausdorff Distance Approximation

链接: https://arxiv.org/abs/2511.18207
作者: Jiuzhou Fu,Luanzheng Guo,Nathan R. Tallent,Dongfang Zhao
类目: Information Retrieval (cs.IR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-70] Accelerating Time Series Foundation Models with Speculative Decoding

链接: https://arxiv.org/abs/2511.18191
作者: Pranav Subbaraman,Fang Sun,Yue Yao,Huacong Tang,Xiao Luo,Yizhou Sun
类目: Machine Learning (cs.LG)
*备注: 14 pages, 7 figures

点击查看摘要

[LG-71] Bayesian Calibration of Engine-out NOx Models for Engine-to-Engine Transferability

链接: https://arxiv.org/abs/2511.18178
作者: Shrenik Zinage,Peter Meckl,Ilias Bilionis
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-72] Bringing Stability to Diffusion: Decomposing and Reducing Variance of Training Masked Diffusion Models

链接: https://arxiv.org/abs/2511.18159
作者: Mengni Jia,Mengyu Zhou,Yihao Liu,Xiaoxi Jiang,Guanjun Jiang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-73] LocaGen: Low-Overhead Indoor Localization Through Spatial Augmentation

链接: https://arxiv.org/abs/2511.18158
作者: Abdelrahman Abdelmotlb,Abdallah Taman,Sherif Mostafa,Moustafa Youssef
类目: Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI)
*备注: Accepted at GeoIndustry @ ACM SIGSPATIAL 2025 (The 4th International Workshop on Spatial Big Data and AI for Industrial Applications)

点击查看摘要

[LG-74] scipy.spatial.transform: Differentiable Framework-Agnostic 3D Transformations in Python

链接: https://arxiv.org/abs/2511.18157
作者: Martin Schuck,Alexander von Rohr,Angela P. Schoellig
类目: Machine Learning (cs.LG); Robotics (cs.RO)
*备注: Accepted as oral at the 1st Workshop on Differentiable Systems and Scientific Machine Learning @ EurIPS 2025

点击查看摘要

[LG-75] A Coordinated Dual-Arm Framework for Delicate Snap-Fit Assemblies

链接: https://arxiv.org/abs/2511.18153
作者: Shreyas Kumar,Barat S,Debojit Das,Yug Desai,Siddhi Jain,Rajesh Kumar,Harish J. Palanthandalam-Madapusi
类目: Robotics (cs.RO); Machine Learning (cs.LG)
*备注: 10 pages, 9 figures

点击查看摘要

[LG-76] Vulnerability-Aware Robust Multimodal Adversarial Training AAAI26

链接: https://arxiv.org/abs/2511.18138
作者: Junrui Zhang,Xinyu Zhao,Jie Peng,Chenjie Wang,Jianmin Ji,Tianlong Chen
类目: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
*备注: Accepted by AAAI26

点击查看摘要

[LG-77] Active Learning with Selective Time-Step Acquisition for PDEs

链接: https://arxiv.org/abs/2511.18107
作者: Yegon Kim,Hyunsu Kim,Gyeonghoon Ko,Juho Lee
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-78] owards Harnessing the Power of LLM s for ABAC Policy Mining

链接: https://arxiv.org/abs/2511.18098
作者: More Aayush Babasaheb(Indian Institute of Technology Kharagpur, India),Shamik Sural(Indian Institute of Technology Kharagpur, India)
类目: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-79] Hierarchical Linkage Clustering Beyond Binary Trees and Ultrametrics

链接: https://arxiv.org/abs/2511.18056
作者: Maximilien Dreveton,Matthias Grossglauser,Daichi Kuroda,Patrick Thiran
类目: Machine Learning (cs.LG); Methodology (stat.ME); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-80] Sparse Kalman Identification for Partially Observable Systems via Adaptive Bayesian Learning

链接: https://arxiv.org/abs/2511.18051
作者: Jilan Mei,Tengjie Zheng,Lin Cheng,Shengping Gong,Xu Huang
类目: ystems and Control (eess.SY); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-81] Curvature-Aware Safety Restoration In LLM s Fine-Tuning

链接: https://arxiv.org/abs/2511.18039
作者: Thong Bach,Thanh Nguyen-Tang,Dung Nguyen,Thao Minh Le,Truyen Tran
类目: Machine Learning (cs.LG)
*备注: 19 pages, 10 figures

点击查看摘要

[LG-82] Correlated-Sequence Differential Privacy

链接: https://arxiv.org/abs/2511.18025
作者: Yifan Luo,Meng Zhang,Jin Xu,Junting Chen,Jianwei Huang
类目: Cryptography and Security (cs.CR); Information Theory (cs.IT); Machine Learning (cs.LG)
*备注: 11 pages, 5 figures. Published in 2025 34th International Conference on Computer Communications and Networks (ICCCN), IEEE, August 2025

点击查看摘要

[LG-83] Understanding Private Learning From Feature Perspective

链接: https://arxiv.org/abs/2511.18006
作者: Meng Ding,Mingxi Lei,Shaopeng Fu,Shaowei Wang,Di Wang,Jinhui Xu
类目: Machine Learning (cs.LG)
*备注: 39pages

点击查看摘要

[LG-84] Learning Rate Scheduling with Matrix Factorization for Private Training

链接: https://arxiv.org/abs/2511.17994
作者: Nikita P. Kalinin,Joel Daniel Andersson
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-85] An Adaptive Resonance Theory-based Topological Clustering Algorithm with a Self-Adjusting Vigilance Parameter

链接: https://arxiv.org/abs/2511.17983
作者: Naoki Masuyama,Yuichiro Toda,Yusuke Nojima,Hisao Ishibuchi
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: This manuscript is currently under review

点击查看摘要

[LG-86] Federated Anomaly Detection and Mitigation for EV Charging Forecasting Under Cyberattacks

链接: https://arxiv.org/abs/2511.17978
作者: Oluleke Babayomi,Dong-Seong Kim
类目: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
*备注: 6 pages

点击查看摘要

[LG-87] Synthesizing Precise Protocol Specs from Natural Language for Effective Test Generation

链接: https://arxiv.org/abs/2511.17977
作者: Kuangxiangzi Liu,Dhiman Chakraborty,Alexander Liggesmeyer,Andreas Zeller
类目: oftware Engineering (cs.SE); Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI)
*备注:

点击查看摘要

[LG-88] Controllability Analysis of State Space-based Language Model

链接: https://arxiv.org/abs/2511.17970
作者: Mohamed Mabrok,Yalda Zafari
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-89] Uncertainty-Aware Federated Learning for Cyber-Resilient Microgrid Energy Management

链接: https://arxiv.org/abs/2511.17968
作者: Oluleke Babayomi,Dong-Seong Kim
类目: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
*备注: 6 pages

点击查看摘要

[LG-90] On Transportability for Structural Causal Bandits

链接: https://arxiv.org/abs/2511.17953
作者: Min Woo Park,Sanghack Lee
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-91] Mitigating Catastrophic Forgetting in Streaming Generative and Predictive Learning via Stateful Replay

链接: https://arxiv.org/abs/2511.17936
作者: Wenzhang Du
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 11 pages, 4 figures

点击查看摘要

[LG-92] A Reinforcement Learning Framework for Resource Allocation in Uplink Carrier Aggregation in the Presence of Self Interference

链接: https://arxiv.org/abs/2511.17931
作者: Jaswanth Bodempudi,Batta Siva Sairam,Madepalli Haritha,Sandesh Rao Mattu,Ananthanarayanan Chockalingam
类目: Information Theory (cs.IT); Machine Learning (cs.LG); Signal Processing (eess.SP)
*备注: Accepted in IEEE Trans. on Machine Learning in Communications and Networking

点击查看摘要

[LG-93] oken-Controlled Re-ranking for Sequential Recommendation via LLM s

链接: https://arxiv.org/abs/2511.17913
作者: Wenxi Dai,Wujiang Xu,Pinhuan Wang,Dimitris N. Metaxas
类目: Information Retrieval (cs.IR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-94] Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction

链接: https://arxiv.org/abs/2511.17879
作者: Yusong Wu,Stephen Brade,Teng Ma,Tia-Jane Fowler,Enning Yang,Berker Banar,Aaron Courville,Natasha Jaques,Cheng-Zhi Anna Huang
类目: Machine Learning (cs.LG); Sound (cs.SD)
*备注:

点击查看摘要

[LG-95] he Horcrux: Mechanistically Interpretable Task Decomposition for Detecting and Mitigating Reward Hacking in Embodied AI Systems NEURIPS

链接: https://arxiv.org/abs/2511.17869
作者: Subramanyam Sahoo,Jared Junkin
类目: Machine Learning (cs.LG)
*备注: Accepted to the NeurIPS (Mexico City) 2025 Workshop on Embodied and Safe-Assured Robotic Systems (E-SARS). Thanks to Aman Chadha

点击查看摘要

[LG-96] Generative Model Predictive Control in Manufacturing Processes: A Review

链接: https://arxiv.org/abs/2511.17865
作者: Suk Ki Lee,Ronnie F. P. Stone,Max Gao,Wenlong Zhang,Zhenghui Sha,Hyunwoong Ko
类目: ystems and Control (eess.SY); Machine Learning (cs.LG)
*备注: 24 pages, 5 figures, Review article

点击查看摘要

[LG-97] Equivalence of Context and Parameter Updates in Modern Transformer Blocks

链接: https://arxiv.org/abs/2511.17864
作者: Adrian Goldwaser,Michael Munn,Javier Gonzalvo,Benoit Dherin
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-98] Cost-Sensitive Conformal Training with Provably Controllable Learning Bounds AAAI

链接: https://arxiv.org/abs/2511.17861
作者: Xuesong Jia,Yuanjie Shi,Ziquan Liu,Yi Xu,Yan Yan
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: Accepted for Publication at Association for the Advancement of Artificial Intelligence (AAAI), 2026

点击查看摘要

[LG-99] ransformers with RL or SFT Provably Learn Sparse Boolean Functions But Differently

链接: https://arxiv.org/abs/2511.17852
作者: Bochen Lyu,Yiyang Jia,Xiaohao Cai,Zhanxing Zhu
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 43 pages, 5 figures

点击查看摘要

[LG-100] Scaling Kinetic Monte-Carlo Simulations of Grain Growth with Combined Convolutional and Graph Neural Networks

链接: https://arxiv.org/abs/2511.17848
作者: Zhihui Tian,Ethan Suwandi,Tomas Oppelstrup,Vasily V. Bulatov,Joel B. Harley,Fei Zhou
类目: Machine Learning (cs.LG); Materials Science (cond-mat.mtrl-sci)
*备注:

点击查看摘要

[LG-101] Internalizing Tools as Morphisms in Graded Transformers

链接: https://arxiv.org/abs/2511.17840
作者: Tony Shaska
类目: Machine Learning (cs.LG); Category Theory (math.CT)
*备注:

点击查看摘要

[LG-102] A novel k-means clustering approach using two distance measures for Gaussian data

链接: https://arxiv.org/abs/2511.17823
作者: Naitik Gada(1) ((1) Rochester Institute of Technology)
类目: Machine Learning (cs.LG); Computational Engineering, Finance, and Science (cs.CE); Methodology (stat.ME); Machine Learning (stat.ML)
*备注: Keywords: machine learning, clustering algorithms, k-means

点击查看摘要

[LG-103] High-Accuracy List-Decodable Mean Estimation

链接: https://arxiv.org/abs/2511.17822
作者: Ziyun Chen,Spencer Compton,Daniel Kane,Jerry Li
类目: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS); Machine Learning (stat.ML)
*备注: Abstract shortened to meet arXiv requirement

点击查看摘要

[LG-104] Adaptive Layer-Wise Transformations for Post-Training Quantization of Large Language Models

链接: https://arxiv.org/abs/2511.17809
作者: Cuong Pham,Hoang Anh Dung,Cuong C. Nguyen,Trung Le,Gustavo Carneiro,Jianfei Cai,Thanh-Toan Do
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-105] Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models

链接: https://arxiv.org/abs/2511.17801
作者: Cuong Pham,Hoang Anh Dung,Cuong C. Nguyen,Trung Le,Gustavo Carneiro,Thanh-Toan Do
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-106] Semi-Supervised Federated Multi-Label Feature Selection with Fuzzy Information Measures

链接: https://arxiv.org/abs/2511.17796
作者: Afsaneh Mahanipour,Hana Khamfroush
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: This paper has been accepted for presentation at GLOBECOM 2025

点击查看摘要

[LG-107] Physical Reinforcement Learning

链接: https://arxiv.org/abs/2511.17789
作者: Sam Dillavou,Shruti Mishra
类目: Machine Learning (cs.LG); Disordered Systems and Neural Networks (cond-mat.dis-nn)
*备注: 9 pages 4 figures

点击查看摘要

[LG-108] Data-Driven Predictive Modeling of Microfluidic Cancer Cell Separation Using a Deterministic Lateral Displacement Device ICDM

链接: https://arxiv.org/abs/2511.17787
作者: Elizabeth Chen,Andrew Lee,Tanbir Sarowar,Xiaolin Chen
类目: Machine Learning (cs.LG); Medical Physics (physics.med-ph); Quantitative Methods (q-bio.QM)
*备注: Accepted to IEEE International Conference on Data Mining (ICDM) 2025 REU Symposium

点击查看摘要

[LG-109] Improved Sample Complexity for Full Coverag e in Compact and Continuous Spaces

链接: https://arxiv.org/abs/2511.17784
作者: Lyu Yuhuan
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-110] Smoothed Agnostic Learning of Halfspaces over the Hypercube

链接: https://arxiv.org/abs/2511.17782
作者: Yiwen Kou,Raghu Meka
类目: Machine Learning (cs.LG); Computational Complexity (cs.CC); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-111] PrismSSL: One Interface Many Modalities; A Single-Interface Library for Multimodal Self-Supervised Learning

链接: https://arxiv.org/abs/2511.17776
作者: Melika Shirian,Kianoosh Vadaei,Kian Majlessi,Audrina Ebrahimi,Arshia Hemmat,Peyman Adibi,Hossein Karshenas
类目: Machine Learning (cs.LG); Multimedia (cs.MM)
*备注:

点击查看摘要

[LG-112] LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation

链接: https://arxiv.org/abs/2511.17765
作者: Darren Chiu,Zhehui Huang,Ruohai Ge,Gaurav S. Sukhatme
类目: Robotics (cs.RO); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
*备注: 20 pages, 15 figures

点击查看摘要

[LG-113] Periodicity-Enforced Neural Network for Designing Deterministic Lateral Displacement Devices ICDM

链接: https://arxiv.org/abs/2511.17754
作者: Andrew Lee,Mahir Mobarrat,Xiaolin Chen
类目: Machine Learning (cs.LG); Fluid Dynamics (physics.flu-dyn)
*备注: Accepted to IEEE International Conference on Data Mining (ICDM) 2025 REU Symposium

点击查看摘要

[LG-114] Diffusion Models are Molecular Dynamics Simulators

链接: https://arxiv.org/abs/2511.17741
作者: Justin Diamond,Markus Lill
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-115] Boosting Brain-inspired Path Integration Efficiency via Learning-based Replication of Continuous Attractor Neurodynamics

链接: https://arxiv.org/abs/2511.17687
作者: Zhangyu Ge,Xu He,Lingfei Mo,Xiaolin Meng,Wenxuan Yin,Youdong Zhang,Lansong Jiang,Fengyuan Liu
类目: Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
*备注:

点击查看摘要

[LG-116] A Hybrid Classical-Quantum Fine Tuned BERT for Text Classification AAAI AAAI2025

链接: https://arxiv.org/abs/2511.17677
作者: Abu Kaisar Mohammad Masum,Naveed Mahmud,M. Hassan Najafi,Sercan Aygun
类目: Machine Learning (cs.LG); Quantum Physics (quant-ph)
*备注: This paper has been accepted by First AAAI Symposium on Quantum Information Machine Learning (QIML): Bridging Quantum Computing and Artificial Intelligence at AAAI 2025 Fall Symposium

点击查看摘要

[LG-117] Lane-Frame Quantum Multimodal Driving Forecasts for the Trajectory of Autonomous Vehicles

链接: https://arxiv.org/abs/2511.17675
作者: Navneet Singh,Shiva Raj Pokhrel
类目: Machine Learning (cs.LG); Quantum Physics (quant-ph)
*备注:

点击查看摘要

[LG-118] GANGR: GAN-Assisted Scalable and Efficient Global Routing Parallelization DATE2026

链接: https://arxiv.org/abs/2511.17665
作者: Hadi Khodaei Jooshin,Inna Partin-Vaisband
类目: Machine Learning (cs.LG)
*备注: Accepted in DATE 2026

点击查看摘要

[LG-119] Enhancing Breast Cancer Prediction with LLM -Inferred Confounders

链接: https://arxiv.org/abs/2511.17662
作者: Debmita Roy
类目: Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
*备注: 2 pages, 1 figure, 1 table

点击查看摘要

[LG-120] Multi-Agent Coordination in Autonomous Vehicle Routing: A Simulation-Based Study of Communication Memory and Routing Loops

链接: https://arxiv.org/abs/2511.17656
作者: KM Khalid Saifullah,Daniel Palmer
类目: Multiagent Systems (cs.MA); Machine Learning (cs.LG); Robotics (cs.RO)
*备注:

点击查看摘要

[LG-121] BlockCert: Certified Blockwise Extraction of Transformer Mechanisms

链接: https://arxiv.org/abs/2511.17645
作者: Sandro Andric
类目: Machine Learning (cs.LG)
*备注: 16 pages, 1 figure

点击查看摘要

[LG-122] F: A Trapezoidal Temporal Fusion Framework for LTV Forecasting in Douyin AAAI

链接: https://arxiv.org/abs/2511.17639
作者: Yibing Wan,Zhengxiong Guan,Chaoli Zhang,Xiaoyang Li,Lai Xu,Beibei Jia,Zhenzhe Zheng,Fan Wu
类目: Machine Learning (cs.LG)
*备注: Accepted by AAAI IAAI Track

点击查看摘要

[LG-123] Smart Manufacturing: MLOps-Enabled Event-Driven Architecture for Enhanced Control in Steel Production

链接: https://arxiv.org/abs/2511.17632
作者: Bestoun S. Ahmed,Tommaso Azzalin,Andreas Kassler,Andreas Thore,Hans Lindback
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-124] Enhanced Federated Deep Multi-View Clustering under Uncertainty Scenario

链接: https://arxiv.org/abs/2511.17631
作者: Bingjun Wei,Xuemei Cao,Jiafen Liu,Haoyang Liang,Xin Yang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-125] Boundary-Aware Adversarial Filtering for Reliable Diagnosis under Extreme Class Imbalance

链接: https://arxiv.org/abs/2511.17629
作者: Yanxuan Yu,Michael S. Hughes,Julien Lee,Jiacheng Zhou,Andrew F. Laine
类目: Machine Learning (cs.LG)
*备注: 5 pages, 3 figures. Submitted to IEEE ISBI (under review)

点击查看摘要

[LG-126] Rectifying Mean-Shift in Cascaded Precipitation Nowcasting

链接: https://arxiv.org/abs/2511.17628
作者: Fanbo Ju,Haiyuan Shi,Qingjian Ni
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-127] Efficient Large-Scale Learning of Minimax Risk Classifiers ICDM

链接: https://arxiv.org/abs/2511.17626
作者: Kartheek Bondugula,Santiago Mazuelas,Aritz Pérez
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: In IEEE ICDM (2025)

点击查看摘要

[LG-128] QML-HCS: A Hypercausal Quantum Machine Learning Framework for Non-Stationary Environments

链接: https://arxiv.org/abs/2511.17624
作者: Hector E Mozo
类目: Machine Learning (cs.LG)
*备注: 11 pages, 10 figures, and 8 tables. The implementation and full source code of the Hypercausal Quantum Machine Learning System (QML-HCS) are openly available on GitHub at: this https URL

点击查看摘要

[LG-129] AI-driven Generation of MALDI-TOF MS for Microbial Characterization

链接: https://arxiv.org/abs/2511.17611
作者: Lucía Schmidt-Santiago,David Rodríguez-Temporal,Carlos Sevilla-Salcedo,Vanessa Gómez-Verdejo
类目: Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
*备注:

点击查看摘要

[LG-130] Finding Pre-Injury Patterns in Triathletes from Lifestyle Recovery and Load Dynamics Features

链接: https://arxiv.org/abs/2511.17610
作者: Leonardo Rossi,Bruno Rodrigues
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-131] Copula Based Fusion of Clinical and Genomic Machine Learning Risk Scores for Breast Cancer Risk Stratification

链接: https://arxiv.org/abs/2511.17605
作者: Agnideep Aich,Sameera Hewage,Md Monzur Murshed
类目: Machine Learning (cs.LG); Methodology (stat.ME); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-132] Generalizable and Efficient Automated Scoring with a Knowledge-Distilled Multi-Task Mixture-of-Experts

链接: https://arxiv.org/abs/2511.17601
作者: Luyang Fang,Tao Wang,Ping Ma,Xiaoming Zhai
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-133] Non-stationary and Varying-discounting Markov Decision Processes for Reinforcement Learning

链接: https://arxiv.org/abs/2511.17598
作者: Zhizuo Chen,Theodore T. Allen
类目: Machine Learning (cs.LG); Optimization and Control (math.OC); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-134] AutoSAGE: Input-Aware CUDA Scheduling for Sparse GNN Aggregation (SpMM/SDDMM) and CSR Attention

链接: https://arxiv.org/abs/2511.17594
作者: Aleksandar Stankovic
类目: Machine Learning (cs.LG); Performance (cs.PF)
*备注: 10 pages, several figures. Code and artifacts: this https URL

点击查看摘要

[LG-135] Comparative Analysis of Large Language Model Inference Serving Systems: A Performance Study of vLLM and HuggingFace TGI

链接: https://arxiv.org/abs/2511.17593
作者: Saicharan Kolluru
类目: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC); Performance (cs.PF)
*备注: 10 pages, benchmarking study of LLM inference systems

点击查看摘要

[LG-136] Root Cause Analysis for Microservice Systems via Cascaded Conditional Learning with Hypergraphs

链接: https://arxiv.org/abs/2511.17566
作者: Shuaiyu Xie,Hanbin He,Jian Wang,Bing Li
类目: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC); Software Engineering (cs.SE)
*备注:

点击查看摘要

[LG-137] Q-Learning-Based Time-Critical Data Aggregation Scheduling in IoT

链接: https://arxiv.org/abs/2511.17531
作者: Van-Vi Vo,Tien-Dung Nguyen,Duc-Tai Le,Hyunseung Choo
类目: Networking and Internet Architecture (cs.NI); Machine Learning (cs.LG)
*备注: 7 pages, 6 figures

点击查看摘要

[LG-138] DyPBP: Dynamic Peer Beneficialness Prediction for Cryptocurrency P2P Networking

链接: https://arxiv.org/abs/2511.17523
作者: Nazmus Sakib,Simeon Wuthier,Amanul Islam,Xiaobo Zhou,Jinoh Kim,Ikkyun Kim,Sang-Yoon Chang
类目: Networking and Internet Architecture (cs.NI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-139] Causal Intervention Sequence Analysis for Fault Tracking in Radio Access Networks

链接: https://arxiv.org/abs/2511.17505
作者: Chenhua Shi,Joji Philip,Subhadip Bandyopadhyay,Jayanta Choudhury
类目: Networking and Internet Architecture (cs.NI); Machine Learning (cs.LG)
*备注: 6 pages, 7 figures, 1 table, accepted by IEEE FMLDS 2025

点击查看摘要

[LG-140] Nonparametric Instrumental Variable Regression with Observed Covariates

链接: https://arxiv.org/abs/2511.19404
作者: Zikai Shen,Zonghao Chen,Dimitri Meunier,Ingo Steinwart,Arthur Gretton,Zhu Li
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Statistics Theory (math.ST)
*备注:

点击查看摘要

[LG-141] Artificial Intelligence Driven Workflow for Accelerating Design of Novel Photosensitizers

链接: https://arxiv.org/abs/2511.19347
作者: Hongyi Wang,Xiuli Zheng,Weimin Liu,Zitian Tang,Sheng Gong
类目: Materials Science (cond-mat.mtrl-sci); Machine Learning (cs.LG); Chemical Physics (physics.chem-ph)
*备注:

点击查看摘要

[LG-142] High-throughput validation of phase formability and simulation accuracy of Cantor alloys

链接: https://arxiv.org/abs/2511.19335
作者: Changjun Cheng,Daniel Persaud,Kangming Li,Michael J. Moorehead,Natalie Page,Christian Lavoie,Beatriz Diaz Moreno,Adrien Couet,Samuel E Lofland,Jason Hattrick-Simpers
类目: Materials Science (cond-mat.mtrl-sci); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-143] orchQuantumDistributed NEURIPS2025

链接: https://arxiv.org/abs/2511.19291
作者: Oliver Knitter,Jonathan Mei,Masako Yamada,Martin Roetteler
类目: Quantum Physics (quant-ph); Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG)
*备注: 12 pages, 4 figures, to appear in the AI for Science Workshop at NeurIPS 2025

点击查看摘要

[LG-144] Performance Guarantees for Quantum Neural Estimation of Entropies

链接: https://arxiv.org/abs/2511.19289
作者: Sreejith Sreekumar,Ziv Goldfeld,Mark M. Wilde
类目: Quantum Physics (quant-ph); Information Theory (cs.IT); Machine Learning (cs.LG)
*备注: 42+4 pages

点击查看摘要

[LG-145] he Unified Non-Convex Framework for Robust Causal Inference: Overcoming the Gaussian Barrier and Optimization Frag ility

链接: https://arxiv.org/abs/2511.19284
作者: Eichi Uehara
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Methodology (stat.ME)
*备注: 10 pages, 1 table

点击查看摘要

[LG-146] A Robust State Filter Against Unmodeled Process And Measurement Noise

链接: https://arxiv.org/abs/2511.19157
作者: Weitao Liu
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-147] Feature Ranking in Credit-Risk with Qudit-Based Networks

链接: https://arxiv.org/abs/2511.19150
作者: Georgios Maragkopoulos,Lazaros Chavatzoglou,Aikaterini Mandilara,Dimitris Syvridis
类目: Quantum Physics (quant-ph); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-148] Structured Matching via Cost-Regularized Unbalanced Optimal Transport

链接: https://arxiv.org/abs/2511.19075
作者: Emanuele Pardini,Katerina Papagiannouli
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Applications (stat.AP)
*备注:

点击查看摘要

[LG-149] Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification

链接: https://arxiv.org/abs/2511.18876
作者: Lilian Say(LPSM),Christophe Denis(SAMM),Rafael Pinot(LPSM)
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-150] Solution of Incompressible Flow Equations with Physics and Equality Constrained Artificial Neural Networks

链接: https://arxiv.org/abs/2511.18820
作者: Qifeng Hu,Inanc Senocak
类目: Fluid Dynamics (physics.flu-dyn); Machine Learning (cs.LG)
*备注: 21 pages, 13 figures

点击查看摘要

[LG-151] Uncertainty of Network Topology with Applications to Out-of-Distribution Detection

链接: https://arxiv.org/abs/2511.18813
作者: Sing-Yuan Yeh,Chun-Hao Yang
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Methodology (stat.ME)
*备注: Submitted for journal publication

点击查看摘要

[LG-152] On Instability of Minimax Optimal Optimism-Based Bandit Algorithms

链接: https://arxiv.org/abs/2511.18750
作者: Samya Praharaj,Koulik Khamaru
类目: Machine Learning (stat.ML); Information Theory (cs.IT); Machine Learning (cs.LG); Statistics Theory (math.ST)
*备注:

点击查看摘要

[LG-153] Equivariant Deep Equilibrium Models for Imaging Inverse Problems

链接: https://arxiv.org/abs/2511.18667
作者: Alexander Mehta,Ruangrawee Kitichotkul,Vivek K Goyal,Julián Tachella
类目: Image and Video Processing (eess.IV); Machine Learning (cs.LG); Signal Processing (eess.SP)
*备注:

点击查看摘要

[LG-154] Fast Escape Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data

链接: https://arxiv.org/abs/2511.18661
作者: Guillaume Braun,Bruno Loureiro,Ha Quang Minh,Masaaki Imaizumi
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-155] Autoencoder for Position-Assisted Beam Prediction in mmWave ISAC Systems

链接: https://arxiv.org/abs/2511.18594
作者: Ahmad A. Aziz El-Banna,Octavia A. Dobre
类目: ignal Processing (eess.SP); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-156] From Simulations to Surveys: Domain Adaptation for Galaxy Observations NEURIPS2025

链接: https://arxiv.org/abs/2511.18590
作者: Kaley Brauer,Aditya Prasad Dash,Meet J. Vyas,Ahmed Salim,Stiven Briand Massala
类目: Astrophysics of Galaxies (astro-ph.GA); Machine Learning (cs.LG)
*备注: 8 pages, 4 figures. Will be presented at NeurIPS 2025 ML4PS

点击查看摘要

[LG-157] Differential privacy with dependent data

链接: https://arxiv.org/abs/2511.18583
作者: Valentin Roth,Marco Avella-Medina
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Statistics Theory (math.ST)
*备注:

点击查看摘要

[LG-158] Ensuring Calibration Robustness in Split Conformal Prediction Under Adversarial Attacks AISTATS2026

链接: https://arxiv.org/abs/2511.18562
作者: Xunlei Qian,Yue Xing
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: Submitted to AISTATS 2026

点击查看摘要

[LG-159] A joint optimization approach to identifying sparse dynamics using least squares kernel collocation

链接: https://arxiv.org/abs/2511.18555
作者: Alexander W. Hsu,Ike W. Griss Salas,Jacob M. Stevens-Haas,J. Nathan Kutz,Aleksandr Aravkin,Bamdad Hosseini
类目: Methodology (stat.ME); Machine Learning (cs.LG); Dynamical Systems (math.DS); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-160] ransforming Conditional Density Estimation Into a Single Nonparametric Regression Task

链接: https://arxiv.org/abs/2511.18530
作者: Alexander G. Reisach,Olivier Collier,Alex Luedtke,Antoine Chambaz
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-161] Reliable Selection of Heterogeneous Treatment Effect Estimators

链接: https://arxiv.org/abs/2511.18464
作者: Jiayi Guo,Zijun Gao
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-162] Brain-MGF: Multimodal Graph Fusion Network for EEG-fMRI Brain Connectivity Analysis Under Psilocybin

链接: https://arxiv.org/abs/2511.18325
作者: Sin-Yee Yap,Fuad Noman,Junn Yong Loo,Devon Stoliker,Moein Khajehnejad,Raphaël C.-W. Phan,David L. Dowe,Adeel Razi,Chee-Ming Ting
类目: Neurons and Cognition (q-bio.NC); Machine Learning (cs.LG)
*备注: 5 pages

点击查看摘要

[LG-163] Improving Forecasts of Suicide Attempts for Patients with Little Data NEURIPS2025

链接: https://arxiv.org/abs/2511.18199
作者: Genesis Hang,Annie Chen,Hope Neveux,Matthew K. Nock,Yaniv Yacoby
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: Accepted at the TS4H Workshop at NeurIPS 2025

点击查看摘要

[LG-164] Sparse Polyak with optimal thresholding operators for high-dimensional M-estimation

链接: https://arxiv.org/abs/2511.18167
作者: Tianqi Qiao,Marie Maros
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Optimization and Control (math.OC)
*备注:

点击查看摘要

[LG-165] Conformal Prediction for Compositional Data

链接: https://arxiv.org/abs/2511.18141
作者: Lucas P. Amaral,Luben M. C. Cabezas,Thiago R. Ramos,Gustavo H. G. A. Pereira
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: 18 pages, 4 figures

点击查看摘要

[LG-166] An operator splitting analysis of Wasserstein–Fisher–Rao gradient flows

链接: https://arxiv.org/abs/2511.18060
作者: Francesca Romana Crucinio,Sahani Pathiraja
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Methodology (stat.ME)
*备注:

点击查看摘要

[LG-167] On a Reinforcement Learning Methodology for Epidemic Control with application to COVID-19

链接: https://arxiv.org/abs/2511.18035
作者: Giacomo Iannucci,Petros Barmpounakis,Alexandros Beskos,Nikolaos Demiris
类目: Methodology (stat.ME); Machine Learning (cs.LG); Computation (stat.CO); Machine Learning (stat.ML)
*备注: Submitted to Statistics and Computing. Approx. 26 pages, 10 figures

点击查看摘要

信息检索

[IR-0] Revisiting Feedback Models for HyDE

链接: https://arxiv.org/abs/2511.19349
作者: Nour Jedidi,Jimmy Lin
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-1] Heterogeneous Multi-treatment Uplift Modeling for Trade-off Optimization in Short-Video Recommendation KDD2026

链接: https://arxiv.org/abs/2511.18997
作者: Chenhao Zhai,Chang Meng,Xueliang Wang,Shuchang Liu,Xiaolong Hu,Shisong Tang,Xiaoqiang Feng,Xiu Li
类目: Information Retrieval (cs.IR)
*备注: Accepted by KDD 2026

点击查看摘要

[IR-2] STORE: Semantic Tokenization Orthogonal Rotation and Efficient Attention for Scaling Up Ranking Models

链接: https://arxiv.org/abs/2511.18805
作者: Yi Xu,Chaofan Fan,Jinxin Hu,Yu Zhang,Zeng Xiaoyi,Jing Zhang
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-3] Multimodal Large Language Models with Adaptive Preference Optimization for Sequential Recommendation

链接: https://arxiv.org/abs/2511.18740
作者: Yu Wang,Yonghui Yang,Le Wu,Yi Zhang,Richang Hong
类目: Information Retrieval (cs.IR)
*备注: 11 pages,6 figures

点击查看摘要

[IR-4] A Recommender System Based on Binary Matrix Representations for Cognitive Disorders

链接: https://arxiv.org/abs/2511.18645
作者: Raoul H. Kutil,Georg Zimmermann,Christian Borgelt
类目: Information Retrieval (cs.IR)
*备注: 19 pages, 1 figure, 3 tables

点击查看摘要

[IR-5] me Matters: Enhancing Sequential Recommendations with Time-Guided Graph Neural ODEs

链接: https://arxiv.org/abs/2511.18347
作者: Haoyan Fu,Zhida Qin,Shixiao Yang,Haoyao Zhang,Bin Lu,Shuang Li,Tianyu Huang,John C.S. Lui
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-6] UFO: Unfair-to-Fair Evolving Mitigates Unfairness in LLM -based Recommender Systems via Self-Play Fine-tuning

链接: https://arxiv.org/abs/2511.18342
作者: Jiaming Zhang,Yuyuan Li,Xiaohua Feng,Zhifei Ren,Li Zhang,Chaochao Chen
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-7] Large Language Model Enhanced Graph Invariant Contrastive Learning for Out-of-Distribution Recommendation

链接: https://arxiv.org/abs/2511.18282
作者: Jiahao Liang,Haoran Yang,Xiangyu Zhao,Zhiwen Yu,Mianjie Li,Chuan Shi,Kaixiang Yang
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-8] Democratic Recommendation with User and Item Representatives Produced by Graph Condensation

链接: https://arxiv.org/abs/2511.18279
作者: Jiahao Liang,Haoran Yang,Xiangyu Zhao,Zhiwen Yu,Guandong Xu,Wanyu Wang,Kaixiang Yang
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

附件下载

点击下载今日全部论文列表