Arxiv今日论文 | 2025-11-04

本篇博文主要内容为 2025-11-04 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。

链接: https://arxiv.org/abs/2511.01846
作者: Thang Luong,Dawsen Hwang,Hoang H. Nguyen,Golnaz Ghiasi,Yuri Chervonyi,Insuk Seo,Junsu Kim,Garrett Bingham,Jonathan Lee,Swaroop Mishra,Alex Zhai,Clara Huiyi Hu,Henryk Michalewski,Jimin Kim,Jeonghyun Ahn,Junhwi Bae,Xingyou Song,Trieu H. Trinh,Quoc V. Le,Junehyuk Jung
机构: Google DeepMind(谷歌深度思维)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: EMNLP 2025 (main conference), this https URL

点击查看摘要

[NLP-2] KV Cache Transform Coding for Compact Storag e in LLM Inference

【速读】：该论文旨在解决大规模语言模型（Large Language Models, LLMs）在推理阶段因键值缓存（Key-Value Cache, KV Cache）管理效率低下而导致的GPU内存占用过高问题。具体而言，尽管共享前缀提示（shared-prefix prompts）可使KV缓存在迭代代码编辑和对话场景中复用，但过时缓存仍会浪费宝贵的GPU显存资源，迫使进行缓存卸载或重新计算。解决方案的关键在于提出一种轻量级变换编码器（KVTC），它通过结合主成分分析（PCA）驱动的特征去相关性、自适应量化与熵编码技术，在不修改模型参数的前提下实现高效的KV缓存压缩。该方法仅需短暂校准即可部署，显著提升了缓存存储密度，最高可达20倍压缩比，且在保持推理准确性和长上下文能力的同时，特定场景下压缩比可达40倍以上。

链接: https://arxiv.org/abs/2511.01815
作者: Konrad Staniszewski,Adrian Łańcucki
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

Abstract:Serving large language models (LLMs) at scale necessitates efficient key-value (KV) cache management. KV caches can be reused across conversation turns via shared-prefix prompts that are common in iterative code editing and chat. However, stale caches consume scarce GPU memory, require offloading, or force recomputation. We present KVTC, a lightweight transform coder that compresses KV caches for compact on-GPU and off-GPU storage. Drawing on classical media compression, KVTC combines PCA-based feature decorrelation, adaptive quantization, and entropy coding. It requires only a brief initial calibration and leaves model parameters unchanged. By exploiting redundancies in KV caches, KVTC achieves up to 20 \times compression while maintaining reasoning and long-context accuracy, and 40 \times or higher for specific use cases. We test KVTC with Llama 3, Mistral NeMo, and R1-Qwen 2.5 models across benchmarks including AIME25, LiveCodeBench, GSM8K, MMLU, Qasper, RULER, and MATH-500. It consistently outperforms inference-time baselines such as token eviction, quantization, and SVD-based methods, while achieving higher compression ratios. These results support KVTC as a practical building block for memory-efficient LLM serving with reusable KV caches.
zh

[NLP-3] Plan-and-Write: Structure-Guided Length Control for LLM s without Model Retraining KDD2025

【速读】：该论文旨在解决大型语言模型（Large Language Models, LLMs）中长度控制（length control）这一关键但未被充分研究的问题，尤其在语音交互等需要简洁回应或研究摘要等需详尽输出的场景下具有重要应用价值。现有方法如正则化DPO（Regularized DPO）、长度指令微调（Length-Instruction Fine Tuning）和工具增强方法通常依赖昂贵的模型重训练或复杂的推理时工具链。本文提出一种无需模型重训练的提示工程（prompt engineering）方法，其核心在于结构引导策略（structure-guided approach），通过在提示中嵌入显式的规划机制与词数统计逻辑，促使模型在生成过程中主动跟踪并严格遵守预设长度约束。实验证明，该方法在六种主流LLM上显著提升了长度保真度（length fidelity），尤其在短至中等长度约束下表现突出，部分模型长度遵循性提升达37.6%，同时保持甚至提升输出质量，为生产环境中难以进行模型重训练的应用提供了即插即用的解决方案。

链接: https://arxiv.org/abs/2511.01807
作者: Adewale Akinfaderin,Shreyas Subramanian,Akarsha Sehwag
机构: Amazon Web Services(亚马逊网络服务)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Presented at Workshop on Prompt Optimization, KDD 2025, Toronto, Canada

点击查看摘要

Abstract:Length control in Large Language Models (LLMs) is a crucial but under-addressed challenge, with applications ranging from voice interfaces requiring concise responses to research summaries needing comprehensive outputs. Current approaches to length control, including Regularized DPO, Length-Instruction Fine Tuning, and tool-augmented methods, typically require expensive model retraining or complex inference-time tooling. This paper presents a prompt engineering methodology that enables precise length control without model retraining. Our structure-guided approach implements deliberate planning and word counting mechanisms within the prompt, encouraging the model to carefully track and adhere to specified length constraints. Comprehensive evaluations across six state-of-the-art LLMs demonstrate that our method significantly improves length fidelity for several models compared to standard prompting when applied to document summarization tasks, particularly for shorter-to-medium length constraints. The proposed technique shows varying benefits across different model architectures, with some models demonstrating up to 37.6% improvement in length adherence. Quality evaluations further reveal that our approach maintains or enhances overall output quality compared to standard prompting techniques. Our approach provides an immediately deployable solution for applications requiring precise length control, particularly valuable for production environments where model retraining is impractical or cost-prohibitive.
zh

[NLP-4] Accumulating Context Changes the Beliefs of Language Models

【速读】：该论文旨在解决语言模型（Language Model, LM）在长时间交互或文本阅读过程中，其信念体系（belief profiles）可能因上下文积累而发生隐性变化的问题，这种变化可能导致模型输出不一致或偏离原始对齐目标，从而影响其可靠性。解决方案的关键在于通过设计实验任务，分别测量模型在讨论道德困境和政治议题时的陈述信念变化，并结合工具使用行为任务验证这些信念变化是否反映在实际行为中，结果表明模型的信念具有高度可塑性，且行为变化与陈述信念变化高度一致，揭示了长期对话或阅读带来的潜在风险。

链接: https://arxiv.org/abs/2511.01805
作者: Jiayi Geng,Howard Chen,Ryan Liu,Manoel Horta Ribeiro,Robb Willer,Graham Neubig,Thomas L. Griffiths
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

Abstract:Language model (LM) assistants are increasingly used in applications such as brainstorming and research. Improvements in memory and context size have allowed these models to become more autonomous, which has also resulted in more text accumulation in their context windows without explicit user intervention. This comes with a latent risk: the belief profiles of models – their understanding of the world as manifested in their responses or actions – may silently change as context accumulates. This can lead to subtly inconsistent user experiences, or shifts in behavior that deviate from the original alignment of the models. In this paper, we explore how accumulating context by engaging in interactions and processing text – talking and reading – can change the beliefs of language models, as manifested in their responses and this http URL results reveal that models’ belief profiles are highly malleable: GPT-5 exhibits a 54.7% shift in its stated beliefs after 10 rounds of discussion about moral dilemmas and queries about safety, while Grok 4 shows a 27.2% shift on political issues after reading texts from the opposing position. We also examine models’ behavioral changes by designing tasks that require tool use, where each tool selection corresponds to an implicit belief. We find that these changes align with stated belief shifts, suggesting that belief shifts will be reflected in actual behavior in agentic systems. Our analysis exposes the hidden risk of belief shift as models undergo extended sessions of talking or reading, rendering their opinions and actions unreliable.
zh

[NLP-5] Random Initialization of Gated Sparse Adapters ICML2025

链接: https://arxiv.org/abs/2511.01794
作者: Vi Retault,Yohaï-Eliel Berreby
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 13 pages (8 main), 6 figures (4 main). Accepted by NewInML workshop @ ICML 2025 on June 27, 2025

点击查看摘要

[NLP-6] RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks

链接: https://arxiv.org/abs/2511.01758
作者: Mian Wu,Gavin Zhang,Sewon Min,Sergey Levine,Aviral Kumar
机构: Shanghai Jiao Tong University (上海交通大学); UC Berkeley (加州大学伯克利分校); Carnegie Mellon University (卡内基梅隆大学)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Project page: this https URL

点击查看摘要

[NLP-7] Efficient Tool-Calling Multi-Expert NPC Agent for Commonsense Persona-Grounded Dialogue EMNLP2025

链接: https://arxiv.org/abs/2511.01720
作者: Mahammad Nuriyev
机构: Université Paris-Saclay (巴黎-萨克雷大学)
类目: Computation and Language (cs.CL)
备注: 10 pages, 1 figure, 2 tables. Technical report for the Commonsense Persona-Grounded Dialogue Challenge (CPDC) 2025, part of the Wordplay 2025 Workshop @ EMNLP 2025

点击查看摘要

[NLP-8] Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement

链接: https://arxiv.org/abs/2511.01706
作者: Sekh Mainul Islam,Pepa Atanasova,Isabelle Augenstein
机构: University of Copenhagen (哥本哈根大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Under review

点击查看摘要

[NLP-9] Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI

【速读】：该论文旨在解决现代对话式大语言模型（Large Language Models, LLMs）中“AI助手”人格（persona）塑造缺乏系统性研究与可控方法的问题，尤其关注如何在后训练阶段有效、稳定地引导模型表现出特定的性格特征（如幽默、关怀或恶意），从而提升交互质量、对齐开发者与用户意图，并增强对抗性提示下的鲁棒性。解决方案的关键在于提出首个开源的“人格训练”（character training）框架，其核心是结合宪法式人工智能（Constitutional AI）与一种基于合成内省数据的新颖数据流水线，通过微调三个主流开源权重模型（使用11个示例人格进行训练），实现对助手人格的精细化控制，相较传统约束系统提示或激活引导（activation steering）方法，在生成连贯性和真实性上表现更优，且对通用能力基准测试影响极小。

链接: https://arxiv.org/abs/2511.01689
作者: Sharan Maiya,Henning Bartsch,Nathan Lambert,Evan Hubinger
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 12 pages, 6 figures, 4 tables

点击查看摘要

Abstract:The character of the “AI assistant” persona generated by modern chatbot large language models influences both surface-level behavior and apparent values, beliefs, and ethics. These all affect interaction quality, perceived intelligence, and alignment with both developer and user intentions. The shaping of this persona, known as character training, is a critical component of industry post-training, yet remains effectively unstudied in the academic literature. We introduce the first open implementation of character training, leveraging Constitutional AI and a new data pipeline using synthetic introspective data to shape the assistant persona in a more effective and controlled manner than alternatives such as constraining system prompts or activation steering. Specifically, we fine-tune three popular open-weights models using 11 example personas, such as humorous, deeply caring, or even malevolent. To track the effects of our approach, we introduce a method which analyzes revealed preferences, uncovering clear and holistic changes in character. We find these changes are more robust to adversarial prompting than the above two alternatives, while also leading to more coherent and realistic generations. Finally, we demonstrate this fine-tuning has little to no effect on general capabilities as measured by common benchmarks. We describe and open-source our full post-training method, the implementation of which can be found at this https URL.
zh

[NLP-10] SeaLLM s-Audio: Large Audio-Language Models for Southeast Asia

【速读】：该论文旨在解决东南亚地区多语言音频理解与交互能力不足的问题，尤其是在生成式 AI (Generative AI) 领域缺乏针对印尼语、泰语、越南语等本地语言的高质量大音频语言模型（Large Audio-Language Model, LALM）的问题。解决方案的关键在于提出 SeaLLMs-Audio，这是首个专为东南亚五种语言（印尼语、泰语、越南语、英语和中文）设计的大规模音频语言模型，具备多语言、多模态（支持纯音频、纯文本及音文联合输入）和多任务能力（涵盖语音识别、语音情感识别、语音问答、语音摘要及语音对话等），并通过构建 SeaBench-Audio 基准测试体系实现自动化评估，实验表明其在东南亚语言上的表现具有竞争力。

链接: https://arxiv.org/abs/2511.01670
作者: Chaoqun Liu,Mahani Aljunied,Guizhen Chen,Hou Pong Chan,Weiwen Xu,Yu Rong,Wenxuan Zhang
机构: DAMO Academy, Alibaba Group(阿里巴巴集团达摩院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 10 pages

点击查看摘要

Abstract:We introduce SeaLLMs-Audio, the first large audio-language model (LALM) tailored for multiple Southeast Asian (SEA) languages-Indonesian (id), Thai (th), and Vietnamese (vi)-alongside English (en) and Chinese (zh). Trained on a large-scale audio corpus, SeaLLMs-Audio exhibits strong performance across diverse audio-centric tasks, spanning fine-grained audio understanding and voice-based interaction. Its key features include: 1) Multilingual: the model primarily supports 5 languages, namely Indonesian, Thai, Vietnamese, English, and Chinese; 2) Multimodal: the model accepts flexible input modalities, including audio only, text only, as well as audio with text; 3) Multi-task: the model supports a wide range of tasks, including audio analysis tasks such as Audio Captioning, Automatic Speech Recognition, Speech-to-Text Translation, Speech Emotion Recognition, Speech Question Answering, and Speech Summarization. It also enables voice-based dialogue, including answering factual, mathematical, and general knowledge queries. As a significant step towards advancing audio LLMs in Southeast Asia, we expect SeaLLMs-Audio to benefit both the regional research community and industry. To automate LALM evaluation for Southeast Asia, we introduce SeaBench-Audio, a benchmark spanning multiple tasks. Experiments show that SeaLLMs-Audio achieves competitive performance compared with other LALMs on SEA languages.
zh

[NLP-11] EngChain: A Symbolic Benchmark for Verifiable Multi-Step Reasoning in Engineering

链接: https://arxiv.org/abs/2511.01650
作者: Ayesha Gull,Muhammad Usman Safder,Rania Elbadry,Preslav Nakov,Zhuohan Xie
机构: Namal University; MBZUAI (Mohamed bin Zayed University of Artificial Intelligence)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 24 pages, includes figures and tables; introduces the EngChain benchmark

点击查看摘要

[NLP-12] Evaluating Cultural Knowledge Processing in Large Language Models : A Cognitive Benchmarking Framework Integrating Retrieval-Augmented Generation

【速读】：该论文旨在解决大语言模型（Large Language Models, LLMs）在处理和应用文化特定知识时缺乏系统性评估标准的问题。其解决方案的关键在于提出一个融合布卢姆认知分类法（Bloom’s Taxonomy）与检索增强生成（Retrieval-Augmented Generation, RAG）的认知基准测试框架，通过六个层级的认知域（记忆、理解、应用、分析、评价与创造）对模型输出的语义准确性与文化相关性进行量化评估，并以台湾客家数字文化档案作为核心测试场景，从而实现对LLMs在跨文化语境下知识理解与生成能力的精细化测评。

链接: https://arxiv.org/abs/2511.01649
作者: Hung-Shin Lee,Chen-Chi Chang,Ching-Yuan Chen,Yun-Hsiang Hsu
机构: 未知
类目: Computation and Language (cs.CL)
备注: This paper has been accepted by The Electronic Library, and the full article is now available on Emerald Insight

点击查看摘要

Abstract:This study proposes a cognitive benchmarking framework to evaluate how large language models (LLMs) process and apply culturally specific knowledge. The framework integrates Bloom’s Taxonomy with Retrieval-Augmented Generation (RAG) to assess model performance across six hierarchical cognitive domains: Remembering, Understanding, Applying, Analyzing, Evaluating, and Creating. Using a curated Taiwanese Hakka digital cultural archive as the primary testbed, the evaluation measures LLM-generated responses’ semantic accuracy and cultural relevance.
zh

[NLP-13] A Graph-based RAG for Energy Efficiency Question Answering

链接: https://arxiv.org/abs/2511.01643
作者: Riccardo Campi,Nicolò Oreste Pinciroli Vago,Mathyas Giudici,Pablo Barrachina Rodriguez-Guisado,Marco Brambilla,Piero Fraternali
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
备注:

点击查看摘要

[NLP-14] ParlaSpeech 3.0: Richly Annotated Spoken Parliamentary Corpora of Croatian Czech Polish and Serbian LREC2026

【速读】：该论文旨在解决多语言议会语音语料库在下游研究中缺乏丰富自动标注层的问题，从而限制了其在语音处理、情感分析等领域的应用潜力。解决方案的关键在于通过自动化流程对ParlaSpeech语料库进行多层次标注增强：在文本模态上加入语言学标注和情感预测，在语音模态上识别填充停顿（filled pauses）这一典型话语不流畅现象；同时，针对两种斯拉夫语言进一步提供词级与音素级对齐以及多音节词重音位置的自动标注。这些增强显著提升了语料库在跨学科研究中的实用性，例如通过声学特征分析情感相关性。

链接: https://arxiv.org/abs/2511.01619
作者: Nikola Ljubešić,Peter Rupnik,Ivan Porupski,Taja Kuzman Pungeršek
机构: 未知
类目: Computation and Language (cs.CL)
备注: Submitted to the LREC 2026 conference; 11 pages, 2 figures, 3 tables

点击查看摘要

Abstract:ParlaSpeech is a collection of spoken parliamentary corpora currently spanning four Slavic languages - Croatian, Czech, Polish and Serbian - all together 6 thousand hours in size. The corpora were built in an automatic fashion from the ParlaMint transcripts and their corresponding metadata, which were aligned to the speech recordings of each corresponding parliament. In this release of the dataset, each of the corpora is significantly enriched with various automatic annotation layers. The textual modality of all four corpora has been enriched with linguistic annotations and sentiment predictions. Similar to that, their spoken modality has been automatically enriched with occurrences of filled pauses, the most frequent disfluency in typical speech. Two out of the four languages have been additionally enriched with detailed word- and grapheme-level alignments, and the automatic annotation of the position of primary stress in multisyllabic words. With these enrichments, the usefulness of the underlying corpora has been drastically increased for downstream research across multiple disciplines, which we showcase through an analysis of acoustic correlates of sentiment. All the corpora are made available for download in JSONL and TextGrid formats, as well as for search through a concordancer.
zh

[NLP-15] Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models

【速读】：该论文旨在解决当前多模态大语言模型（Multimodal Large Language Models, MLLMs）在3D空间推理任务中对细节空间信息捕捉能力不足的问题，特别是跨视角一致性（cross-view consistency）这一关键挑战，这直接影响其在真实场景中的鲁棒性表现。解决方案的关键在于提出一种名为“视角学习”（Viewpoint Learning）的新任务，并构建了包含10万组以物体为中心的多视角图像对及其问答数据的Viewpoint-100K数据集；在此基础上采用两阶段微调策略：第一阶段通过监督微调（Supervised Fine-Tuning, SFT）注入基础空间知识，第二阶段利用群体相对策略优化（Group Relative Policy Optimization, GRPO）强化泛化能力；同时引入混合冷启动初始化方法，协同学习视角表示并保持推理逻辑的一致性，从而显著提升MLLM在域内与域外3D推理任务中的性能。

链接: https://arxiv.org/abs/2511.01618
作者: Xiaoyu Zhan,Wenxuan Huang,Hao Sun,Xinyu Fu,Changfeng Ma,Shaosheng Cao,Bohan Jia,Shaohui Lin,Zhenfei Yin,Lei Bai,Wanli Ouyang,Yuanqi Li,Jie Guo,Yanwen Guo
机构: Nanjing University (南京大学); Xiaohongshu Inc. (小红书公司); East China Normal University (华东师范大学); The Chinese University of Hong Kong (香港中文大学); Shanghai Jiao Tong University (上海交通大学); University of Oxford (牛津大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注:

点击查看摘要

Abstract:Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved 2D visual understanding, prompting interest in their application to complex 3D reasoning tasks. However, it remains unclear whether these models can effectively capture the detailed spatial information required for robust real-world performance, especially cross-view consistency, a key requirement for accurate 3D reasoning. Considering this issue, we introduce Viewpoint Learning, a task designed to evaluate and improve the spatial reasoning capabilities of MLLMs. We present the Viewpoint-100K dataset, consisting of 100K object-centric image pairs with diverse viewpoints and corresponding question-answer pairs. Our approach employs a two-stage fine-tuning strategy: first, foundational knowledge is injected to the baseline MLLM via Supervised Fine-Tuning (SFT) on Viewpoint-100K, resulting in significant improvements across multiple tasks; second, generalization is enhanced through Reinforcement Learning using the Group Relative Policy Optimization (GRPO) algorithm on a broader set of questions. Additionally, we introduce a hybrid cold-start initialization method designed to simultaneously learn viewpoint representations and maintain coherent reasoning thinking. Experimental results show that our approach significantly activates the spatial reasoning ability of MLLM, improving performance on both in-domain and out-of-domain reasoning tasks. Our findings highlight the value of developing foundational spatial skills in MLLMs, supporting future progress in robotics, autonomous systems, and 3D scene understanding.
zh

[NLP-16] Imperfect Language Artificial Intelligence and the Human Mind: An Interdisciplinary Approach to Linguistic Errors in Native Spanish Speakers

链接: https://arxiv.org/abs/2511.01615
作者: Francisco Portillo López
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 12 pages, 3 figures

点击查看摘要

[NLP-17] BIRD: Bronze Inscription Restoration and Dating EMNLP2025

链接: https://arxiv.org/abs/2511.01589
作者: Wenjie Hua,Hoang H. Nguyen,Gangyan Ge
机构: Wuhan University (武汉大学); University of Illinois, Chicago (伊利诺伊大学芝加哥分校); Xinjiang University (新疆大学)
类目: Computation and Language (cs.CL)
备注: Accepted at EMNLP 2025 (Main Conference)

点击查看摘要

[NLP-18] ECO Decoding: Entropy-Based Control for Controllability and Fluency in Controllable Dialogue Generation EMNLP2025

链接: https://arxiv.org/abs/2511.01568
作者: Seungmin Shin,Dooyoung Kim,Youngjoong Ko
机构: SungKyunKwan University (成均馆大学)
类目: Computation and Language (cs.CL)
备注: Published at EMNLP 2025 main

点击查看摘要

[NLP-19] Math anxiety and associative knowledge structure are entwined in psychology students but not in Large Language Models like GPT GPT -3.5 and GPT-4o

链接: https://arxiv.org/abs/2511.01558
作者: Luciana Ciringione,Emma Franchino,Simone Reigl,Isaia D’Onofrio,Anna Serbati,Oleksandra Poquet,Florence Gabriel,Massimo Stella
机构: 未知
类目: Computation and Language (cs.CL); Computers and Society (cs.CY)
备注:

点击查看摘要

[NLP-20] Hidden in Plain Sight: Where Developers Confess Self-Admitted Technical Debt

链接: https://arxiv.org/abs/2511.01529
作者: Murali Sridharan,Mikel Robredo,Leevi Rantala,Matteo Esposito,Valentina Lenarduzzi,Mika Mantyla
机构: University of Oulu (奥卢大学); University of Helsinki (赫尔辛基大学)
类目: oftware Engineering (cs.SE); Computation and Language (cs.CL); Programming Languages (cs.PL)
备注:

点击查看摘要

[NLP-21] Difficulty-Controllable Cloze Question Distractor Generation

链接: https://arxiv.org/abs/2511.01526
作者: Seokhoon Kang,Yejin Jeon,Seonjeong Hwang,Gary Geunbae Lee
机构: POSTECH(浦项科技大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-22] BanglaNirTox: A Large-scale Parallel Corpus for Explainable AI in Bengali Text Detoxification

链接: https://arxiv.org/abs/2511.01512
作者: Ayesha Afroza Mohsin,Mashrur Ahsan,Nafisa Maliyat,Shanta Maria,Syed Rifat Raiyan,Hasan Mahmud,Md Kamrul Hasan
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Under review, 6 pages, 1 figure, 2 tables

点击查看摘要

[NLP-23] Synthetic Eggs in Many Baskets: The Impact of Synthetic Data Diversity on LLM Fine-Tuning

【速读】：该论文旨在解决合成数据（synthetic data）来源多样性对微调后大语言模型行为影响的问题，重点关注分布坍塌（distribution collapse）、对抗鲁棒性（adversarial robustness）和自偏好偏差（self-preference bias）三个维度。其解决方案的关键在于：使用来自多种来源的合成数据进行微调，能够有效缓解分布坍塌，维持输出分布的广度与文本多样性；相较于人类标注数据，合成数据虽在去除安全防护机制方面效果相当，但能保持更高输出质量，从而提升可用性但也可能增加风险；此外，微调可降低自偏好偏差，其中人类数据效果最佳，多源合成数据次之。

链接: https://arxiv.org/abs/2511.01490
作者: Max Schaffelder,Albert Gatt
机构: Utrecht University (乌得勒支大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

Abstract:As synthetic data becomes widely used in language model development, understanding its impact on model behavior is crucial. This paper investigates the impact of the diversity of sources of synthetic data on fine-tuned large language models. We focus on three key dimensions: distribution collapse, adversarial robustness, and self-preference bias. Our findings reveal that fine-tuning models on synthetic data from diverse sources can mitigate distribution collapse, preserving the breadth of the output distribution and the diversity of the output text. Furthermore, while both human and synthetic fine-tuning data can remove safeguards, the latter preserves higher output quality, thus making outputs potentially more usable and dangerous. Finally, fine-tuning reduces self-preference bias, with human data being the most effective, followed by multi-source synthetic data.
zh

[NLP-24] owards Consistent Detection of Cognitive Distortions: LLM -Based Annotation and Dataset-Agnostic Evaluation

链接: https://arxiv.org/abs/2511.01482
作者: Neha Sharma,Navneet Agarwal,Kairit Sirts
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-25] BARD: budget-aware reasoning distillation

链接: https://arxiv.org/abs/2511.01470
作者: Lujie Niu,Lei Shen,Yi Jiang,Caixia Yuan,Xiaojie Wang,Wenbo Su,Bo zheng
机构: Taobao & Tmall Group of Alibaba(淘宝与天猫集团)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-26] “Dont Teach Minerva”: Guiding LLM s Through Complex Syntax for Faithful Latin Translation with RAG

链接: https://arxiv.org/abs/2511.01454
作者: Sergio Torres Aguilar
机构: Universidad Complutense de Madrid (康普顿斯大学)
类目: Computation and Language (cs.CL); Digital Libraries (cs.DL)
备注:

点击查看摘要

[NLP-27] LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge

链接: https://arxiv.org/abs/2511.01409
作者: Heng Zhou,Ao Yu,Yuchen Fan,Jianing Shi,Li Kang,Hejia Geng,Yongting Zhang,Yutao Fan,Yuhao Wu,Tiancheng He,Yiran Qin,Lei Bai,Zhenfei Yin
机构: University of Science and Technology of China (中国科学技术大学); Shanghai AI Laboratory (上海人工智能实验室); Shanghai Jiao Tong University (上海交通大学); London School of Economics (伦敦经济学院); BUPT (北京邮电大学); Harbin Institute of Technology (哈尔滨工业大学); SUTD (新加坡科技设计大学); University of Oxford (牛津大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-28] RAG Smith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets

链接: https://arxiv.org/abs/2511.01386
作者: Muhammed Yusuf Kartal(1),Suha Kagan Kose(2),Korhan Sevinç(1),Burak Aktas(2) ((1) TOBB University of Economics and Technology, (2) Roketsan Inc.)
机构: TOBB University of Economics and Technology (TOBB经济与技术大学); Roketsan Inc. (罗克桑公司)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
备注: 45 pages

点击查看摘要

[NLP-29] Confounding Factors in Relating Model Performance to Morphology EMNLP2025

链接: https://arxiv.org/abs/2511.01380
作者: Wessel Poelman,Thomas Bauwens,Miryam de Lhoneux
机构: KU Leuven (鲁汶大学)
类目: Computation and Language (cs.CL)
备注: EMNLP 2025: Main Conference

点击查看摘要

[NLP-30] he Ouroboros of Benchmarking: Reasoning Evaluation in an Era of Saturation NEURIPS NEURIPS2025

链接: https://arxiv.org/abs/2511.01365
作者: İbrahim Ethem Deveci,Duygu Ataman
机构: Middle East Technical University (中东技术大学)
类目: Computation and Language (cs.CL)
备注: Accepted to NeurIPS 2025 Workshop on LLM Evaluation ( this https URL )

点击查看摘要

[NLP-31] Safer in Translation? Presupposition Robustness in Indic Languages LREC2026

链接: https://arxiv.org/abs/2511.01360
作者: Aadi Palnitkar,Arjun Suresh,Rishi Rajesh,Puneet Puli
机构: 未知
类目: Computation and Language (cs.CL)
备注: This is a submission to LREC 2026 (Language Resources and Evaluation Conference 2026). Corresponding author: aadipalnitkar96@gmail.com

点击查看摘要

[NLP-32] PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise

链接: https://arxiv.org/abs/2511.01359
作者: Sapir Harary,Eran Hirsch,Aviv Slobodkin,David Wan,Mohit Bansal,Ido Dagan
机构: Bar-Ilan University (巴伊兰大学); UNC 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)
备注: 9 pages + appendix. Code, datasets, and models are available at this https URL

点击查看摘要

[NLP-33] hinking with DistilQwen : A Tale of Four Distilled Reasoning and Reward Model Series EMNLP2025

链接: https://arxiv.org/abs/2511.01354
作者: Wenrui Cai,Chengyu Wang,Junbing Yan,Jun Huang,Xiangzhong Fang
机构: Shanghai Jiao Tong University (上海交通大学); Alibaba Cloud Computing (阿里云计算)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: emnlp 2025 industry track

点击查看摘要

[NLP-34] left|circlearrowrightboxedtextBUSright|: A Large and Diverse Multimodal Benchmark for evaluating the ability of Vision-Language Models to understand Rebus Puzzles

链接: https://arxiv.org/abs/2511.01340
作者: Trishanu Das,Abhilash Nandy,Khush Bajaj,Deepiha S
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注: 7 pages, 5 figures, 4 tables

点击查看摘要

[NLP-35] DEEPAMBIGQA: Ambiguous Multi-hop Questions for Benchmarking LLM Answer Completeness

链接: https://arxiv.org/abs/2511.01323
作者: Jiabao Ji,Min Li,Priyanshu Kumar,Shiyu Chang,Saloni Potdar
机构: UCSB; Apple
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 25 pages

点击查看摘要

[NLP-36] DeepSpecs: Expert-Level Questions Answering in 5G

链接: https://arxiv.org/abs/2511.01305
作者: Aman Ganapathy Manvattira,Yifei Xu,Ziyue Dang,Songwu Lu
机构: University of California, Los Angeles (加州大学洛杉矶分校)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI)
备注:

点击查看摘要

[NLP-37] FirstAidQA: A Synthetic Dataset for First Aid and Emergency Response in Low-Connectivity Settings NEURIPS2025

链接: https://arxiv.org/abs/2511.01289
作者: Saiyma Sittul Muna,Rezwan Islam Salvi,Mushfiqur Rahman Mushfique,Ajwad Abrar
机构: Islamic University of Technology (伊斯兰科技大学)
类目: Computation and Language (cs.CL)
备注: Accepted at the 5th Muslims in Machine Learning (MusIML) Workshop, co-located with NeurIPS 2025

点击查看摘要

[NLP-38] “Give a Positive Review Only”: An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers

链接: https://arxiv.org/abs/2511.01287
作者: Qin Zhou,Zhexin Zhang,Zhi Li,Limin Sun
机构: Institute of Information Engineering, CAS (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); The Conversational AI (CoAI) group, DCST, Tsinghua University (清华大学数据科学与技术研究院对话人工智能组)
类目: Computation and Language (cs.CL); Cryptography and Security (cs.CR)
备注:

点击查看摘要

[NLP-39] When What and How: Rethinking Retrieval-Enhanced Speculative Decoding

链接: https://arxiv.org/abs/2511.01282
作者: Min Fang,Zhihui Fu,Qibin Zhao,Jun Wang
机构: OPPO Research Institute (OPPO研究院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-40] AraFinNews: Arabic Financial Summarisation with Domain-Adapted LLM s

链接: https://arxiv.org/abs/2511.01265
作者: Mo El-Haj,Paul Rayson
机构: 未知
类目: Computation and Language (cs.CL)
备注: 10 pages

点击查看摘要

[NLP-41] FEval-TTC: Fair Evaluation Protocol for Test-Time Compute

链接: https://arxiv.org/abs/2511.01203
作者: Pavel Rumiantsev,Soumyasundar Pal,Yingxue Zhang,Mark Coates
机构: McGill University (麦吉尔大学); Huawei Noah’s Ark Lab (华为诺亚方舟实验室)
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-42] DEER: Disentangled Mixture of Experts with Instance-Adaptive Routing for Generalizable Machine-Generated Text Detection

链接: https://arxiv.org/abs/2511.01192
作者: Guoxin Ma,Xiaoming Liu,Zhanhan Zhang,Chengzhengxu Li,Shengchao Liu,Yu Lan
机构: 未知
类目: Computation and Language (cs.CL)
备注: Under Review

点击查看摘要

[NLP-43] Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning

链接: https://arxiv.org/abs/2511.01191
作者: Ru Wang,Wei Huang,Qi Cao,Yusuke Iwasawa,Yutaka Matsuo,Jiaxian Guo
机构: The University of Tokyo (东京大学); RIKEN Center for Advanced Intelligence Project (理化学研究所先进智能项目中心); Google Research, Australia (谷歌研究院，澳大利亚)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-44] ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction

链接: https://arxiv.org/abs/2511.01188
作者: Lvhua Wu,Xuefeng Jiang,Sheng Sun,Tian Wen,Yuwei Wang,Min Liu
机构: Institute of Computing Technology, Chinese Academy of Sciences (中国科学院计算技术研究所); University of Chinese Academy of Sciences (中国科学院大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-45] Surfacing Subtle Stereotypes: A Multilingual Debate-Oriented Evaluation of Modern LLM s

链接: https://arxiv.org/abs/2511.01187
作者: Muhammed Saeed,Muhammad Abdul-mageed,Shady Shehata
机构: 未知
类目: Computation and Language (cs.CL); Computers and Society (cs.CY)
备注:

点击查看摘要

[NLP-46] Learning When to Quit in Sales Conversations

链接: https://arxiv.org/abs/2511.01181
作者: Emaad Manzoor,Eva Ascarza,Oded Netzer
机构: Cornell University (康奈尔大学); Harvard Business School (哈佛商学院); Columbia Business School (哥伦比亚商学院)
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-47] MicroRemed: Benchmarking LLM s in Microservices Remediation

链接: https://arxiv.org/abs/2511.01166
作者: Lingzhe Zhang,Yunpeng Zhai,Tong Jia,Chiming Duan,Minghua He,Leyi Pan,Zhaoyang Liu,Bolin Ding,Ying Li
机构: Peking University (北京大学); Alibaba Group (阿里巴巴集团); Tsinghua University (清华大学)
类目: Computation and Language (cs.CL); Software Engineering (cs.SE)
备注: 24 pages, 13 figures, 5 tables

点击查看摘要

[NLP-48] S2Doc - Spatial-Semantic Document Format LREC2026

链接: https://arxiv.org/abs/2511.01113
作者: Sebastian Kempf,Frank Puppe
机构: 未知
类目: Digital Libraries (cs.DL); Computation and Language (cs.CL)
备注: 8 pages, 2 figures, submitted to LREC2026

点击查看摘要

[NLP-49] HarnessLLM : Automatic Testing Harness Generation via Reinforcement Learning

链接: https://arxiv.org/abs/2511.01104
作者: Yujian Liu,Jiabao Ji,Yang Zhang,Wenbo Guo,Tommi Jaakkola,Shiyu Chang
机构: UC Santa Barbara (加州大学圣塔芭芭拉分校); MIT-IBM Watson AI Lab (麻省理工学院-IBM沃森人工智能实验室); MIT CSAIL (麻省理工学院计算机科学与人工智能实验室)
类目: oftware Engineering (cs.SE); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-50] SVer: A Benchmark for Fact Verification Against Time-Series Evidence EMNLP2025

链接: https://arxiv.org/abs/2511.01101
作者: Marek Strong,Andreas Vlachos
机构: University of Cambridge (剑桥大学)
类目: Computation and Language (cs.CL)
备注: Accepted to EMNLP 2025

点击查看摘要

[NLP-51] Improving Romanian LLM Pretraining Data using Diversity and Quality Filtering

链接: https://arxiv.org/abs/2511.01090
作者: Vlad Negoita,Mihai Masala,Traian Rebedea
机构: National University of Science and Technology POLITEHNICA Bucharest (布加勒斯特理工大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-52] HPLT~3.0: Very Large-Scale Multilingual Resources for LLM and MT. Mono- and Bi-lingual Data Multilingual Evaluation and Pre-Trained Models

链接: https://arxiv.org/abs/2511.01066
作者: Stephan Oepen,Nikolay Arefev,Mikko Aulamo,Marta Bañón,Maja Buljan,Laurie Burchell,Lucas Charpentier,Pinzhen Chen,Mariya Fedorova,Ona de Gibert,Barry Haddow,Jan Hajič,Jindrič Helcl,Andrey Kutuzov,Zihao Li,Risto Luukkonen,Bhavitvya Malik,Vladislav Mikhailov,Amanda Myntti,Dayyán O’Brien,Lucie Poláková,Sampo Pyysalo,Gema Ramírez Sánchez,Janine Siewert,Pavel Stepachev,Jörg Tiedemann,Teemu Vahtola,Fedor Vitiugin,Tea Vojtěchová,Jaume Zaragoza
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-53] Building a Silver-Standard Dataset from NICE Guidelines for Clinical LLM s

链接: https://arxiv.org/abs/2511.01053
作者: Qing Ding,Eric Hua Qing Zhang,Felix Jozsa,Julia Ive
机构: 未知
类目: Computation and Language (cs.CL)
备注: Submitted to EFMI Medical Informatics Europe 2026

点击查看摘要

[NLP-54] VayuChat: An LLM -Powered Conversational Interface for Air Quality Data Analytics

链接: https://arxiv.org/abs/2511.01046
作者: Vedant Acharya,Abhay Pisharodi,Rishabh Mondal,Mohammad Rafiuddin,Nipun Batra
机构: Indian Institute of Technology Gandhinagar (印度理工学院甘地纳格尔分校); Council on Energy, Environment and Water (能源、环境与水理事会)
类目: Computation and Language (cs.CL)
备注: 4 Pages, 4 Figures

点击查看摘要

[NLP-55] On the Emergence of Induction Heads for In-Context Learning

链接: https://arxiv.org/abs/2511.01033
作者: Tiberiu Musat,Tiago Pimentel,Lorenzo Noci,Alessandro Stolfo,Mrinmaya Sachan,Thomas Hofmann
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-56] OceanAI: A Conversational Platform for Accurate Transparent Near-Real-Time Oceanographic Insights

链接: https://arxiv.org/abs/2511.01019
作者: Bowen Chen,Jayesh Gajbhar,Gregory Dusek,Rob Redmon,Patrick Hogan,Paul Liu,DelWayne Bohnenstiehl,Dongkuan(DK)Xu,Ruoying He
机构: North Carolina State University (北卡罗来纳州立大学); NOAA (美国国家海洋和大气管理局)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG); Atmospheric and Oceanic Physics (physics.ao-ph)
备注: A related presentation will be given at the AGU(American Geophysical Union) and AMS(American Meteorological Society) Annual Meetings

点击查看摘要

[NLP-57] Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning

链接: https://arxiv.org/abs/2511.01016
作者: Wenjin Liu,Haoran Luo,Xueyuan Lin,Haoming Liu,Tiesunlong Shen,Jiapu Wang,Rui Mao,Erik Cambria
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-58] IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluation

【速读】：该论文旨在解决当前大型语言模型（Large Language Models, LLMs）在指令遵循能力评估中存在的缺陷，如评估成本高、可靠性差等问题。现有方法依赖于LLM-as-a-Judge进行偏好优化或强化学习，但其奖励信号不稳定且计算开销大。解决方案的关键在于提出IF-CRITIC——一种高效的LLM评议员，通过构建约束检查清单（constraint checklist）来结构化分解输入指令，并基于多阶段批判过滤机制收集高质量训练数据；进一步采用约束级别的偏好优化方法训练IF-CRITIC，使其能够提供可扩展且可靠的约束遵循评估。实验表明，IF-CRITIC在评估性能上优于Deepseek-R1和o4-mini等强基线模型，并能以更低的计算开销显著提升LLMs的指令遵循优化效果。

链接: https://arxiv.org/abs/2511.01014
作者: Bosi Wen,Yilin Niu,Cunxiang Wang,Pei Ke,Xiaoying Ling,Ying Zhang,Aohan Zeng,Hongning Wang,Minlie Huang
机构: 未知
类目: Computation and Language (cs.CL)
备注: 21 pages, 5 figures

点击查看摘要

Abstract:Instruction following is a fundamental ability of Large Language Models (LLMs), requiring their generated outputs to follow multiple constraints imposed in input instructions. Numerous studies have attempted to enhance this ability through preference optimization or reinforcement learning based on reward signals from LLM-as-a-Judge. However, existing evaluation models for instruction following still possess many deficiencies, such as substantial costs and unreliable assessments. To this end, we propose IF-CRITIC, an LLM critic that can provide efficient and reliable assessments of constraint following in the instructions. We first develop a checklist generator to decompose instructions and generate constraint checklists. With the assistance of the checklists, we collect high-quality critique training data through a multi-stage critique filtering mechanism and employ a constraint-level preference optimization method to train IF-CRITIC. Extensive experiments demonstrate that the evaluation performance of IF-CRITIC can beat strong LLM-as-a-Judge baselines, including Deepseek-R1 and o4-mini. With the scalable reward signals provided by IF-CRITIC, LLMs can achieve substantial performance gains in instruction-following optimization under lower computational overhead compared to strong LLM critic baselines.
zh

[NLP-59] MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL

链接: https://arxiv.org/abs/2511.01008
作者: Haolin Yang,Jipeng Zhang,Zhitao He,Yi R. Fung
机构: The Hong Kong University of Science and Technology (香港科技大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-60] Advancing Machine-Generated Text Detection from an Easy to Hard Supervision Perspective

链接: https://arxiv.org/abs/2511.00988
作者: Chenwang Wu,Yiu-ming Cheung,Bo Han,Defu Lian
机构: Hong Kong Baptist University (香港浸会大学); University of Science and Technology of China (中国科学技术大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-61] ORANGE: An Online Reflection ANd GEneration framework with Domain Knowledge for Text-to-SQL

链接: https://arxiv.org/abs/2511.00985
作者: Yiwen Jiao,Tonghui Ren,Yuche Gao,Zhenying He,Yinan Jing,Kai Zhang,X. Sean Wang
机构: 未知
类目: Databases (cs.DB); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 16 pages, 4 figures, preprint

点击查看摘要

[NLP-62] he Riddle of Reflection: Evaluating Reasoning and Self-Awareness in Multilingual LLM s using Indian Riddles

链接: https://arxiv.org/abs/2511.00960
作者: Abhinav P M,Ojasva Saxena,Oswald C,Parameswari Krishnamurthy
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-63] LLM s Position Themselves as More Rational Than Humans: Emergence of AI Self-Awareness Measured Through Game Theory

链接: https://arxiv.org/abs/2511.00926
作者: Kyung-Hoon Kim
机构: Gmarket; Seoul National University (首尔国立大学)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 19 pages, 6 figures, 28 models tested across 4,200 trials

点击查看摘要

[NLP-64] he Biased Oracle: Assessing LLM s Understandability and Empathy in Medical Diagnoses ALT NEURIPS2025

链接: https://arxiv.org/abs/2511.00924
作者: Jianzhou Yao,Shunchang Liu,Guillaume Drui,Rikard Pettersson,Alessandro Blasimme,Sara Kijewski
机构: ETH Zurich (苏黎世联邦理工学院)
类目: Computation and Language (cs.CL)
备注: Accepted by NeurIPS 2025 GenAI4Health Workshop

点击查看摘要

[NLP-65] ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval

链接: https://arxiv.org/abs/2511.00903
作者: Ahmed Masry,Megh Thakkar,Patrice Bechard,Sathwik Tejaswi Madhusudhan,Rabiul Awal,Shambhavi Mishra,Akshay Kalkunte Suresh,Srivatsava Daruru,Enamul Hoque,Spandana Gella,Torsten Scholak,Sai Rajeswar
机构: ServiceNow; York University (约克大学); MILA - Quebec AI Institute (魁北克人工智能研究所); Université de Montréal (蒙特利尔大学); École de technologie supérieure (高等技术学院)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-66] Assessing LLM Reasoning Steps via Principal Knowledge Grounding EMNLP2025

链接: https://arxiv.org/abs/2511.00879
作者: Hyeon Hwang,Yewon Cho,Chanwoong Yoon,Yein Park,Minju Song,Kyungjae Lee,Gangwoo Kim,Jaewoo Kang
机构: Korea University(韩国国立大学); University of Seoul(首尔大学); AWS AI Labs(AWS人工智能实验室); AIGEN Sciences(AIGEN科学公司)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Accepted to EMNLP 2025 Findings

点击查看摘要

[NLP-67] riCon-Fair: Triplet Contrastive Learning for Mitigating Social Bias in Pre-trained Language Models

链接: https://arxiv.org/abs/2511.00854
作者: Chong Lyu,Lin Li,Shiqing Wu,Jingling Yuan
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-68] Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies

链接: https://arxiv.org/abs/2511.00819
作者: Yuxuan Hu,Jianchao Tan,Jiaqi Zhang,Wen Zan,Pingwei Sun,Yifan Lu,Yerui Sun,Yuchen Xie,Xunliang Cai,Jing Zhang
机构: Renmin University of China (中国人民大学); Meituan (美团)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-69] GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding

链接: https://arxiv.org/abs/2511.00810
作者: Shijie Zhou,Viet Dac Lai,Hao Tan,Jihyung Kil,Wanrong Zhu,Changyou Chen,Ruiyi Zhang
机构: University at Buffalo (纽约州立大学布法罗分校); Adobe Research (Adobe 研究院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-70] GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents

链接: https://arxiv.org/abs/2511.00802
作者: Jie JW Wu,Ayanda Patrick Herlihy,Ahmad Saleem Mirza,Ali Afoud,Fatemeh Fard
机构: Michigan Technological University (密歇根理工大学); Birmingham City University (伯明翰城市大学); University of British Columbia, Kelowna (不列颠哥伦比亚大学，基隆纳分校)
类目: oftware Engineering (cs.SE); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-71] Reevaluating Self-Consistency Scaling in Multi-Agent Systems

链接: https://arxiv.org/abs/2511.00751
作者: Chiyan Loo
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 7 pages, 3 figures

点击查看摘要

[NLP-72] Erasing Ugly from the Internet: Propagation of the Beauty Myth in Text-Image Models

链接: https://arxiv.org/abs/2511.00749
作者: Tanvi Dinkar,Aiqi Jiang,Gavin Abercrombie,Ioannis Konstas
机构: Heriot Watt University (赫瑞-瓦特大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注: This is a preprint under review

点击查看摘要

[NLP-73] Do Methods to Jailbreak and Defend LLM s Generalize Across Languages?

链接: https://arxiv.org/abs/2511.00689
作者: Berk Atil,Rebecca J. Passonneau,Fred Morstatter
机构: Penn State University (宾夕法尼亚州立大学); Information Sciences Institute, USC (南加州大学信息科学研究所)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-74] Do You Know About My Nation? Investigating Multilingual Language Models Cultural Literacy Through Factual Knowledge EMNLP2025

链接: https://arxiv.org/abs/2511.00657
作者: Eshaan Tanwar,Anwoy Chatterjee,Michael Saxon,Alon Albalak,William Yang Wang,Tanmoy Chakraborty
机构: Indian Institute of Technology Delhi (印度理工学院德里分校); University of Washington (华盛顿大学); Lila Sciences; University of California, Santa Barbara (加州大学圣塔芭芭拉分校)
类目: Computation and Language (cs.CL)
备注: Accepted in EMNLP 2025. Code at: this https URL

点击查看摘要

[NLP-75] Leverag ing Multi-Agent System (MAS) and Fine-Tuned Small Language Models (SLMs) for Automated Telecom Network Troubleshooting

链接: https://arxiv.org/abs/2511.00651
作者: Chenhua Shi,Bhavika Jalli,Gregor Macdonald,John Zou,Wanlu Lei,Mridul Jain,Joji Philip
机构: Ericsson(爱立信)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Theory (cs.IT); Multiagent Systems (cs.MA); Networking and Internet Architecture (cs.NI)
备注: 6 pages, 7 figures, 1 table

点击查看摘要

[NLP-76] DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching

链接: https://arxiv.org/abs/2511.00640
作者: Zicheng Xu,Guanchu Wang,Yu-Neng Chuang,Guangyao Zheng,Alexander S. Szalay,Zirui Liu,Vladimir Braverman
机构: Johns Hopkins University (约翰霍普金斯大学); University of North Carolina at Charlotte (北卡罗来纳大学夏洛特分校); Rice University (莱斯大学); University of Minnesota (明尼苏达大学)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-77] Modeling the Construction of a Literary Archetype: The Case of the Detective Figure in French Literature

链接: https://arxiv.org/abs/2511.00627
作者: Jean Barré,Olga Seminck,Antoine Bourgois,Thierry Poibeau
机构: 未知
类目: Computation and Language (cs.CL)
备注: 19 pages, 2 tables, 5 figures Conference Computational Humanities Research 2025

点击查看摘要

[NLP-78] Certain but not Probable? Differentiating Certainty from Probability in LLM Token Outputs for Probabilistic Scenarios EMNLP2025

链接: https://arxiv.org/abs/2511.00620
作者: Autumn Toney-Wails,Ryan Wails
机构: SciTech Strategies, Inc.(SciTech策略公司); Georgetown University (乔治城大学)
类目: Computation and Language (cs.CL)
备注: To appear at the Second Workshop on Uncertainty-Aware NLP @EMNLP 2025 (UncertaiNLP '25)

点击查看摘要

[NLP-79] Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering

链接: https://arxiv.org/abs/2511.00617
作者: Eric Bigelow,Daniel Wurgaft,YingQiao Wang,Noah Goodman,Tomer Ullman,Hidenori Tanaka,Ekdeep Singh Lubana
机构: Goodfire AI; Harvard University (哈佛大学); NTT Research (NTT 研究所); Stanford University (斯坦福大学)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (stat.ML)
备注:

点击查看摘要

[NLP-80] SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative Decoding

链接: https://arxiv.org/abs/2511.00606
作者: Jameson Sandler,Jacob K. Christopher,Thomas Hartvigsen,Nando Fioretto
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-81] OpenSIR: Open-Ended Self-Improving Reason er

链接: https://arxiv.org/abs/2511.00602
作者: Wai-Chung Kwan,Joshua Ong Jun Leang,Pavlos Vougiouklis,Jeff Z. Pan,Marco Valentino,Pasquale Minervini
机构: University of Edinburgh (爱丁堡大学); Imperial College London (帝国理工学院); Huawei Technologies Research & Development (UK) Limited (华为技术英国研发有限公司); University of Sheffield (谢菲尔德大学); Miniml.AI (Miniml.AI)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-82] Structurally Refined Graph Transformer for Multimodal Recommendation

链接: https://arxiv.org/abs/2511.00584
作者: Ke Shi,Yan Zhang,Miao Zhang,Lifan Chen,Jiali Yi,Kui Xiao,Xiaoju Hou,Zhifei Li
机构: Hubei University (湖北大学); Guangdong Industry Polytechnic University (广东工业大学)
类目: Information Retrieval (cs.IR); Computation and Language (cs.CL)
备注: Comment: 13 pages, 7 figures, accepted by IEEE Transactions on Multimedia 2025

点击查看摘要

[NLP-83] FlashEVA: Accelerating LLM inference via Efficient Attention

链接: https://arxiv.org/abs/2511.00576
作者: Juan Gabriel Kostelec,Qinghai Guo
机构: Huawei Zurich Research Center (华为瑞士研究中心); Huawei ACS Lab (华为人工智能与计算科学实验室)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Technical Report

点击查看摘要

[NLP-84] Friend or Foe: How LLM s Safety Mind Gets Fooled by Intent Shift Attack

链接: https://arxiv.org/abs/2511.00556
作者: Peng Ding,Jun Kuang,Wen Sun,Zongyu Wang,Xuezhi Cao,Xunliang Cai,Jiajun Chen,Shujian Huang
机构: Nanjing University (南京大学); Meituan Inc. (美团公司)
类目: Computation and Language (cs.CL)
备注: Preprint, 14 pages, 5 figures, 7 tables

点击查看摘要

[NLP-85] Multi-refined Feature Enhanced Sentiment Analysis Using Contextual Instruction

链接: https://arxiv.org/abs/2511.00537
作者: Peter Atandoh,Jie Zou,Weikang Guo,Jiwei Wei,Zheng Wang
机构: University of Electronic Science and Technology of China (电子科技大学); Southwestern University of Finance and Economics (西南财经大学); Tongji University (同济大学)
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-86] Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions Self-Knowingly

链接: https://arxiv.org/abs/2511.00536
作者: Wenya Xie,Shaochen(Henry)Zhong,Hoang Anh Duy Le,Zhaozhuo Xu,Jianwen Xie,Zirui Liu
机构: University of Minnesota (明尼苏达大学); Rice University (莱斯大学); Stevens Institute of Technology (史蒂文斯理工学院); Lambda, Inc (Lambda公司)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-87] Reasoning Planning for Language Models

链接: https://arxiv.org/abs/2511.00521
作者: Bao Nguyen,Hieu Trung Nguyen,Ruifeng She,Xiaojin Fu,Viet Anh Nguyen
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 29 pages, 5 figures

点击查看摘要

[NLP-88] Exploring and Mitigating Gender Bias in Encoder-Based Transformer Models

链接: https://arxiv.org/abs/2511.00519
作者: Ariyan Hossain,Khondokar Mohammad Ahanaf Hannan,Rakinul Haque,Nowreen Tarannum Rafa,Humayra Musarrat,Shoaib Ahmed Dipu,Farig Yousuf Sadeque
机构: BRAC University (BRAC大学)
类目: Computation and Language (cs.CL)
备注: 25 pages, 20 figures

点击查看摘要

[NLP-89] Fine-Tuning DialoGPT on Common Diseases in Rural Nepal for Medical Conversations

链接: https://arxiv.org/abs/2511.00514
作者: Birat Poudel,Satyam Ghimire,Er. Prakash Chandra Prasad
机构: 未知
类目: Computation and Language (cs.CL)
备注: 6 pages, 6 figures, 3 tables

点击查看摘要

[NLP-90] Zero-RAG : Towards Retrieval-Augmented Generation with Zero Redundant Knowledge

链接: https://arxiv.org/abs/2511.00505
作者: Qi Luo,Xiaonan Li,Junqi Dai,Shuang Cheng,Xipeng Qiu
机构: Fudan University (复旦大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-91] oM: Leverag ing Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models EMNLP2025

链接: https://arxiv.org/abs/2511.00489
作者: Jiani Guo,Zuchao Li,Jie Wu,Qianren Wang,Yun Li,Lefei Zhang,Hai Zhao,Yujiu Yang
机构: Wuhan University (武汉大学); Tsinghua University (清华大学); Shanghai Huawei Technologies (上海华为技术有限公司); Cognitive AI Lab; Shanghai Jiao Tong University (上海交通大学)
类目: Computation and Language (cs.CL)
备注: EMNLP 2025 Main Conference

点击查看摘要

[NLP-92] textttReMind: Understanding Deductive Code Reasoning in LLM s

链接: https://arxiv.org/abs/2511.00488
作者: Jun Gao,Yun Peng,Xiaoxue Ren
机构: Zhejiang University (浙江大学); The Chinese University of Hong Kong (香港中文大学)
类目: Programming Languages (cs.PL); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-93] With Privacy Size Matters: On the Importance of Dataset Size in Differentially Private Text Rewriting AACL2025

链接: https://arxiv.org/abs/2511.00487
作者: Stephen Meisenbacher,Florian Matthes
机构: Technical University of Munich (慕尼黑工业大学)
类目: Computation and Language (cs.CL)
备注: 11 pages, 1 figure, 5 tables. Accepted to IJCNLP-AACL 2025 (Main)

点击查看摘要

[NLP-94] Leverag ing the Cross-Domain Cross-Linguistic Corpus for Low Resource NMT: A Case Study On Bhili-Hindi-English Parallel Corpus EMNLP2025

链接: https://arxiv.org/abs/2511.00486
作者: Pooja Singh,Shashwat Bhardwaj,Vaibhav Sharma,Sandeep Kumar
机构: Indian Institute of Technology Delhi (印度理工学院德里分校)
类目: Computation and Language (cs.CL)
备注: Accepted in EMNLP 2025

点击查看摘要

[NLP-95] Remembering Unequally: Global and Disciplinary Bias in LLM -Generated Co-Authorship Networks

链接: https://arxiv.org/abs/2511.00476
作者: Ghazal Kalhor,Afra Mashhadi
机构: University of Tehran (德黑兰大学); University of Washington (华盛顿大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-96] G2: Guided Generation for Enhanced Output Diversity in LLM s EMNLP2025

链接: https://arxiv.org/abs/2511.00432
作者: Zhiwen Ruan,Yixia Li,Yefeng Liu,Yun Chen,Weihua Luo,Peng Li,Yang Liu,Guanhua Chen
机构: Southern University of Science and Technology (南方科技大学); Tsinghua University (清华大学); Shanghai University of Finance and Economics (上海财经大学); Alibaba International Digital Commerce (阿里巴巴国际数字商业)
类目: Computation and Language (cs.CL)
备注: EMNLP 2025

点击查看摘要

[NLP-97] MedRECT: A Medical Reasoning Benchmark for Error Correction in Clinical Texts

链接: https://arxiv.org/abs/2511.00421
作者: Naoto Iwase,Hiroki Okuyama,Junichiro Iwasawa
机构: Preferred Networks, Inc., Tokyo, Japan; School of Medicine, Nagoya University, Nagoya, Japan
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-98] PADBen: A Comprehensive Benchmark for Evaluating AI Text Detectors Against Paraphrase Attacks

链接: https://arxiv.org/abs/2511.00416
作者: Yiwei Zha,Rui Min,Shanu Sushmita
机构: Khoury College of Computer Science, Northeastern University (东北大学计算机科学学院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-99] Diverse Human Value Alignment for Large Language Models via Ethical Reasoning

链接: https://arxiv.org/abs/2511.00379
作者: Jiahao Wang,Songkai Xue,Jinghui Li,Xiaozhen Wang
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Accepted by AIES 2025, camera-ready version

点击查看摘要

[NLP-100] Reasoning Trajectories for Socratic Debugging of Student Code: From Misconceptions to Contradictions and Updated Beliefs

链接: https://arxiv.org/abs/2511.00371
作者: Erfan Al-Hossami,Razvan Bunescu
机构: University of North Carolina at Charlotte (北卡罗来纳大学夏洛特分校)
类目: Computation and Language (cs.CL); Computers and Society (cs.CY); Software Engineering (cs.SE)
备注: 25 pages, 2 tables, 13 figures

点击查看摘要

[NLP-101] Reject Only Critical Tokens: Pivot-Aware Speculative Decoding NEURIPS2025

链接: https://arxiv.org/abs/2511.00351
作者: Amir Ziashahabi,Yavuz Faruk Bakman,Duygu Nur Yaldiz,Mostafa El-Khamy,Sai Praneeth Karimireddy,Salman Avestimehr
机构: University of Southern California (南加州大学); Device Solutions Research America, Samsung Semiconductor, Inc. (三星半导体公司)
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注: Accepted at NeurIPS 2025 Efficient Reasoning Workshop

点击查看摘要

[NLP-102] LingGym: How Far Are LLM s from Thinking Like Field Linguists? EMNLP2025

链接: https://arxiv.org/abs/2511.00343
作者: Changbing Yang,Franklin Ma,Freda Shi,Jian Zhu
机构: University of British Columbia (不列颠哥伦比亚大学); University of Waterloo (滑铁卢大学); Vector Institute (向量研究所)
类目: Computation and Language (cs.CL)
备注: EMNLP 2025 Main

点击查看摘要

[NLP-103] Reversal Invariance in Autoregressive Language Models

链接: https://arxiv.org/abs/2511.00341
作者: Mihir Sahasrabudhe
机构: 未知
类目: Computation and Language (cs.CL)
备注: 7 pages, theoretical note

点击查看摘要

[NLP-104] Language Modeling With Factorization Memory

链接: https://arxiv.org/abs/2511.00315
作者: Lee Xiong,Maksim Tkachenko,Johanes Effendi,Ting Cai
机构: Rakuten Group, Inc.
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-105] Calibration Across Layers: Understanding Calibration Evolution in LLM s EMNLP2025

链接: https://arxiv.org/abs/2511.00280
作者: Abhinav Joshi,Areeb Ahmad,Ashutosh Modi
机构: Indian Institute of Technology Kanpur (印度理工学院坎普尔分校)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Accepted at EMNLP 2025 (main)

点击查看摘要

[NLP-106] LongCat-Flash-Omni Technical Report

链接: https://arxiv.org/abs/2511.00279
作者: Meituan LongCat Team,Bairui Wang,Bayan,Bin Xiao,Bo Zhang,Bolin Rong,Borun Chen,Chang Wan,Chao Zhang,Chen Huang,Chen Chen,Chen Chen,Chengxu Yang,Chengzuo Yang,Cong Han,Dandan Peng,Delian Ruan,Detai Xin,Disong Wang,Dongchao Yang,Fanfan Liu,Fengjiao Chen,Fengyu Yang,Gan Dong,Gang Huang,Gang Xu,Guanglu Wan,Guoqiang Tan,Guoqiao Yu,Haibo Qiu,Hao Lu,Hongbo Liu,Hongyu Xiang,Jiaheng Wu,Jian Yang,Jiaxing Liu,Jing Huang,Jingang Wang,Jinrui Ding,Juchao Jiang,Jun Kuang,Jun Wang,Junhui Mei,Ke Ding,Kefeng Zhang,Lei Chen,Liang Shi,Limeng Qiao,Liming Zheng,Lin Ma,Liuyang Guo,Liya Ma,Luying Sun,Man Gao,Mengshen Zhu,Miao Cao,Minliang Lin,Nuo Xu,Peng Shi,Qi Zhang,Qian Fang,Qian Wang,Qian Yang,Quanxiu Wang,Rongxiang Weng,Rongxin Guo,Ruoxuan Liang,Senbin Yang,Shanbo Xu,Shanglin Lei,Shengze Ye,Shimin Chen,Shuaiqi Chen,Shujie Hu,Shuo Li,Siqi Yang,Siyu Xu,Siyu Ren,Song Li,Songxiang Liu,Tianhao Bai,Tianye Dai,Wei Hong,Wei Wang,Weixiao Zhao,Wengang Cao,Wenlong Zhu,Wenlong He,Xi Su,Xi Nan,Xiaohan Zhao,Xiaohao Wang,Xiaoyu Zhao,Xiaoyu Wang,Xiaoyu Li,Xin Pan,Xin Chen,Xiusong Sun,Xu Xiang,Xudong Xing
机构: Meituan LongCat Team (美团长猫团队)
类目: Multimedia (cs.MM); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG); Sound (cs.SD)
备注:

点击查看摘要

[NLP-107] POSESTITCH-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation EMNLP2025

链接: https://arxiv.org/abs/2511.00270
作者: Abhinav Joshi,Vaibhav Sharma,Sanjeet Singh,Ashutosh Modi
机构: Indian Institute of Technology Kanpur (印度理工学院坎普尔分校)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Accepted at EMNLP 2025 (Main)

点击查看摘要

[NLP-108] IL-PCSR: Legal Corpus for Prior Case and Statute Retrieval EMNLP2025

链接: https://arxiv.org/abs/2511.00268
作者: Shounak Paul,Dhananjay Ghumare,Pawan Goyal,Saptarshi Ghosh,Ashutosh Modi
机构: IIT Kharagpur (印度理工学院克勒格布尔分校); IIT Kanpur (印度理工学院坎普尔分校)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG)
备注: Accepted at EMNLP 2025 (Main)

点击查看摘要

[NLP-109] Agent BnB: A Browser-Based Cybersecurity Tabletop Exercise with Large Language Model Support and Retrieval-Aligned Scaffolding

链接: https://arxiv.org/abs/2511.00265
作者: Arman Anwar,Zefang Liu
机构: 未知
类目: Computation and Language (cs.CL); Cryptography and Security (cs.CR)
备注:

点击查看摘要

[NLP-110] Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning

链接: https://arxiv.org/abs/2511.00222
作者: Marwa Abdulhai,Ryan Cheng,Donovan Clay,Tim Althoff,Sergey Levine,Natasha Jaques
机构: UC Berkeley (加州大学伯克利分校); University of Washington (华盛顿大学); Google DeepMind (谷歌深度智障)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-111] Advancing Cognitive Science with LLM s

链接: https://arxiv.org/abs/2511.00206
作者: Dirk U. Wulff,Rui Mata
机构: Max Planck Institute for Biological Cybernetics (马普所生物控制论研究所); University of Basel (巴塞尔大学)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-112] raining LLM s Beyond Next Token Prediction - Filling the Mutual Information Gap

链接: https://arxiv.org/abs/2511.00198
作者: Chun-Hao Yang,Bo-Han Feng,Tzu-Yuan Lai,Yan Yu Chen,Yin-Kai Dean Huang,Shou-De Lin
机构: National Taiwan University (国立台湾大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-113] ParaScopes: What do Language Models Activations Encode About Future Text?

链接: https://arxiv.org/abs/2511.00180
作者: Nicky Pochinkov,Yulia Volkova,Anna Vasileva,Sai V R Chereddy
机构: 未知
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: Main paper: 9 pages, 10 figures. Total 24 pages

点击查看摘要

[NLP-114] Can SAEs reveal and mitigate racial biases of LLM s in healthcare?

链接: https://arxiv.org/abs/2511.00177
作者: Hiba Ahsan,Byron C. Wallace
机构: Northeastern University (东北大学)
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-115] Real-time and Zero-footprint Bag of Synthetic Syllables Algorithm for E-mail Spam Detection Using Subject Line and Short Text Fields

链接: https://arxiv.org/abs/2511.00118
作者: Stanislav Selitskiy
机构: 未知
类目: Cryptography and Security (cs.CR); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-116] Cognitive Alignment in Personality Reasoning : Leverag ing Prototype Theory for MBTI Inference

链接: https://arxiv.org/abs/2511.00115
作者: Haoyuan Li,Yuanbo Tong,Yuchen Li,Zirui Wang,Chunhou Liu,Jiamou Liu
机构: The University of Auckland (奥克兰大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-117] Wayfinding through the AI wilderness: Mapping rhetorics of ChatGPT prompt writing on X (formerly Twitter) to promote critical AI literacies

链接: https://arxiv.org/abs/2511.00106
作者: Anuj Gupta,Ann Shivers-McNair
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC)
备注: Published in the journal Computers and Composition, Issue 74 (2024)

点击查看摘要

[NLP-118] QuantumBench: A Benchmark for Quantum Problem Solving

链接: https://arxiv.org/abs/2511.00092
作者: Shunya Minami,Tatsuya Ishigaki,Ikko Hamamura,Taku Mikuriya,Youmi Ma,Naoaki Okazaki,Hiroya Takamura,Yohichi Suzuki,Tadashi Kadowaki
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Quantum Physics (quant-ph)
备注: 11 pages, 8 figures

点击查看摘要

[NLP-119] Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph

链接: https://arxiv.org/abs/2511.00086
作者: Fali Wang,Jihai Chen,Shuhua Yang,Runxue Bao,Tianxiang Zhao,Zhiwei Zhang,Xianfeng Tang,Hui Liu,Qi He,Suhang Wang
机构: The Pennsylvania State University (宾夕法尼亚州立大学); University of Pittsburgh (匹兹堡大学); Amazon (亚马逊); Microsoft (微软)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Under review

点击查看摘要

[NLP-120] Chitchat with AI: Understand the supply chain carbon disclosure of companies worldwide through Large Language Model

链接: https://arxiv.org/abs/2511.00024
作者: Haotian Hang,Yueyang Shen,Vicky Zhu,Jose Cruz,Michelle Li
机构: University of Southern California (南加州大学); University of Michigan (密歇根大学); Babson College (巴布森学院); University of Connecticut (康涅狄格大学)
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Applications (stat.AP)
备注:

点击查看摘要

[NLP-121] Multimodal Detection of Fake Reviews using BERT and ResNet-50

链接: https://arxiv.org/abs/2511.00020
作者: Suhasnadh Reddy Veluru,Sai Teja Erukude,Viswa Chaitanya Marella
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
备注: Published in IEEE

点击查看摘要

[NLP-122] PlotCraft: Pushing the Limits of LLM s for Complex and Interactive Data Visualization

链接: https://arxiv.org/abs/2511.00010
作者: Jiajun Zhang,Jianke Zhang,Zeyu Cui,Jiaxi Yang,Lei Zhang,Binyuan Hui,Qiang Liu,Zilei Wang,Liang Wang,Junyang Lin
机构: USTC (中国科学技术大学); THU (清华大学); Qwen Team, Alibaba Inc. (通义实验室，阿里巴巴集团); CASIA (中国科学院自动化研究所); SIAT (深圳先进技术研究院)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-123] Multimodal Learning with Augmentation Techniques for Natural Disaster Assessment

链接: https://arxiv.org/abs/2511.00004
作者: Adrian-Dinu Urse,Dumitru-Clementin Cercel,Florin Pop
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at 2025 IEEE 21st International Conference on Intelligent Computer Communication and Processing (ICCP 2025)

点击查看摘要

[NLP-124] A Proof of Learning Rate Transfer under μP

链接: https://arxiv.org/abs/2511.01734
作者: Soufiane Hayou
机构: Johns Hopkins University (约翰霍普金斯大学)
类目: Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: 23 pages

点击查看摘要

[NLP-125] Novelty and Impact of Economics Papers

链接: https://arxiv.org/abs/2511.01211
作者: Chaofeng Wu
机构: Northwestern University (西北大学)
类目: General Economics (econ.GN); Computational Engineering, Finance, and Science (cs.CE); Computation and Language (cs.CL); Digital Libraries (cs.DL)
备注:

点击查看摘要

[NLP-126] MULTI-Bench: A Multi-Turn Interactive Benchmark for Assessing Emotional Intelligence ability of Spoken Dialogue Models ICASSP2026

链接: https://arxiv.org/abs/2511.00850
作者: Yayue Deng,Guoqiang Hu,Haiyang Sun,Xiangyu Zhang,Haoyang Zhang,Fei Tian,Xuerui Yang,Gang Yu,Eng Siong Chng
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: Submitted to ICASSP 2026

点击查看摘要

计算机视觉

[CV-0] IR-Bench: A Comprehensive Benchmark for Agent ic Thinking-with-Images Reasoning

链接: https://arxiv.org/abs/2511.01833
作者: Ming Li,Jike Zhong,Shitian Zhao,Haoquan Zhang,Shaoheng Lin,Yuxiang Lai,Wei Chen,Konstantinos Psounis,Kaipeng Zhang
机构: Shanghai AI Laboratory (上海人工智能实验室); University of Southern California (南加州大学); Emory University (埃默里大学); Chinese University of Hong Kong (香港中文大学); Rice University (莱斯大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Preprint

点击查看摘要

[CV-1] SciTextures: Collecting and Connecting Visual Patterns Models and Code Across Science and Art

链接: https://arxiv.org/abs/2511.01817
作者: Sagi Eppel,Alona Strugatski
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-2] PROPEX-RAG : Enhanced GraphRAG using Prompt-Driven Prompt Execution

链接: https://arxiv.org/abs/2511.01802
作者: Tejas Sarnaik,Manan Shah,Ravi Hegde
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted in PReMI 2025

点击查看摘要

[CV-3] Fractional Diffusion Bridge Models NEURIPS2025

链接: https://arxiv.org/abs/2511.01795
作者: Gabriel Nobis,Maximilian Springenberg,Arina Belova,Rembert Daems,Christoph Knochenhauer,Manfred Opper,Tolga Birdal,Wojciech Samek
机构: Fraunhofer HHI; Ghent University–imec; FlandersMake–MIRO; Technical University of Munich; Technical University of Berlin; University of Potsdam; University of Birmingham; Imperial College London; Wojciech Samek†{}^{\ \dagger}
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO); Machine Learning (stat.ML)
备注: To appear in NeurIPS 2025 proceedings. This version includes post-camera-ready revisions

点击查看摘要

[CV-4] How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment

链接: https://arxiv.org/abs/2511.01775
作者: Zhen Chen,Qing Xu,Jinlin Wu,Biao Yang,Yuhao Zhai,Geng Guo,Jing Zhang,Yinlu Ding,Nassir Navab,Jiebo Luo
机构: 未知
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-5] UniLION: Towards Unified Autonomous Driving Model with Linear Group RNNs

链接: https://arxiv.org/abs/2511.01768
作者: Zhe Liu,Jinghua Hou,Xiaoqing Ye,Jingdong Wang,Hengshuang Zhao,Xiang Bai
机构: Huazhong University of Science and Technology (华中科技大学); The University of Hong Kong (香港大学); Baidu Inc. (百度)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-6] Wonder3D: Cross-domain Diffusion for High-fidelity 3D Generation from a Single Image

【速读】：该论文旨在解决单视角图像到高保真纹理网格生成任务中普遍存在的效率低、几何一致性差和细节缺失问题。现有基于Score Distillation Sampling (SDS) 的方法虽能利用扩散模型先验恢复3D结构，但优化过程耗时且结果不稳定；而直接通过快速网络推理的方法则常因缺乏几何细节导致质量不高。其解决方案的关键在于提出一种跨域扩散模型（cross-domain diffusion model），能够同时生成多视角法向量图（normal maps）与对应的颜色图像，并引入多视角跨域注意力机制以增强视图间及模态间的信息交互，从而提升重建的一致性与完整性；进一步设计了一种级联式三维网格提取算法（cascaded 3D mesh extraction algorithm），在粗到精的策略下仅需约3分钟即可从多视角2D表示中生成高质量表面，显著提升了效率与精度。

链接: https://arxiv.org/abs/2511.01767
作者: Yuxiao Yang,Xiao-Xiao Long,Zhiyang Dou,Cheng Lin,Yuan Liu,Qingsong Yan,Yuexin Ma,Haoqian Wang,Zhiqiang Wu,Wei Yin
机构: Tsinghua University (清华大学); Nanjing University (南京大学); Wright State University (赖特州立大学); Horizon Robotics ( horizon 机器人); University of Hong Kong (香港大学); Macau University of Science and Technology (澳门科技大学); Hong Kong University of Science and Technology (香港科技大学); Wuhan University (武汉大学); ShanghaiTech University (上海科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 21 pages, 19 figures, accepted by TPAMI

点击查看摘要

Abstract:In this work, we introduce \textbfWonder3D++, a novel method for efficiently generating high-fidelity textured meshes from single-view images. Recent methods based on Score Distillation Sampling (SDS) have shown the potential to recover 3D geometry from 2D diffusion priors, but they typically suffer from time-consuming per-shape optimization and inconsistent geometry. In contrast, certain works directly produce 3D information via fast network inferences, but their results are often of low quality and lack geometric details. To holistically improve the quality, consistency, and efficiency of single-view reconstruction tasks, we propose a cross-domain diffusion model that generates multi-view normal maps and the corresponding color images. To ensure the consistency of generation, we employ a multi-view cross-domain attention mechanism that facilitates information exchange across views and modalities. Lastly, we introduce a cascaded 3D mesh extraction algorithm that drives high-quality surfaces from the multi-view 2D representations in only about 3 minute in a coarse-to-fine manner. Our extensive evaluations demonstrate that our method achieves high-quality reconstruction results, robust generalization, and good efficiency compared to prior works. Code available at this https URL.
zh

[CV-7] HGFreNet: Hop-hybrid GraphFomer for 3D Human Pose Estimation with Trajectory Consistency in Frequency Domain

【速读】：该论文旨在解决单目视频中2D到3D人体姿态提升（2D-to-3D human pose lifting）问题，其核心挑战在于由2D姿态估计带来的深度模糊性和误差导致的3D轨迹不一致性。现有方法通常仅在时间域上限制相邻帧间的抖动，忽略了骨骼关节运动的全局时空相关性。解决方案的关键在于提出一种新型图Transformer架构HGFreNet，其包含两个核心组件：一是跳数混合图注意力（Hop-Hybrid Graph Attention, HGA）模块，通过将每个关节的k跳邻居聚合为混合组并引入注意力机制，显著扩展感受野并建模全局空间关联；二是频域轨迹一致性约束机制，利用Transformer编码器捕捉全局时间相关性，并在频域中约束3D姿态轨迹的一致性，从而提升时序稳定性与位置精度。实验表明，该方法在Human3.6M和MPI-INF-3DHP两个标准数据集上均优于当前最先进（SOTA）方法。

链接: https://arxiv.org/abs/2511.01756
作者: Kai Zhai,Ziyan Huang,Qiang Nie,Xiang Li,Bo Ouyang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

Abstract:2D-to-3D human pose lifting is a fundamental challenge for 3D human pose estimation in monocular video, where graph convolutional networks (GCNs) and attention mechanisms have proven to be inherently suitable for encoding the spatial-temporal correlations of skeletal joints. However, depth ambiguity and errors in 2D pose estimation lead to incoherence in the 3D trajectory. Previous studies have attempted to restrict jitters in the time domain, for instance, by constraining the differences between adjacent frames while neglecting the global spatial-temporal correlations of skeletal joint motion. To tackle this problem, we design HGFreNet, a novel GraphFormer architecture with hop-hybrid feature aggregation and 3D trajectory consistency in the frequency domain. Specifically, we propose a hop-hybrid graph attention (HGA) module and a Transformer encoder to model global joint spatial-temporal correlations. The HGA module groups all k -hop neighbors of a skeletal joint into a hybrid group to enlarge the receptive field and applies the attention mechanism to discover the latent correlations of these groups globally. We then exploit global temporal correlations by constraining trajectory consistency in the frequency domain. To provide 3D information for depth inference across frames and maintain coherence over time, a preliminary network is applied to estimate the 3D pose. Extensive experiments were conducted on two standard benchmark datasets: Human3.6M and MPI-INF-3DHP. The results demonstrate that the proposed HGFreNet outperforms state-of-the-art (SOTA) methods in terms of positional accuracy and temporal consistency.
zh

[CV-8] 3EED: Ground Everything Everywhere in 3D NEURIPS2025

链接: https://arxiv.org/abs/2511.01755
作者: Rong Li,Yuhao Dong,Tianshuai Hu,Ao Liang,Youquan Liu,Dongyue Lu,Liang Pan,Lingdong Kong,Junwei Liang,Ziwei Liu
机构: HKUST(GZ)(香港科技大学（广州）); NTU(南洋理工大学); HKUST(香港科技大学); NUS(新加坡国立大学); FDU(复旦大学); Shanghai AI Laboratory(上海人工智能实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: NeurIPS 2025 DB Track; 29 pages, 17 figures, 10 tables; Project Page at this https URL

点击查看摘要

[CV-9] CGF-DETR: Cross-Gated Fusion DETR for Enhanced Pneumonia Detection in Chest X-rays

链接: https://arxiv.org/abs/2511.01730
作者: Yefeng Wu,Yucheng Song,Ling Wu,Shan Wan,Yecheng Zhao
机构: Anhui University (安徽大学); Wannan Medical College (皖南医学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-10] oward Strategy Identification and Subtask Decomposition In Task Exploration

链接: https://arxiv.org/abs/2511.01728
作者: Tom Odem
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-11] Probabilistic Robustness for Free? Revisiting Training via a Benchmark

【速读】：该论文旨在解决当前生成式 AI（Generative AI）模型在面对随机扰动时的鲁棒性评估与提升方法缺乏系统性比较的问题。现有研究多聚焦于对抗鲁棒性（Adversarial Robustness, AR），而概率鲁棒性（Probabilistic Robustness, PR）虽被视为更贴近实际应用的补充指标，但针对PR的训练方法仍处于探索阶段，且存在评价标准不统一、与强对抗训练（Adversarial Training, AT）基线对比不足、以及缺乏通用框架衡量泛化能力等局限。为此，作者提出了PRBench——首个专门用于评估不同鲁棒性训练方法对PR提升效果的基准平台，其关键在于构建了一个包含清洁准确率、PR性能、AR性能、训练效率及泛化误差（Generalization Error, GE）在内的多维评测体系，并通过理论分析揭示了PR性能的泛化特性。实验表明，AT方法在多种超参数下更擅长同时提升AR和PR，而PR针对性训练方法则具有更低的GE和更高的清洁准确率，为后续研究提供了可复现、可比较的标准化评估路径。

链接: https://arxiv.org/abs/2511.01724
作者: Yi Zhang,Zheng Wang,Chen Zhen,Wenjie Ruan,Qing Guo,Siddartha Khastgir,Carsten Maple,Xingyu Zhao
机构: WMG, University of Warwick (华威大学WMG学院); Department of Computer Science, University of Liverpool (利物浦大学计算机科学系); Center for Frontier AI Research, A*STAR, Singapore (新加坡科技研究局前沿人工智能研究中心); School of Computing, National University of Singapore (新加坡国立大学计算机学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

Abstract:Deep learning models are notoriously vulnerable to imperceptible perturbations. Most existing research centers on adversarial robustness (AR), which evaluates models under worst-case scenarios by examining the existence of deterministic adversarial examples (AEs). In contrast, probabilistic robustness (PR) adopts a statistical perspective, measuring the probability that predictions remain correct under stochastic perturbations. While PR is widely regarded as a practical complement to AR, dedicated training methods for improving PR are still relatively underexplored, albeit with emerging progress. Among the few PR-targeted training methods, we identify three limitations: i non-comparable evaluation protocols; ii limited comparisons to strong AT baselines despite anecdotal PR gains from AT; and iii no unified framework to compare the generalization of these methods. Thus, we introduce PRBench, the first benchmark dedicated to evaluating improvements in PR achieved by different robustness training methods. PRBench empirically compares most common AT and PR-targeted training methods using a comprehensive set of metrics, including clean accuracy, PR and AR performance, training efficiency, and generalization error (GE). We also provide theoretical analysis on the GE of PR performance across different training methods. Main findings revealed by PRBench include: AT methods are more versatile than PR-targeted training methods in terms of improving both AR and PR performance across diverse hyperparameter settings, while PR-targeted training methods consistently yield lower GE and higher clean accuracy. A leaderboard comprising 222 trained models across 7 datasets and 10 model architectures is publicly available at this https URL.
zh

[CV-12] Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process

链接: https://arxiv.org/abs/2511.01718
作者: Jiayi Chen,Wenxuan Song,Pengxiang Ding,Ziyang Zhou,Han Zhao,Feilong Tang,Donglin Wang,Haoang Li
机构: HKUST(GZ); Westlake University; Zhejiang University; Monash University
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-13] Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond

链接: https://arxiv.org/abs/2511.01704
作者: Xin Qiao,Matteo Poggi,Xing Wei,Pengchao Deng,Yanhui Zhou,Stefano Mattoccia
机构: Xi’an Jiaotong University (西安交通大学); University of Bologna (博洛尼亚大学); Anyang Institute of Technology (安阳工学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-14] Progressive Translation of HE to IHC with Enhanced Structural Fidelity

链接: https://arxiv.org/abs/2511.01698
作者: Yuhang Kang,Ziyu Su,Tianyang Wang,Zaibo Li,Wei Chen,Muhammad Khalid Khan Niazi
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-15] UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback NEURIPS2025

链接: https://arxiv.org/abs/2511.01678
作者: Ropeway Liu,Hangjie Yuan,Bo Dong,Jiazheng Xing,Jinwang Wang,Rui Zhao,Yan Xing,Weihua Chen,Fan Wang
机构: Zhejiang University (浙江大学); DAMO Academy (达摩院); Alibaba Group (阿里巴巴集团); Hupan Lab (湖畔实验室); National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: NeurIPS 2025

点击查看摘要

[CV-16] Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward

链接: https://arxiv.org/abs/2511.01645
作者: Xiaogang Xu,Ruihang Chu,Jian Wang,Kun Zhou,Wenjie Shu,Harry Yang,Ser-Nam Lim,Hao Chen,Liang Lin
机构: The Chinese University of Hong Kong (香港中文大学); Tsinghua University (清华大学); Snap Research; Shenzhen University (深圳大学); HKUST (香港科技大学); University of Central Florida (中佛罗里达大学); UC Davis (加州大学戴维斯分校); Sun Yat-Sen University (中山大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-17] Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers

链接: https://arxiv.org/abs/2511.01617
作者: Mohamed Eltahir,Ali Habibullah,Lama Ayash,Tanveer Hussain,Naeemullah Khan
机构: King Abdullah University of Science and Technology (KAUST); King Khalid University (KKU); Edge Hill University
类目: Computer Vision and Pattern Recognition (cs.CV); Information Retrieval (cs.IR)
备注:

点击查看摘要

[CV-18] Benchmark-Ready 3D Anatomical Shape Classification MICCAI2025

【速读】：该论文旨在解决医学3D解剖形状分类中因网格数据复杂性和缺乏标准化基准测试而导致的进展受限问题，核心挑战在于如何实现高效、结构保持的图下采样以及在低标注数据条件下提升模型性能。其解决方案的关键是提出一种非学习型的网格下采样算子——预计算结构池化（Precomputed Structural Pooling, PSPooling），该方法基于几何邻近性预先计算节点对应关系，支持并行化且可逆的池化与上采样操作，并保证支撑结构的完整性；相比选择式方法避免了稀疏性和重建误差，也克服了边收缩方法的串行开销，特别适用于高分辨率医学网格。结合自监督图自动编码器，PSPooling显著提升了低标签场景下的重建保真度和分类准确率，为医学3D形状学习建立了强基线。

链接: https://arxiv.org/abs/2511.01613
作者: Tomáš Krsička,Tibor Kubík
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Shape in Medical Imaging, ShapeMI 2025, Held in Conjunction with MICCAI 2025

点击查看摘要

Abstract:Progress in anatomical 3D shape classification is limited by the complexity of mesh data and the lack of standardized benchmarks, highlighting the need for robust learning methods and reproducible evaluation. We introduce two key steps toward clinically and benchmark-ready anatomical shape classification via self-supervised graph autoencoding. We propose Precomputed Structural Pooling (PSPooling), a non-learnable mesh pooling operator designed for efficient and structure-preserving graph coarsening in 3D anatomical shape analysis. PSPooling precomputes node correspondence sets based on geometric proximity, enabling parallelizable and reversible pooling and unpooling operations with guaranteed support structure. This design avoids the sparsity and reconstruction issues of selection-based methods and the sequential overhead of edge contraction approaches, making it particularly suitable for high-resolution medical meshes. To demonstrate its effectiveness, we integrate PSPooling into a self-supervised graph autoencoder that learns anatomy-aware representations from unlabeled surface meshes. We evaluate the downstream benefits on MedShapeNet19, a new curated benchmark dataset we derive from MedShapeNet, consisting of 19 anatomical classes with standardized training, validation, and test splits. Experiments show that PSPooling significantly improves reconstruction fidelity and classification accuracy in low-label regimes, establishing a strong baseline for medical 3D shape learning. We hope that MedShapeNet19 will serve as a widely adopted benchmark for anatomical shape classification and further research in medical 3D shape analysis. Access the complete codebase, model weights, and dataset information here: this https URL.
zh

[CV-19] DINO-MX: A Modular Flexible Framework for Self-Supervised Learning

【速读】：该论文旨在解决现有视觉基础模型（Vision Foundation Models, VFM）训练流程中存在的灵活性不足、领域特定性强以及计算成本高等问题，从而限制其在不同应用场景和资源条件下的可扩展性与实用性。解决方案的关键在于提出一个模块化且可扩展的训练框架 DINO-MX，该框架整合了 DINO、DINOv2 和 DINOv3 的核心思想，并基于配置驱动的设计实现了多种 Transformer 架构的支持与灵活组合；同时引入低秩适应（LoRA）、层冻结（layer freezing）、知识蒸馏（knowledge distillation）等高效训练策略，并兼容 Hugging Face 生态系统及分布式训练（DDP 与 FSDP），显著降低计算开销并提升模型适配能力，且通过标签引导的数据增强方法实现无需额外检测或分割头即可优化注意力定位的可解释性功能。

链接: https://arxiv.org/abs/2511.01610
作者: Mahmut Selman Gokmen,Cody Bumgardner
机构: University of Kentucky (肯塔基大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

Abstract:Vision Foundation Models (VFMs) have advanced representation learning through self-supervised methods. However, existing training pipelines are often inflexible, domain-specific, or computationally expensive, which limits their usability across different domains and resource settings. DINO-MX is a modular and extensible training framework that combines the core principles of DINO, DINOv2 and DINOv3 within a unified configuration-driven system. It supports a variety of transformer-based architectures and is fully compatible with the Hugging Face ecosystem. The framework includes multiple training strategies such as low-rank adaptation (LoRA), layer freezing, and knowledge distillation, along with support for distributed training through both Distributed Data Parallel (DDP) and Fully Sharded Data Parallel (FSDP). DINO-MX is designed to work with both natural and specialized data types, including single- and multi-channel images. Experimental results on diverse datasets show that DINO-MX achieves competitive performance while significantly reducing computational costs. Additionally, it offers interpretability tools and a label-guided data augmentation method that improves attention-based localization without the need for extra detection or segmentation heads. DINO-MX provides a reproducible and scalable foundation for developing, adapting, and benchmarking self-supervised vision models across a range of research and real-world applications.
zh

[CV-20] Lite ENSAM: a lightweight cancer segmentation model for 3D Computed Tomography

链接: https://arxiv.org/abs/2511.01600
作者: Agnar Martin Bjørnstad,Elias Stenhede,Arian Ranjbar
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-21] MARS: Multi-Agent Robotic System with Multimodal Large Language Models for Assistive Intelligence

【速读】：该论文旨在解决现有智能助残机器人系统在风险感知规划、用户个性化适配以及将语言指令转化为可执行技能方面的不足，尤其是在杂乱家庭环境中的落地难题。解决方案的关键在于提出MARS（Multi-Agent Robotic System），一个基于多模态大语言模型（Multimodal Large Language Models, MLLMs）的多智能体架构，集成视觉感知、风险评估、任务规划与执行评估四个专用代理，通过跨模态理解与分层多智能体决策协同，实现动态室内环境中自适应、风险敏感且个性化的辅助决策与执行能力。

链接: https://arxiv.org/abs/2511.01594
作者: Renjun Gao,Peiyan Zhong
机构: Mustard University (澳门城市大学)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注: 3 figures, 1 table; under review at Multimedia Systems (Springer)

点击查看摘要

Abstract:Multimodal large language models (MLLMs) have shown remarkable capabilities in cross-modal understanding and reasoning, offering new opportunities for intelligent assistive systems, yet existing systems still struggle with risk-aware planning, user personalization, and grounding language plans into executable skills in cluttered homes. We introduce MARS - a Multi-Agent Robotic System powered by MLLMs for assistive intelligence and designed for smart home robots supporting people with disabilities. The system integrates four agents: a visual perception agent for extracting semantic and spatial features from environment images, a risk assessment agent for identifying and prioritizing hazards, a planning agent for generating executable action sequences, and an evaluation agent for iterative optimization. By combining multimodal perception with hierarchical multi-agent decision-making, the framework enables adaptive, risk-aware, and personalized assistance in dynamic indoor environments. Experiments on multiple datasets demonstrate the superior overall performance of the proposed system in risk-aware planning and coordinated multi-agent execution compared with state-of-the-art multimodal models. The proposed approach also highlights the potential of collaborative AI for practical assistive scenarios and provides a generalizable methodology for deploying MLLM-enabled multi-agent systems in real-world environments.
zh

[CV-22] Wave-Particle (Continuous-Discrete) Dualistic Visual Tokenization for Unified Understanding and Generation

链接: https://arxiv.org/abs/2511.01593
作者: Yizhu Chen,Chen Ju,Zhicheng Wang,Shuai Xiao,Xu Chen,Jinsong Lan,Xiaoyong Zhu,Ying Chen
机构: Zhejiang University (浙江大学); Alibaba Group (阿里巴巴集团); Peking University (北京大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-23] Explore More Learn Better: Parallel MLLM Embeddings under Mutual Information Minimization

【速读】：该论文旨在解决当前多模态嵌入模型（Multimodal Embedding Models）在架构设计上的局限性问题，即现有方法普遍采用单输入、单一嵌入、对比监督（Single Input, Singular Embedding, Contrastive Supervision, SSC）范式，导致丰富多样的输入信息被压缩为单一的嵌入表示，无法充分利用多模态大语言模型（MLLMs）的潜力。其解决方案的关键在于提出一种并行解耦框架（Parallel Decoupling Framework, PDF），通过利用MLLM固有的可引导性（steerability），即在明确指令下生成差异化响应的能力，对共享的MLLM骨干网络施加不同的可学习前缀（learnable prefixes），从而为同一输入生成多个并行路径以获得多样化的嵌入表示；同时引入互信息最小化（Mutual Information Minimization, MIM）作为显式约束，并结合每路径的对比监督，实现嵌入空间的语义覆盖广度与一致性之间的平衡，最终在推理阶段仅需一次前向传播即可获取高质量嵌入，且计算开销极低。

链接: https://arxiv.org/abs/2511.01588
作者: Zhicheng Wang,Chen Ju,Xu Chen,Shuai Xiao,Jinsong Lan,Xiaoyong Zhu,Ying Chen,Zhiguo Cao
机构: Zhejiang University (浙江大学); Alibaba Group (阿里巴巴集团); Huazhong University of Science and Technology (华中科技大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

Abstract:Embedding models are a cornerstone of modern AI. Driven by Multimodal Large Language Models (MLLMs), they have made great progress in architecture and data curation, while the holistic paradigm is still limited to SSC, i.e., single input, singular embedding, contrastive supervision, which collapses rich, multifaceted inputs into monolithic embeddings and fails to fully exploit MLLM capabilities. In this paper, we tailor one Parallel Decoupling Framework (PDF) for multimodal embedding learning, by utilizing the proprietary steerability of MLLMs, i.e., their ability to flexibly generate quite differentiated response under explicit instructions. Concretely, PDF conditions a shared MLLM backbone on distinct, learnable prefixes to roll out multiple parallel paths for one input, then relies on these paths to obtain parallel embeddings. To promote full parallel diversity, we employ Mutual Information Minimization (MIM) as an explicit constraint, coupled with per-path contrastive supervision to maintain semantic alignment. Such dual-objectives force PDF to yield robust semantic coverage and a generalizable embedding space. Ultimately, the remarkable embedding space are accessible at inference via one single forward pass, incurring negligible computational overhead. We instantiate PDF on multiple MLLM backbones and prove its effectiveness on MMEB benchmark. Significant gains are consistently achieved across various resolutions and model sizes, e.g., boosting the VLM2Vec-LLaVA-1.6-LR model by a remarkable +8.9% (7B), while the VLM2Vec-Qwen2VL models by +4.2% (2B) and +3.1% (7B). In terms of efficiency, our 2B model surpasses its baseline by +2.6% using only half the computational budget.
zh

[CV-24] Generative Adversarial Synthesis and Deep Feature Discrimination of Brain Tumor MRI Images

链接: https://arxiv.org/abs/2511.01574
作者: Md Sumon Ali,Muzammil Behzad
机构: King Fahd University of Petroleum and Minerals (国王法赫德石油与矿业大学); SDAIA-KFUPM Joint Research Center for Artificial Intelligence (沙特数据和人工智能局-国王法赫德石油与矿业大学人工智能联合研究中心)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pagers, 8 Figures

点击查看摘要

[CV-25] PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model

链接: https://arxiv.org/abs/2511.01571
作者: Wenqi Liang,Gan Sun,Yao He,Jiahua Dong,Suyan Dai,Ivan Laptev,Salman Khan,Yang Cong
机构: South China University of Technology (华南理工大学); Chinese Academy of Sciences (中国科学院); Mohamed bin Zayed University of Artificial Intelligence (穆罕默德·本·扎耶德人工智能大学); Australian National University (澳大利亚国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: 17pages,7 figures, 5 tabels

点击查看摘要

[CV-26] NOA: a versatile extensible tool for AI-based organoid analysis

链接: https://arxiv.org/abs/2511.01549
作者: Mikhail Konov,Lion J. Gleiter,Khoa Co,Monica Yabal,Tingying Peng
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-27] PCD-ReID: Occluded Person Re-Identification for Base Station Inspection

链接: https://arxiv.org/abs/2511.01546
作者: Ge Gao,Zishuo Gao,Hongyan Cui,Zhiyang Jia,Zhuang Luo,ChaoPeng Liu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 11 pages, 7 figures

点击查看摘要

[CV-28] Driving scenario generation and evaluation using a structured layer representation and foundational models

链接: https://arxiv.org/abs/2511.01541
作者: Arthur Hubert,Gamal Elghazaly,Raphaël Frank
机构: University of Luxembourg (卢森堡大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-29] NSYNC: Negative Synthetic Image Generation for Contrastive Training to Improve Stylized Text-To-Image Translation

链接: https://arxiv.org/abs/2511.01517
作者: Serkan Ozturk,Samet Hicsonmez,Pinar Duygulu
机构: Hacettepe University (哈切特佩大学); University of Luxembourg (卢森堡大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Under review

点击查看摘要

[CV-30] Example-Based Feature Painting on Textures

链接: https://arxiv.org/abs/2511.01513
作者: Andrei-Timotei Ardelean,Tim Weyrich
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR)
备注: "\c{opyright} 2025 Andrei-Timotei Ardelean, Tim Weyrich. This is the author’s version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in ACM Trans. Graph., Vol. 44, No. 6, this https URL

点击查看摘要

[CV-31] Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement NEURIPS2025

【速读】：该论文旨在解决低光照图像增强（Low-light Image Enhancement, LLIE）中重建保真度与跨场景泛化能力之间的平衡难题，尤其针对现有方法依赖成对的低光/正常光图像进行确定性像素映射、忽视真实环境中亮度连续变化过程而导致在缺乏正常光参考时性能下降的问题。解决方案的关键在于提出一种基于亮度感知的统计量化框架（Luminance-Aware Statistical Quantification, LASQ），将亮度过渡建模为强度坐标空间中的幂律分布，并通过分层幂函数近似实现对连续亮度层的概率采样，取代传统的确定性映射；同时设计扩散前向过程以自主发现最优亮度层间过渡路径，从而在无正常光参考的情况下实现无监督分布拟合，显著提升实际应用中的适应性和鲁棒性，且在有参考数据时亦能取得更优的域内性能与跨域泛化能力。

链接: https://arxiv.org/abs/2511.01510
作者: Derong Kong,Zhixiong Yang,Shengxi Li,Shuaifeng Zhi,Li Liu,Zhen Liu,Jingyuan Xia
机构: National University of Defense Technology (国防科技大学); Beihang University (北京航空航天大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at NeurIPS 2025

点击查看摘要

Abstract:Low-light image enhancement (LLIE) faces persistent challenges in balancing reconstruction fidelity with cross-scenario generalization. While existing methods predominantly focus on deterministic pixel-level mappings between paired low/normal-light images, they often neglect the continuous physical process of luminance transitions in real-world environments, leading to performance drop when normal-light references are unavailable. Inspired by empirical analysis of natural luminance dynamics revealing power-law distributed intensity transitions, this paper introduces Luminance-Aware Statistical Quantification (LASQ), a novel framework that reformulates LLIE as a statistical sampling process over hierarchical luminance distributions. Our LASQ re-conceptualizes luminance transition as a power-law distribution in intensity coordinate space that can be approximated by stratified power functions, therefore, replacing deterministic mappings with probabilistic sampling over continuous luminance layers. A diffusion forward process is designed to autonomously discover optimal transition paths between luminance layers, achieving unsupervised distribution emulation without normal-light references. In this way, it considerably improves the performance in practical situations, enabling more adaptable and versatile light restoration. This framework is also readily applicable to cases with normal-light references, where it achieves superior performance on domain-specific datasets alongside better generalization-ability across non-reference datasets.
zh

[CV-32] Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learning

链接: https://arxiv.org/abs/2511.01502
作者: Mengtan Zhang,Zizhan Guo,Hongbo Zhao,Yi Feng,Zuyi Xiong,Yue Wang,Shaoyi Du,Hanli Wang,Rui Fan
机构: Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University; College of Electronic & Information Engineering, Tongji University; Department of Control Science and Engineering, Zhejiang University; National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications, and the Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University; College of Electronic & Information Engineering, the School of Computer Science and Technology, and the Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University; College of Electronic & Information Engineering, Shanghai Institute of Intelligent Science and Technology, Shanghai Research Institute for Intelligent Autonomous Systems, the State Key Laboratory of Autonomous Intelligent Unmanned Systems, the Frontiers Science Center for Intelligent Autonomous Systems (Ministry of Education), and Shanghai Key Laboratory of Intelligent Autonomous Systems, Tongji University; National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: 18 pages, 14 figures

点击查看摘要

[CV-33] SE(3)-PoseFlow: Estimating 6D Pose Distributions for Uncertainty-Aware Robotic Manipulation

链接: https://arxiv.org/abs/2511.01501
作者: Yufeng Jin,Niklas Funk,Vignesh Prasad,Zechu Li,Mathias Franzius,Jan Peters,Georgia Chalvatzaki
机构: TU Darmstadt (达姆施塔特工业大学); Honda Research Institute Europe GmbH (本田研究欧洲有限公司); DFKI (德国人工智能研究中心); Hessian.AI (黑森人工智能)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-34] EPAN: Robust Pedestrian Re-Identification via Enhanced Alignment Network for IoT Surveillance

【速读】：该论文旨在解决物联网（Internet of Things, IoT）环境中行人重识别（Person Re-identification, ReID）在不同视角和环境变化下的鲁棒性问题。解决方案的关键在于提出一种双分支架构的增强型行人对齐网络（Enhanced Pedestrian Alignment Network, EPAN），通过提取多尺度与多视角下的对齐信息，有效缓解透视变换和环境差异对特征表示的影响，从而显著提升跨摄像头场景下ReID的准确性，在Inspection-Personnel数据集上实现了Rank-1准确率90.09%和平均精度均值（mean Average Precision, mAP）78.82%。

链接: https://arxiv.org/abs/2511.01498
作者: Zhiyang Jia,Hongyan Cui,Ge Gao,Bo Li,Minjie Zhang,Zishuo Gao,Huiwen Huang,Caisheng Zhuo
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 12 page, 5 figures

点击查看摘要

Abstract:Person re-identification (ReID) plays a pivotal role in computer vision, particularly in surveillance and security applications within IoT-enabled smart environments. This study introduces the Enhanced Pedestrian Alignment Network (EPAN), tailored for robust ReID across diverse IoT surveillance conditions. EPAN employs a dual-branch architecture to mitigate the impact of perspective and environmental changes, extracting alignment information under varying scales and viewpoints. Here, we demonstrate EPAN’s strong feature extraction capabilities, achieving outstanding performance on the Inspection-Personnel dataset with a Rank-1 accuracy of 90.09% and a mean Average Precision (mAP) of 78.82%. This highlights EPAN’s potential for real-world IoT applications, enabling effective and reliable person ReID across diverse cameras in surveillance and security systems. The code and data are available at: this https URL
zh

[CV-35] SecDiff: Diffusion-Aided Secure Deep Joint Source-Channel Coding Against Adversarial Attacks

链接: https://arxiv.org/abs/2511.01466
作者: Changyuan Zhao,Jiacheng Wang,Ruichen Zhang,Dusit Niyato,Hongyang Du,Zehui Xiong,Dong In Kim,Ping Zhang
机构: Nanyang Technological University (南洋理工大学); University of Hong Kong (香港大学); Queen’s University Belfast (贝尔法斯特女王大学); Sungkyunkwan University (成均馆大学); Beijing University of Posts and Telecommunications (北京邮电大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 13 pages, 6 figures

点击查看摘要

[CV-36] HMVLM: Human Motion-Vision-Lanuage Model via MoE LoRA

链接: https://arxiv.org/abs/2511.01463
作者: Lei Hu,Yongjing Ye,Shihong Xia
机构: Institute of Computing Technology, Chinese Academy of Sciences (中国科学院计算技术研究所); University of Chinese Academy of Sciences (中国科学院大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Graphics (cs.GR)
备注: 10 pages, 5figures. The Thirty-Ninth Annual Conference on Neural Information Processing Systems

点击查看摘要

[CV-37] Efficiently Training A Flat Neural Network Before It has been Quantizated

链接: https://arxiv.org/abs/2511.01462
作者: Peng Xia,Junbiao Pang,Tianyang Cai
机构: Beijing University Of Technology (北京工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: ongoing work, more results would be added

点击查看摘要

[CV-38] When to Trust the Answer: Question-Aligned Semantic Nearest Neighbor Entropy for Safer Surgical VQA

链接: https://arxiv.org/abs/2511.01458
作者: Dennis Pierantozzi,Luca Carlini,Mauro Orazio Drago,Chiara Lena,Cesare Hassan,Elena De Momi,Danail Stoyanov,Sophia Bano,Mobarak I. Hoque
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-39] Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation

链接: https://arxiv.org/abs/2511.01450
作者: Jie Du,Xinyu Gong,Qingshan Tan,Wen Li,Yangming Cheng,Weitao Wang,Chenlu Zhan,Suhui Wu,Hao Zhang,Jun Zhang
机构: ByteDance; Shanghai Jiao Tong University
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-40] Privacy Preserving Ordinal-Meta Learning with VLMs for Fine-Grained Fruit Quality Prediction

链接: https://arxiv.org/abs/2511.01449
作者: Riddhi Jain,Manasi Patwardhan,Aayush Mishra,Parijat Deshpande,Beena Rai
机构: TCS-Research(印度塔塔咨询服务公司研究部)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 9 pages, 1 figure, 4 tables

点击查看摘要

[CV-41] Contrast-Guided Cross-Modal Distillation for Thermal Object Detection

链接: https://arxiv.org/abs/2511.01435
作者: SiWoo Kim,JhongHyun An
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-42] rrain-Enhanced Resolution-aware Refinement Attention for Off-Road Segmentation

链接: https://arxiv.org/abs/2511.01434
作者: Seongkyu Choi,Jhonghyun An
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-43] UniSOT: A Unified Framework for Multi-Modality Single Object Tracking

【速读】：该论文旨在解决现有单目标跟踪器在处理多模态参考（如边界框、自然语言或两者结合）与多模态视频输入（如RGB、RGB+Depth、RGB+Thermal或RGB+Event）时存在的局限性问题，即当前方法通常仅针对特定模态组合设计，导致模型分离、难以泛化且实用性受限。解决方案的关键在于提出一个统一的跟踪框架UniSOT，其通过共享参数实现对三种参考模态和四种视频模态的所有组合进行联合建模，在保持模型结构一致性的同时显著提升跨模态跟踪性能，实验证明其在18个基准上优于专门针对单一模态设计的追踪器。

链接: https://arxiv.org/abs/2511.01427
作者: Yinchao Ma,Yuyang Tang,Wenfei Yang,Tianzhu Zhang,Xu Zhou,Feng Wu
机构: University of Science and Technology of China (中国科学技术大学); Sangfor Research Institute (深信服研究院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: The paper has been accepted by TPAMI

点击查看摘要

Abstract:Single object tracking aims to localize target object with specific reference modalities (bounding box, natural language or both) in a sequence of specific video modalities (RGB, RGB+Depth, RGB+Thermal or RGB+Event.). Different reference modalities enable various human-machine interactions, and different video modalities are demanded in complex scenarios to enhance tracking robustness. Existing trackers are designed for single or several video modalities with single or several reference modalities, which leads to separate model designs and limits practical applications. Practically, a unified tracker is needed to handle various requirements. To the best of our knowledge, there is still no tracker that can perform tracking with these above reference modalities across these video modalities simultaneously. Thus, in this paper, we present a unified tracker, UniSOT, for different combinations of three reference modalities and four video modalities with uniform parameters. Extensive experimental results on 18 visual tracking, vision-language tracking and RGB+X tracking benchmarks demonstrate that UniSOT shows superior performance against modality-specific counterparts. Notably, UniSOT outperforms previous counterparts by over 3.0% AUC on TNL2K across all three reference modalities and outperforms Un-Track by over 2.0% main metric across all three RGB+X video modalities.
zh

[CV-44] Learning to Seek Evidence: A Verifiable Reasoning Agent with Causal Faithfulness Analysis CVPR

链接: https://arxiv.org/abs/2511.01425
作者: Yuhang Huang,Zekai Lin,Fan Zhong,Lei Liu
机构: Fudan University (复旦大学); Institute of Biomedical Science, Fudan University (复旦大学生物医学科学研究所); Intelligent Medicine Institute, Fudan University (复旦大学智能医学研究院); Shanghai Institute of Infectious Disease and Biosecurity, Fudan University (复旦大学上海传染病与生物安全研究所); Shanghai Institute of Stem Cell Research and Clinical Translation, Fudan University (复旦大学上海干细胞研究与临床转化研究所)
类目: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: 12 pages, 3 figures. Under review at the Conference on Computer Vision and Pattern Recognition (CVPR) 2026

点击查看摘要

[CV-45] owards One-step Causal Video Generation via Adversarial Self-Distillation

链接: https://arxiv.org/abs/2511.01419
作者: Yongqi Yang,Huayang Huang,Xu Peng,Xiaobin Hu,Donghao Luo,Jiangning Zhang,Chengjie Wang,Yu Wu
机构: Wuhan University (武汉大学); Tencent YouTu Lab
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Under double-blind review as a conference paper

点击查看摘要

[CV-46] Extremal Contours: Gradient-driven contours for compact visual attribution

链接: https://arxiv.org/abs/2511.01411
作者: Reza Karimzadeh,Albert Alonso,Frans Zdyb,Julius B. Kirkegaard,Bulat Ibragimov
机构: University of Copenhagen (哥本哈根大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-47] Semantic BIM enrichment for firefighting assets: Fire-ART dataset and panoramic image-based 3D reconstruction

链接: https://arxiv.org/abs/2511.01399
作者: Ya Wen,Yutong Qiao,Chi Chiu Lam,Ioannis Brilakis,Sanghoon Lee,Mun On Wong
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-48] SEPS: Semantic-enhanced Patch Slimming Framework for fine-grained cross-modal alignment

链接: https://arxiv.org/abs/2511.01390
作者: Xinyu Mao,Junsi Li,Haoji Zhang,Yu Liang,Ming Sun
机构: University of Electronic Science and Technology of China (电子科技大学)
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-49] EREBUS: End-to-end Robust Event Based Underwater Simulation ICRA

链接: https://arxiv.org/abs/2511.01381
作者: Hitesh Kyatham,Arjun Suresh,Aadi Palnitkar,Yiannis Aloimonos
机构: Maryland Robotics Center, University of Maryland, College Park, MD 20742, USA
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: Accepted to ICRA AQUA2SIM Workshop 2025, 6 pages, 3 figures, conference paper

点击查看摘要

[CV-50] CMI-MTL: Cross-Mamba interaction based multi-task learning for medical visual question answering

链接: https://arxiv.org/abs/2511.01357
作者: Qiangguo Jin,Xianyao Zheng,Hui Cui,Changming Sun,Yuqi Fang,Cong Cong,Ran Su,Leyi Wei,Ping Xuan,Junbo Wang
机构: Northwestern Polytechnical University (西北工业大学); La Trobe University (拉特罗布大学); CSIRO Data61 (澳大利亚联邦科学与工业研究组织数据61); Nanjing University (南京大学); Macquarie University (麦考瑞大学); Tianjin University (天津大学); Macao Polytechnic University (澳门理工大学); Shantou University (汕头大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: The paper has been accepted by the 33rd Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2025)

点击查看摘要

[CV-51] Expanding the Content-Style Frontier: a Balanced Subspace Blending Approach for Content-Style LoRA Fusion

链接: https://arxiv.org/abs/2511.01355
作者: Linhao Huang
机构: Beijing University of Technology (北京工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-52] MIQ-SAM3D: From Single-Point Prompt to Multi-Instance Segmentation via Competitive Query Refinement

链接: https://arxiv.org/abs/2511.01345
作者: Jierui Qu,Jianchun Zhao
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-53] RDTE-UNet: A Boundary and Detail Aware UNet for Precise Medical Image Segmentation

【速读】：该论文旨在解决医学图像分割中因解剖结构变异大和边界模糊导致的细粒度结构分割不准确问题。解决方案的关键在于提出RDTE-UNet网络架构，其核心创新包括：采用混合ResBlock细节感知Transformer作为骨干网络以融合局部建模与全局上下文信息；引入ASBE（自适应边界增强模块）提升边界清晰度，HVDA（细粒度特征建模模块）增强细节表达能力，以及EulerFF（基于欧拉公式引导的融合加权模块）优化多尺度特征融合策略，从而在形态、方向和尺度上显著提升结构一致性与边界精度。

链接: https://arxiv.org/abs/2511.01328
作者: Jierui Qu,Jianchun Zhao
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

Abstract:Medical image segmentation is essential for computer-assisted diagnosis and treatment planning, yet substantial anatomical variability and boundary ambiguity hinder reliable delineation of fine structures. We propose RDTE-UNet, a segmentation network that unifies local modeling with global context to strengthen boundary delineation and detail preservation. RDTE-UNet employs a hybrid ResBlock detail-aware Transformer backbone and three modules: ASBE for adaptive boundary enhancement, HVDA for fine-grained feature modeling, and EulerFF for fusion weighting guided by Euler’s formula. Together, these components improve structural consistency and boundary accuracy across morphology, orientation, and scale. On Synapse and BUSI dataset, RDTE-UNet has achieved a comparable level in terms of segmentation accuracy and boundary quality.
zh

[CV-54] A Generative Adversarial Approach to Adversarial Attacks Guided by Contrastive Language-Image Pre-trained Model

链接: https://arxiv.org/abs/2511.01317
作者: Sampriti Soor,Alik Pramanick,Jothiprakash K,Arijit Sur
机构: IIT Guwahati (印度理工学院古瓦哈蒂分校)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 18 pages, 3 figures

点击查看摘要

[CV-55] MVSMamba: Multi-View Stereo with State Space Model NEURIPS2025

链接: https://arxiv.org/abs/2511.01315
作者: Jianfei Jiang,Qiankun Liu,Hongyuan Liu,Haochen Yu,Liyong Wang,Jiansheng Chen,Huimin Ma
机构: University of Science and Technology Beijing, China (北京科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by NeurIPS 2025

点击查看摘要

[CV-56] Perturb a Model Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models NEURIPS2025

链接: https://arxiv.org/abs/2511.01307
作者: Tae-Young Lee,Juwon Seo,Jong Hwan Ko,Gyeong-Moon Park
机构: Korea University (韩国大学); Kyung Hee University (庆熙大学); Sungkyunkwan University (成均馆大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 26 pages, 9 figures, 16 tables, NeurIPS 2025

点击查看摘要

[CV-57] Positive Semi-definite Latent Factor Grouping-Boosted Cluster-reasoning Instance Disentangled Learning for WSI Representation

链接: https://arxiv.org/abs/2511.01304
作者: Chentao Li,Behzad Bozorgtabar,Yifang Ping,Pan Huang,Jing Qin
机构: Columbia University (哥伦比亚大学); École Polytechnique Fédérale de Lausanne (洛桑联邦理工学院); Centre Hospitalier Universitaire Vaudois (沃州大学医院中心); Jingfeng Laboratory (景峰实验室); The Hong Kong Polytechnic University (香港理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Our code is available at this https URL

点击查看摘要

[CV-58] REASON : Probability map-guided dual-branch fusion framework for gastric content assessment

链接: https://arxiv.org/abs/2511.01302
作者: Nu-Fnag Xiao,De-Xing Huang,Le-Tian Wang,Mei-Jiang Gui,Qi Fu,Xiao-Liang Xie,Shi-Qi Liu,Shuangyi Wang,Zeng-Guang Hou,Ying-Wei Wang,Xiao-Hu Zhou
机构: Hunan University of Science and Technology (湖南科技大学); Institute of Automation, Chinese Academy of Sciences (中国科学院自动化研究所); Fudan University (复旦大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Under Review. 12 pages, 10 figures, 6 tables

点击查看摘要

[CV-59] UniREditBench: A Unified Reasoning -based Image Editing Benchmark

链接: https://arxiv.org/abs/2511.01295
作者: Feng Han,Yibin Wang,Chenglin Li,Zheming Liang,Dianyi Wang,Yang Jiao,Zhipeng Wei,Chao Gong,Cheng Jin,Jingjing Chen,Jiaqi Wang
机构: Fudan University (复旦大学); Shanghai Innovation Institute (上海创新研究院); Zhejiang University (浙江大学); UC Berkeley (加州大学伯克利分校)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-60] Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects

链接: https://arxiv.org/abs/2511.01294
作者: Jiawei Wang,Dingyou Wang,Jiaming Hu,Qixuan Zhang,Jingyi Yu,Lan Xu
机构: 未知
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-61] Detecting Generated Images by Fitting Natural Image Distributions NEURIPS2025

链接: https://arxiv.org/abs/2511.01293
作者: Yonggang Zhang,Jun Nie,Xinmei Tian,Mingming Gong,Kun Zhang,Bo Han
机构: The Hong Kong University of Science and Technology (香港科技大学); TMLR Group, Hong Kong Baptist University (香港浸会大学TMLR组); University of Science and Technology of China (中国科学技术大学); The University of Melbourne, Australia (墨尔本大学, 澳大利亚); Carnegie Mellon University (卡内基梅隆大学); Mohamed bin Zayed University of Artificial Intelligence (穆罕默德·本·扎耶德人工智能大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 25 pages, 9 figures, NeurIPS 2025 spotlight

点击查看摘要

[CV-62] Adaptation of Foundation Models for Medical Image Analysis: Strategies Challenges and Future Directions

链接: https://arxiv.org/abs/2511.01284
作者: Karma Phuntsho,Abdullah,Kyungmi Lee,Ickjai Lee,Euijoon Ahn
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-63] PRevivor: Reviving Ancient Chinese Paintings using Prior-Guided Color Transformers

链接: https://arxiv.org/abs/2511.01274
作者: Tan Tang,Yanhong Wu,Junming Gao,Yingcai Wu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-64] MotionStream: Real-Time Video Generation with Interactive Motion Controls

链接: https://arxiv.org/abs/2511.01266
作者: Joonghyuk Shin,Zhengqi Li,Richard Zhang,Jun-Yan Zhu,Jaesik Park,Eli Schechtman,Xun Huang
机构: Adobe Research(Adobe研究院); Carnegie Mellon University (卡内基梅隆大学); Seoul National University (首尔国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Project webpage: this https URL

点击查看摘要

[CV-65] Source-Only Cross-Weather LiDAR via Geometry-Aware Point Drop

链接: https://arxiv.org/abs/2511.01250
作者: YoungJae Cheong,Jhonghyun An
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-66] CenterMamba-SAM: Center-Prioritized Scanning and Temporal Prototypes for Brain Lesion Segmentation

链接: https://arxiv.org/abs/2511.01243
作者: Yu Tian,Zhongheng Yang,Chenshi Liu,Yiyun Su,Ziwei Hong,Zexi Gong,Jingyuan Xu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-67] Beyond Deceptive Flatness: Dual-Order Solution for Strengthening Adversarial Transferability

链接: https://arxiv.org/abs/2511.01240
作者: Zhixuan Zhang,Pingyu Wang,Xingjian Zheng,Linbo Qing,Qi Liu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by Pattern Recognition in Nov 01,2025

点击查看摘要

[CV-68] Eyes on Target: Gaze-Aware Object Detection in Egocentric Video

链接: https://arxiv.org/abs/2511.01237
作者: Vishakha Lall,Yisi Liu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Accepted at RAAI 2025

点击查看摘要

[CV-69] Gesture Generation (Still) Needs Improved Human Evaluation Practices: Insights from a Community-Driven State-of-the-Art Benchmark

链接: https://arxiv.org/abs/2511.01233
作者: Rajmund Nagy(1),Hendric Voss(2),Thanh Hoang-Minh(3),Mihail Tsakov(4),Teodor Nikolov(5),Zeyi Zhang(6),Tenglong Ao(6),Sicheng Yang(7),Shaoli Huang(8),Yongkang Cheng(8),M. Hamza Mughal(9),Rishabh Dabral(9),Kiran Chhatre(1),Christian Theobalt(9),Libin Liu(6),Stefan Kopp(2),Rachel McDonnell(10),Michael Neff(11),Taras Kucherenko(12),Youngwoo Yoon(13),Gustav Eje Henter(1 and 5) ((1) KTH Royal Institute of Technology, (2) Bielefeld University, (3) University of Science – VNUHCM, (4) Independent Researcher, (5) Motorica AB, (6) Peking University, (7) Huawei Technologies Ltd., (8) Astribot, (9) Max-Planck Institute for Informatics, SIC, (10) Trinity College Dublin, (11) University of California, Davis, (12) SEED – Electronic Arts, (13) Electronics and Telecommunications Research Institute (ETRI))
机构: KTH Royal Institute of Technology; Bielefeld University; University of Science – VNUHCM; Independent Researcher; Motorica AB; Peking University; Huawei Technologies Ltd.; Astribot; Max-Planck Institute for Informatics, SIC; Trinity College Dublin; University of California, Davis; SEED – Electronic Arts; Electronics and Telecommunications Research Institute (ETRI)
类目: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR); Human-Computer Interaction (cs.HC)
备注: 23 pages, 10 figures. The last two authors made equal contributions

点击查看摘要

[CV-70] Saliency-Guided Domain Adaptation for Left-Hand Driving in Autonomous Steering

链接: https://arxiv.org/abs/2511.01223
作者: Zahra Mehraban,Sebastien Glaser,Michael Milford,Ronald Schroeter
机构: Queensland University of Technology (昆士兰科技大学); QUT Centre for Robotics and School of Electrical Engineering and Computer Science (昆士兰科技大学机器人中心和电气工程与计算机科学学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-71] hought-For-Food: Reasoning Chain Induced Food Visual Question Answering

链接: https://arxiv.org/abs/2511.01213
作者: Riddhi Jain,Manasi Patwardhan,Parijat Deshpande,Venkataramana Runkana
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 10 pages, 11 figures, 6 tables

点击查看摘要

[CV-72] OmniVLA: Unifiying Multi-Sensor Perception for Physically-Grounded Multimodal VLA

链接: https://arxiv.org/abs/2511.01210
作者: Heyu Guo,Shanmu Wang,Ruichun Ma,Shiqi Jiang,Yasaman Ghasempour,Omid Abari,Baining Guo,Lili Qi
机构: Princeton University (普林斯顿大学); University of California, Los Angeles (加州大学洛杉矶分校); 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-73] MoSa: Motion Generation with Scalable Autoregressive Modeling

链接: https://arxiv.org/abs/2511.01200
作者: Mengyuan Liu,Sheng Yan,Yong Wang,Yingjie Li,Gui-Bin Bian,Hong Liu
机构: Peking University, Shenzhen Graduate School (北京大学深圳研究生院); Chongqing University of Technology (重庆理工大学); Tencent Technology Co., Ltd. (腾讯科技有限公司); Chinese Academy of Sciences (中国科学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-74] A Topology-Aware Graph Convolutional Network for Human Pose Similarity and Action Quality Assessment

链接: https://arxiv.org/abs/2511.01194
作者: Minmin Zeng
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 10 pages, 5 figures. Submitted as a computer vision paper in the cs.CV category

点击查看摘要

[CV-75] LiDAR-VGGT: Cross-Modal Coarse-to-Fine Fusion for Globally Consistent and Metric-Scale Dense Mapping

链接: https://arxiv.org/abs/2511.01186
作者: Lijie Wang,Lianjie Guo,Ziyi Xu,Qianhao Wang,Fei Gao,Xieyuanli Chen
机构: Zhejiang University (浙江大学); Differential Robot Technology Co., Ltd. (差分机器人技术有限公司); National University of Defense Technology (国防科技大学)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-76] Diffusion Transformer meets Multi-level Wavelet Spectrum for Single Image Super-Resolution

链接: https://arxiv.org/abs/2511.01175
作者: Peng Du,Hui Li,Han Xu,Paul Barom Jeon,Dongwook Lee,Daehyun Ji,Ran Yang,Feng Zhu
机构: Samsung R&D Institute China Xi’an (SRCX); Samsung Electronics Co., LTD., South Korea
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-77] Web-Scale Collection of Video Data for 4D Animal Reconstruction NEURIPS2025

链接: https://arxiv.org/abs/2511.01169
作者: Brian Nlong Zhao,Jiajun Wu,Shangzhe Wu
机构: Stanford University (斯坦福大学); University of Illinois Urbana-Champaign (伊利诺伊大学香槟分校); University of Cambridge (剑桥大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: NeurIPS 2025 Datasets and Benchmarks

点击查看摘要

[CV-78] ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation

链接: https://arxiv.org/abs/2511.01163
作者: Yongyuan Liang,Wei Chow,Feng Li,Ziqiao Ma,Xiyao Wang,Jiageng Mao,Jiuhai Chen,Jiatao Gu,Yue Wang,Furong Huang
机构: University of Maryland, College Park(马里兰大学学院公园分校); University of Pennsylvania(宾夕法尼亚大学); The Hong Kong University of Science and Technology(香港科技大学); University of Michigan(密歇根大学); University of Southern California(南加州大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project Page: this https URL

点击查看摘要

[CV-79] MicroAUNet: Boundary-Enhanced Multi-scale Fusion with Knowledge Distillation for Colonoscopy Polyp Image Segmentation

链接: https://arxiv.org/abs/2511.01143
作者: Ziyi Wang,Yuanmei Zhang,Dorna Esrafilzadeh,Ali R. Jalili,Suncheng Xiang
机构: UNSW(新南威尔士大学); Shanghai Jiao Tong University (上海交通大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Work in progress

点击查看摘要

[CV-80] Learning with Category-Equivariant Architectures for Human Activity Recognition

链接: https://arxiv.org/abs/2511.01139
作者: Yoshihiro Maruyama
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-81] Weakly Supervised Concept Learning with Class-Level Priors for Interpretable Medical Diagnosis

链接: https://arxiv.org/abs/2511.01131
作者: Md Nahiduzzaman,Steven Korevaar,Alireza Bab-Hadiashar,Ruwan Tennakoon
机构: RMIT University (皇家墨尔本理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-82] Boosting performance of computer vision applications through embedded GPUs on the edge

链接: https://arxiv.org/abs/2511.01129
作者: Fabio Diniz Rossi
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Distributed, Parallel, and Cluster Computing (cs.DC)
备注: 4 pages, 6 figures

点击查看摘要

[CV-83] Anatomically Constrained Transformers for Echocardiogram Analysis

链接: https://arxiv.org/abs/2511.01109
作者: Alexander Thorley,Agis Chartsias,Jordan Strom,Jeremy Slivnick,Dipak Kotecha,Alberto Gomez,Jinming Duan
机构: University of Birmingham, School of Computer Science (伯明翰大学计算机科学学院); Beth Isreal Deaconess Medical Centre (贝斯以色列女执事医疗中心); University of Chicago (芝加哥大学); Institute of Cardiovascular Sciences, University of Birmingham (心血管科学研究所，伯明翰大学); Ultromics Ltd (Ultromics有限公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-84] Epanechnikov nonparametric kernel density estimation based feature-learning in respiratory disease chest X-ray images

链接: https://arxiv.org/abs/2511.01098
作者: Veronica Marsico,Antonio Quintero-Rincon,Hadj Batatia
机构: Catholic University of Argentina (天主教阿根廷大学); Heriot-Watt University (赫瑞-瓦特大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 12 pages, 6 figures, 3 tables

点击查看摘要

[CV-85] SliceVision-F2I: A Synthetic Feature-to-Image Dataset for Visual Pattern Representation on Network Slices

链接: https://arxiv.org/abs/2511.01087
作者: Md. Abid Hasan Rafi,Mst. Fatematuj Johora,Pankaj Bhowmik
机构: Hajee Mohammad Danesh Science and Technology University (哈吉·穆罕默德·丹esh科学与技术大学)
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-86] GeoToken: Hierarchical Geolocalization of Images via Next Token Prediction ICDM

链接: https://arxiv.org/abs/2511.01082
作者: Narges Ghasemi,Amir Ziashahabi,Salman Avestimehr,Cyrus Shahabi
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Accepted to IEEE International Conference on Data Mining (ICDM) 2025

点击查看摘要

[CV-87] -MLA: A Targeted Multiscale Log–Exponential Attack Framework for Neural Image Compression

链接: https://arxiv.org/abs/2511.01079
作者: Nikolay I. Kalmykov,Razan Dibo,Kaiyu Shen,Xu Zhonghan,Anh-Huy Phan,Yipeng Liu,Ivan Oseledets
机构: Skolkovo Institute of Science and Technology (斯科尔科沃科学与技术学院); University of Electronic Science and Technology of China (电子科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Numerical Analysis (math.NA)
备注: Submitted to Information Systems. Code will be released upon journal publication

点击查看摘要

[CV-88] FastBoost: Progressive Attention with Dynamic Scaling for Efficient Deep Learning

链接: https://arxiv.org/abs/2511.01026
作者: JunXi Yuan
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 17pages , 10figures , 12tables

点击查看摘要

[CV-89] HyFormer-Net: A Synergistic CNN-Transformer with Interpretable Multi-Scale Fusion for Breast Lesion Segmentation and Classification in Ultrasound Images

链接: https://arxiv.org/abs/2511.01013
作者: Mohammad Amanour Rahman
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: This manuscript has been submitted to Informatics in Medicine Unlocked

点击查看摘要

[CV-90] Integrating Visual and X-Ray Machine Learning Features in the Study of Paintings by Goya

链接: https://arxiv.org/abs/2511.01000
作者: Hassan Ugail,Ismail Lujain Jaleel
机构: University of Bradford (布拉德福德大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-91] MID: A Self-supervised Multimodal Iterative Denoising Framework

链接: https://arxiv.org/abs/2511.00997
作者: Chang Nie,Tianchen Deng,Zhe Liu,Hesheng Wang
机构: Shanghai Jiao Tong University (上海交通大学); Key Laboratory of System Control and Information Processing, Ministry of Education of China (教育部系统控制与信息处理重点实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-92] VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel

链接: https://arxiv.org/abs/2511.00981
作者: Suzhong Fu,Rui Sun,Xuan Ding,Jingqi Dong,Yiming Yang,Yao Zhu,Min Chang Jordan Ren,Delin Deng,Angelica Aviles-Rivero,Shuguang Cui,Zhen Li
机构: FNii-Shenzhen (深圳福田区人工智能研究院); CUHK-Shenzhen (香港中文大学（深圳）); Zhejiang University (浙江大学); Boston University (波士顿大学); Vanderbilt University (范德堡大学); Tsinghua University (清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-93] A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis NEURIPS2025

链接: https://arxiv.org/abs/2511.00962
作者: Dongheng Lin,Mengxue Qu,Kunyang Han,Jianbo Jiao,Xiaojie Jin,Yunchao Wei
机构: Beijing Jiaotong University (北京交通大学); University of Birmingham (伯明翰大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: NeurIPS 2025 poster

点击查看摘要

[CV-94] EVTAR: End-to-End Try on with Additional Unpaired Visual Reference

链接: https://arxiv.org/abs/2511.00956
作者: Liuzhuozheng Li,Yue Gong,Shanyuan Liu,Bo Cheng,Yuhang Ma,Liebucha Wu,Dengyang Jiang,Zanyi Wang,Dawei Leng,Yuhui Yin
机构: The University of Tokyo (东京大学); 360 AI Research; Hong Kong University of Science and Technology (香港科技大学); University of California San Diego (加州大学圣地亚哥分校)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-95] Fast-SmartWay: Panoramic-Free End-to-End Zero-Shot Vision-and-Language Navigation

链接: https://arxiv.org/abs/2511.00933
作者: Xiangyu Shi,Zerui Li,Yanyuan Qiao,Qi Wu
机构: Australian Institute for Machine Learning, the University of Adelaide (阿德莱德大学机器学习研究所); CREATE Lab, Swiss Federal Institute of Technology Lausanne (EPFL) (瑞士洛桑联邦理工学院)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-96] Dynamic Multi-level Weighted Alignment Network for Zero-shot Sketch-based Image Retrieval

链接: https://arxiv.org/abs/2511.00925
作者: Hanwen Su,Ge Song,Jiyan Wang,Yuanbo Zhu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-97] Fleming-VL: Towards Universal Medical Visual Reasoning with Multimodal LLM s

【速读】：该论文旨在解决多模态大语言模型（Multimodal Large Language Models, MLLMs）在医疗领域应用时面临的挑战，即如何实现对异构医学模态（如2D图像、3D体素扫描和时间序列视频）的统一理解与建模。由于医疗数据具有高度异质性，且不同模态间存在显著的领域差距和格式不一致性，现有方法难以构建高效通用的医疗MLLMs。解决方案的关键在于提出一个以数据为中心的端到端框架Fleming-VL，其核心策略包括：(1) 通过整合自然域与医学特定域的长上下文数据扩大预训练规模；(2) 利用罕见医学数据（如完整视频分析及超声、皮肤镜等低频2D模态）补充微调；(3) 扩展评估体系以涵盖3D体素和视频理解基准。基于监督微调（SFT）和群体相对策略优化（GRPO），Fleming-VL在多个医学视觉理解任务中达到当前最优性能，并公开发布模型以推动医疗AI研究的透明性与可复现性。

链接: https://arxiv.org/abs/2511.00916
作者: Yan Shu,Chi Liu,Robin Chen,Derek Li,Bryan Dai
机构: Ubiquant
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

Abstract:Multimodal Large Language Models (MLLMs) have demonstrated remarkable effectiveness in various general-domain scenarios, such as visual question answering and image captioning. Recently, researchers have increasingly focused on empowering MLLMs with medical conversational abilities, which hold significant promise for clinical applications. However, medical data presents unique challenges due to its heterogeneous nature – encompassing diverse modalities including 2D images, 3D volumetric scans, and temporal video sequences. The substantial domain gap and data format inconsistencies across these modalities have hindered the development of unified medical MLLMs. To address these challenges, we propose Fleming-VL, a unified end-to-end framework for comprehensive medical visual understanding across heterogeneous modalities. Fleming-VL tackles this problem from a data-centric perspective through three key strategies: (1) scaling up pretraining by integrating long-context data from both natural and medical-specific domains; (2) complementing fine-tuning with rare medical data, including holistic video analysis and underrepresented 2D modalities such as ultrasound and dermoscopy images; (3) extending existing evaluation frameworks to incorporate 3D volumetric and video understanding benchmarks. Through supervised fine-tuning (SFT) and group relative policy optimization (GRPO), we develop Fleming-VL in multiple model scales. Extensive experiments demonstrate that Fleming-VL achieves state-of-the-art performance across multiple benchmarks, including medical VQA, video QA, and 3D medical image understanding. We publicly release Fleming-VL to promote transparent, reproducible, and auditable progress in medical AI.
zh

[CV-98] GraphGeo: Multi-Agent Debate Framework for Visual Geo-localization with Heterogeneous Graph Neural Networks

链接: https://arxiv.org/abs/2511.00908
作者: Heng Zheng,Yuling Shi,Xiaodong Gu,Haochen You,Zijian Zhang,Lubin Gan,Hao Zhang,Wenjun Huang,Jin Huang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR)
备注:

点击查看摘要

[CV-99] Learning with Category-Equivariant Representations for Human Activity Recognition

链接: https://arxiv.org/abs/2511.00900
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); Human-Computer Interaction (cs.HC)
备注:

点击查看摘要

[CV-100] Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion NEURIPS2025

链接: https://arxiv.org/abs/2511.00859
作者: Jaehyun Park,Konyul Park,Daehun Kim,Junseo Park,Jun Won Choi
机构: Seoul National University (首尔国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to NeurIPS 2025

点击查看摘要

[CV-101] Occlusion-Aware Diffusion Model for Pedestrian Intention Prediction

链接: https://arxiv.org/abs/2511.00858
作者: Yu Liu,Zhijie Liu,Zedong Yang,You-Fu Li,He Kong
机构: Southern University of Science and Technology (南方科技大学); City University of Hong Kong (香港城市大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: This manuscript has been accepted to the IEEE Transactions on Intelligent Transportation Systems as a regular paper

点击查看摘要

[CV-102] OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Tasks

链接: https://arxiv.org/abs/2511.00846
作者: Zhihao Peng,Cheng Wang,Shengyuan Liu,Zhiying Liang,Yixuan Yuan
机构: Chinese University of Hong Kong (香港中文大学); Sun Yat-sen Memorial Hospital, Sun Yat-sen University (中山大学附属第一医院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-103] Parameter Interpolation Adversarial Training for Robust Image Classification

链接: https://arxiv.org/abs/2511.00836
作者: Xin Liu,Yichen Yang,Kun He,John E. Hopcroft
机构: Huazhong University of Scinece and Technology (华中科技大学); Cornell University (康奈尔大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Accepted by TIFS 2025

点击查看摘要

[CV-104] Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials NEURIPS2025

链接: https://arxiv.org/abs/2511.00833
作者: Yifan Pu,Jixuan Ying,Qixiu Li,Tianzhu Ye,Dongchen Han,Xiaochen Wang,Ziyi Wang,Xinyu Shao,Gao Huang,Xiu Li
机构: Tsinghua University (清华大学); Peking University (北京大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: NeurIPS 2025

点击查看摘要

[CV-105] Enhancing Adversarial Transferability in Visual-Language Pre-training Models via Local Shuffle and Sample-based Attack NAACL2025

链接: https://arxiv.org/abs/2511.00831
作者: Xin Liu,Aoyang Zhou,Aoyang Zhou
机构: Huazhong University of Science and Technology (华中科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Accepted by NAACL2025 findings

点击查看摘要

[CV-106] OMEGA: Optimized Multimodal Position Encoding Index Derivation with Global Adaptive Scaling for Vision-Language Models

链接: https://arxiv.org/abs/2511.00821
作者: Ruoxiang Huang,Xindian Ma,Rundong Kong,Zhen Yuan,Peng Zhang
机构: Tianjin University (天津大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-107] A-LSDiff:Topology-Aware Diffusion Guided by a Level Set Energy for Pancreas Segmentation

链接: https://arxiv.org/abs/2511.00815
作者: Yue Gou,Fanghui Song,Yuming Xing,Shengzhu Shi,Zhichang Guo,Boying Wu
机构: Harbin Institute of Technology (哈尔滨工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 14 pages, 7 figures

点击查看摘要

[CV-108] LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons

链接: https://arxiv.org/abs/2511.00812
作者: Shashank Nag,Alan T.L. Bacellar,Zachary Susskind,Anshul Jha,Logan Liberty,Aishwarya Sivakumar,Eugene B. John,Krishnan Kailas,Priscila M.V. Lima,Neeraja J. Yadwadkar,Felipe M.G. Franca,Lizy K. John
机构: The University of Texas at Austin (得克萨斯大学奥斯汀分校); The University of Texas at San Antonio (得克萨斯大学圣安东尼奥分校); Independent Researcher; Federal University of Rio de Janeiro (里约热内卢联邦大学); Instituto de Telecomunicações (电信研究所)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted for FPT 2025, 9 pages, conference

点击查看摘要

[CV-109] EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment NEURIPS’25

链接: https://arxiv.org/abs/2511.00804
作者: Abhiram Kusumba,Maitreya Patel,Kyle Min,Changhoon Kim,Chitta Baral,Yezhou Yang
机构: Arizona State University (亚利桑那州立大学); Capital One (资本一号); Oracle (甲骨文); Soongsil University (松林大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: NeurIPS’25 Spotlight | Project page: this https URL

点击查看摘要

[CV-110] Med-Banana-50K: A Cross-modality Large-Scale Dataset for Text-guided Medical Image Editing

链接: https://arxiv.org/abs/2511.00801
作者: Zhihui Chen,Mengling Feng
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注:

点击查看摘要

[CV-111] FedOnco-Bench: A Reproducible Benchmark for Privacy-Aware Federated Tumor Segmentation with Synthetic CT Data

链接: https://arxiv.org/abs/2511.00795
作者: Viswa Chaitanya Marella,Suhasnadh Reddy Veluru,Sai Teja Erukude
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Published in IEEE

点击查看摘要

[CV-112] Class-agnostic 3D Segmentation by Granularity-Consistent Automatic 2D Mask Tracking

链接: https://arxiv.org/abs/2511.00785
作者: Juan Wang,Yasutomo Kawanishi,Tomo Miyazaki,Zhijie Wang,Shinichiro Omachi
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Under review in Pattern Recognition

点击查看摘要

[CV-113] A Hybrid YOLOv5-SSD IoT-Based Animal Detection System for Durian Plantation Protection

链接: https://arxiv.org/abs/2511.00777
作者: Anis Suttan Shahrir,Zakiah Ayop,Syarulnaziah Anawar,Norulzahrah Mohd Zainudin
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-114] owards classification-based representation learning for place recognition on LiDAR scans

链接: https://arxiv.org/abs/2511.00738
作者: Dmitrii Khizbullin,Maksim Konoplia
机构: King Abdullah University of Science and Technology (国王阿卜杜拉大学科技学院); Moscow Institute of Physics and Technology (莫斯科物理技术研究所)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-115] Validating Deep Models for Alzheimers 18F-FDG PET Diagnosis Across Populations: A Study with Latin American Data

链接: https://arxiv.org/abs/2511.00728
作者: Hugo Massaroli,Hernan Chaves,Pilar Anania,Mauricio Farez,Emmanuel Iarussi,Viviana Siless
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 7 pages, 2 figures

点击查看摘要

[CV-116] Applying Medical Imaging Tractography Techniques to Painterly Rendering of Images

链接: https://arxiv.org/abs/2511.00702
作者: Alberto Di Biase
机构: Imperial College London (帝国理工学院)
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV)
备注: Exploratory investigation applying medical imaging tractography techniques to painterly image rendering. Code available at this https URL

点击查看摘要

[CV-117] oward Better Optimization of Low-Dose CT Enhancement: A Critical Analysis of Loss Functions and Image Quality Assessment Metrics

链接: https://arxiv.org/abs/2511.00698
作者: Taifour Yousra,Beghdadi Azeddine,Marie Luong,Zuheng Ming
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-118] Evolve to Inspire: Novelty Search for Diverse Image Generation NEURIPS2025

链接: https://arxiv.org/abs/2511.00686
作者: Alex Inch,Passawis Chaiyapattanaporn,Yuchen Zhu,Yuan Lu,Ting-Wen Ko,Davide Paglieri
机构: University College London (伦敦大学学院); University of Oxford (牛津大学); Tesco Technology (特易购科技); Microsoft Research (微软研究院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 14 pages, 10 figures, Accepted to Neurips 2025 GenProCC Workshop

点击查看摘要

[CV-119] Outlier-Aware Post-Training Quantization for Image Super-Resolution

链接: https://arxiv.org/abs/2511.00682
作者: Hailing Wang,jianglin Lu,Yitian Zhang,Yun Fu
机构: Northeastern University (东北大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-120] Metadata-Aligned 3D MRI Representations for Contrast Understanding and Quality Control

链接: https://arxiv.org/abs/2511.00681
作者: Mehmet Yigit Avci,Pedro Borges,Virginia Fernandez,Paul Wright,Mehmet Yigitsoy,Sebastien Ourselin,Jorge Cardoso
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-121] Benchmarking individual tree segmentation using multispectral airborne laser scanning data: the FGI-EMIT dataset

链接: https://arxiv.org/abs/2511.00653
作者: Lassi Ruoppa,Tarmo Hietala,Verneri Seppänen,Josef Taher,Teemu Hakala,Xiaowei Yu,Antero Kukko,Harri Kaartinen,Juha Hyyppä
机构: Finnish Geospatial Research Institute FGI (芬兰地理空间研究所FGI); The National Land Survey of Finland (芬兰国家土地测量局); Aalto University (阿尔托大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 39 pages, 9 figures

点击查看摘要

[CV-122] Grounding Surgical Action Triplets with Instrument Instance Segmentation: A Dataset and Target-Aware Fusion Approach

链接: https://arxiv.org/abs/2511.00643
作者: Oluwatosin Alabi,Meng Wei,Charlie Budd,Tom Vercauteren,Miaojing Shi
机构: King’s College London (伦敦国王学院); Tongji University (同济大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-123] CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World

链接: https://arxiv.org/abs/2511.00613
作者: Yating Yu,Congqi Cao,Zhaoying Wang,Weihua Meng,Jie Li,Yuxin Li,Zihao Wei,Zhongpei Shen,Jiajun Zhang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-124] RACES: Temporal Recall with Contextual Embeddings for Real-Time Video Anomaly Detection

链接: https://arxiv.org/abs/2511.00580
作者: Yousuf Ahmed Siddiqui,Sufiyaan Usmani,Umer Tariq,Jawwad Ahmed Shamsi,Muhammad Burhan Khan
机构: FAST-NUCES (FAST国家科技大学); System Research Laboratory (SysLab) (系统研究实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 10 pages, 5 figures

点击查看摘要

[CV-125] Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective

链接: https://arxiv.org/abs/2511.00573
作者: Wei Feng,Zongyuan Ge
机构: Monash University (蒙纳士大学); Airdoc–Monash Research (Airdoc–蒙纳士研究)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 29 pages, 5 figures

点击查看摘要

[CV-126] 4D Neural Voxel Splatting: Dynamic Scene Rendering with Voxelized Guassian Splatting

链接: https://arxiv.org/abs/2511.00560
作者: Chun-Tin Wu,Jun-Cheng Chen
机构: National Taiwan University (国立台湾大学); Academia Sinica (中央研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 7 figures

点击查看摘要

[CV-127] Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance

链接: https://arxiv.org/abs/2511.00543
作者: Yunchuan Guan,Yu Liu,Ke Zhou,Hui Li,Sen Jia,Zhiqi Shen,Ziyang Wang,Xinglin Zhang,Tao Chen,Jenq-Neng Hwang,Lei Li
机构: Huazhong University of Science and Technology (华中科技大学); University of Waterloo (滑铁卢大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
备注:

点击查看摘要

[CV-128] MIFO: Learning and Synthesizing Multi-Instance from One Image

链接: https://arxiv.org/abs/2511.00542
作者: Kailun Su,Ziqi He,Xi Wang,Yang Zhou
机构: ShenZhen University (深圳大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 17 pages, 30 figures

点击查看摘要

[CV-129] Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Era

链接: https://arxiv.org/abs/2511.00540
作者: Wenbing Zhu,Chengjie Wang,Bin-Bin Gao,Jiangning Zhang,Guannan Jiang,Jie Hu,Zhenye Gan,Lidong Wang,Ziqing Zhou,Linjie Cheng,Yurui Pan,Bo Peng,Mingmin Chi,Lizhuang Ma
机构: Fudan University (复旦大学); Youtu Lab, Tencent (腾讯优图实验室); Shanghai Jiao Tong University (上海交通大学); Rongcheer Co., Ltd (荣车科技有限公司); City University of Hong Kong (香港城市大学); National University of Singapore (新加坡国立大学); Shanghai Ocean University (上海海洋大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 13 pages, 4 figures and 5 tables

点击查看摘要

[CV-130] xt-guided Fine-Grained Video Anomaly Detection

链接: https://arxiv.org/abs/2511.00524
作者: Jihao Gu,Kun Li,He Wang,Kaan Akşit
机构: University College London (伦敦大学学院); Hong Kong Baptist University (香港浸会大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-131] SegDebias: Test-Time Bias Mitigation for ViT-Based CLIP via Segmentation

链接: https://arxiv.org/abs/2511.00523
作者: Fangyu Wu,Yujun Cai
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-132] ID-Composer: Multi-Subject Video Synthesis with Hierarchical Identity Preservation

链接: https://arxiv.org/abs/2511.00511
作者: Panwang Pan,Jingjing Zhao,Yuchen Lin,Chenguo Lin,Chenxin Li,Haopeng Li,Honglei Yan,Tingting Shen,Yadong Mu
机构: Peking University (北京大学); The Chinese University of Hong Kong (香港中文大学); Xiamen University (厦门大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-133] OmniTrack: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback CVPR2025

链接: https://arxiv.org/abs/2511.00510
作者: Kai Luo,Hao Shi,Kunyu Peng,Fei Teng,Sheng Wu,Kaiwei Wang,Kailun Yang
机构: Hunan University (湖南大学); National Engineering Research Center of Robot Visual Perception and Control Technology (机器人视觉感知与控制技术国家工程研究中心); Zhejiang University (浙江大学); School of Electrical and Electronic Engineering, Nanyang Technological University (南洋理工大学电气与电子工程学院); Karlsruhe Institute of Technology (卡尔斯鲁厄理工学院); INSAIT, Sofia University “St. Kliment Ohridski” (INSAIT，索非亚大学“圣克莱门特·奥赫里德斯基”）
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO); Image and Video Processing (eess.IV)
备注: Extended version of CVPR 2025 paper arXiv:2503.04565 . Datasets and code will be made publicly available at this https URL

点击查看摘要

[CV-134] hree-dimensional narrow volume reconstruction method with unconditional stability based on a phase-field Lagrange multiplier approach

链接: https://arxiv.org/abs/2511.00508
作者: Renjun Gao,Xiangjie Kong,Dongting Cai,Boyi Fu,Junxiang Yang
机构: Macau University of Science and Technology (澳门科技大学)
类目: Numerical Analysis (math.NA); Computational Geometry (cs.CG); Computer Vision and Pattern Recognition (cs.CV)
备注: Preprint, 30+ pages; multiple figures and tables; code and data: this https URL intended for submission to a computational mathematics journal

点击查看摘要

[CV-135] VinDr-CXR-VQA: A Visual Question Answering Dataset for Explainable Chest X-Ray Analysis with Multi-Task Learning

链接: https://arxiv.org/abs/2511.00504
作者: Hai-Dang Nguyen,Ha-Hieu Pham,Hao T. Nguyen,Huy-Hieu Pham
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: ISBI submission. Contains 5 pages, 2 figures, and 6 tables. Code data: this https URL

点击查看摘要

[CV-136] Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models

链接: https://arxiv.org/abs/2511.00503
作者: Panwang Pan,Chenguo Lin,Jingjing Zhao,Chenxin Li,Yuchen Lin,Haopeng Li,Honglei Yan,Kairun Wen,Yunlong Lin,Yixuan Yuan,Yadong Mu
机构: Peking University (北京大学); The Chinese University of Hong Kong (香港中文大学); Xiamen University (厦门大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-137] FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts

链接: https://arxiv.org/abs/2511.00480
作者: Weihao Bo,Yanpeng Sun,Yu Wang,Xinyu Zhang,Zechao Li
机构: Nanjing University of Science and Technology (南京理工大学); National University of Singapore (新加坡国立大学); Baidu VIS (百度视觉智能实验室); University of Auckland (奥克兰大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-138] Longitudinal Vestibular Schwannoma Dataset with Consensus-based Human-in-the-loop Annotations

链接: https://arxiv.org/abs/2511.00472
作者: Navodini Wijethilake,Marina Ivory,Oscar MacCormac,Siddhant Kumar,Aaron Kujawa,Lorena Garcia-Foncillas Macias,Rebecca Burger,Amanda Hitchings,Suki Thomson,Sinan Barazi,Eleni Maratos,Rupert Obholzer,Dan Jiang,Fiona McClenaghan,Kazumi Chia,Omar Al-Salihi,Nick Thomas,Steve Connor,Tom Vercauteren,Jonathan Shapey
机构: King’s College London (伦敦国王学院); King’s College Hospital NHS Foundation Trust (伦敦国王学院医院国家医疗服务体系基金会信托)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-139] HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation NEURIPS2025

链接: https://arxiv.org/abs/2511.00468
作者: Panwang Pan,Tingting Shen,Chenxin Li,Yunlong Lin,Kairun Wen,Jingjing Zhao,Yixuan Yuan
机构: Xiamen University (厦门大学); The Chinese University of Hong Kong (香港中文大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to NeurIPS 2025; Project page: [this URL]( this https URL )

点击查看摘要

[CV-140] Weakly Supervised Pneumonia Localization from Chest X-Rays Using Deep Neural Network and Grad-CAM Explanations

链接: https://arxiv.org/abs/2511.00456
作者: Kiran Shahi,Anup Bagale
机构: MBS Survey Software LTD.(MBS调查软件有限公司); Frontline Hospital(前线医院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-141] oxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training NEURIPS2025

链接: https://arxiv.org/abs/2511.00446
作者: Xin Yao,Haiyang Zhao,Yimin Chen,Jiawei Guo,Kecheng Huang,Ming Zhao
机构: Central South University (中南大学); University of Massachusetts Lowell (马萨诸塞大学洛厄尔分校)
类目: Computer Vision and Pattern Recognition (cs.CV); Cryptography and Security (cs.CR); Machine Learning (cs.LG)
备注: Accepted by NeurIPS 2025

点击查看摘要

[CV-142] Region-Aware Reconstruction Strategy for Pre-training fMRI Foundation Model

链接: https://arxiv.org/abs/2511.00443
作者: Ruthwik Reddy Doodipala,Pankaj Pandey,Carolina Torres Rojas,Manob Jyoti Saikia,Ranganatha Sitaram
机构: St. Jude Children’s Research Hospital (圣犹大儿童研究医院); The University of Memphis (孟菲斯大学)
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-143] Enhancing Frequency Forgery Clues for Diffusion-Generated Image Detection

链接: https://arxiv.org/abs/2511.00429
作者: Daichi Zhang,Tong Zhang,Shiming Ge,Sabine Süsstrunk
机构: EPFL (瑞士联邦理工学院); Chinese Academy of Sciences (中国科学院); University of Chinese Academy of Sciences (中国科学院大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-144] Leverag ing Hierarchical Image-Text Misalignment for Universal Fake Image Detection

链接: https://arxiv.org/abs/2511.00427
作者: Daichi Zhang,Tong Zhang,Jianmin Bao,Shiming Ge,Sabine Süsstrunk
机构: EPFL (瑞士联邦理工学院); Microsoft Research Asia (微软亚洲研究院); Chinese Academy of Sciences (中国科学院); University of Chinese Academy of Sciences (中国科学院大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-145] LGCA: Enhancing Semantic Representation via Progressive Expansion

链接: https://arxiv.org/abs/2511.00419
作者: Thanh Hieu Cao,Trung Khang Tran,Gia Thinh Pham,Tuong Nghiem Diep,Thanh Binh Nguyen
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 15 pages, 5 figures, to appear in SoICT 2025

点击查看摘要

[CV-146] Enhancing Adversarial Transferability by Balancing Exploration and Exploitation with Gradient-Guided Sampling ICCV2025

链接: https://arxiv.org/abs/2511.00411
作者: Zenghao Niu,Weicheng Xie,Siyang Song,Zitong Yu,Feng Liu,Linlin Shen
机构: Shenzhen University (深圳大学); Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) (广东省人工智能与数字经济发展实验室（深圳）); Guangdong Provincial Key Laboratory of Intelligent Information Processing (广东省智能信息处理重点实验室); University of Exeter (埃克塞特大学); Great Bay University (大海大学); Computer Vision Institute, School of Artificial Intelligence (计算机视觉研究所，人工智能学院)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: accepted by iccv 2025

点击查看摘要

[CV-147] CoT-Saliency: Unified Chain-of-Thought Reasoning for Heterogeneous Saliency Tasks

链接: https://arxiv.org/abs/2511.00396
作者: Long Li,Shuichen Ji,Ziyang Luo,Nian Liu,Dingwen Zhang,Junwei Han
机构: Northwestern Polytechnical University (西北工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 14 pages,10 figures

点击查看摘要

[CV-148] SonarSweep: Fusing Sonar and Vision for Robust 3D Reconstruction via Plane Sweeping

链接: https://arxiv.org/abs/2511.00392
作者: Lingpeng Chen,Jiakun Tang,Apple Pui-Yi Chui,Ziyang Hong,Junfeng Wu
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 9 figures, conference

点击查看摘要

[CV-149] VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning

链接: https://arxiv.org/abs/2511.00391
作者: Xuanle Zhao,Deyang Jiang,Zhixiong Zeng,Lei Chen,Haibo Qiu,Jing Huang,Yufeng Zhong,Liming Zheng,Yilin Cao,Lin Ma
机构: Meituan(美团)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Preprint Version, Work in Progress

点击查看摘要

[CV-150] Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models : Benchmark Datasets and Beyond

链接: https://arxiv.org/abs/2511.00389
作者: Fan Zhang,Haoxuan Li,Shengju Qian,Xin Wang,Zheng Lian,Hao Wu,Zhihong Zhu,Yuan Gao,Qiankun Li,Yefeng Zheng,Zhouchen Lin,Pheng-Ann Heng
机构: The Chinese University of Hong Kong (香港中文大学); Peking University (北京大学); Tencent (腾讯); Institute of Automation, Chinese Academy of Sciences (中国科学院自动化研究所); Tsinghua University (清华大学); Nanyang Technological University (南洋理工大学); Westlake University (西湖大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-151] VisionCAD: An Integration-Free Radiology Copilot Framework

链接: https://arxiv.org/abs/2511.00381
作者: Jiaming Li,Junlei Wu,Sheng Wang,Honglin Xiong,Jiangdong Cai,Zihao Zhao,Yitao Zhu,Yuan Yin,Dinggang Shen,Qian Wang
机构: ShanghaiTech University (上海科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Human-Computer Interaction (cs.HC)
备注:

点击查看摘要

[CV-152] Who Can We Trust? Scope-Aware Video Moment Retrieval with Multi-Agent Conflict

链接: https://arxiv.org/abs/2511.00370
作者: Chaochen Wu,Guan Luo,Meiyun Zuo,Zhitao Fan
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-153] Oitijjo-3D: Generative AI Framework for Rapid 3D Heritage Reconstruction from Street View Imagery CEC

链接: https://arxiv.org/abs/2511.00362
作者: Momen Khandoker Ope,Akif Islam,Mohd Ruhul Ameen,Abu Saleh Musa Miah,Md Rashedul Islam,Jungpil Shin
机构: University of Rajshahi, Bangladesh; Marshall University, USA; University of Aizu, Japan; University of Asia Pacific, Bangladesh
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Graphics (cs.GR)
备注: 6 Pages, 4 figures, 2 Tables, Submitted to ICECTE 2026

点击查看摘要

[CV-154] ransfer Learning for Onboard Cloud Segmentation in Thermal Earth Observation: From Landsat to a CubeSat Constellation ICML

链接: https://arxiv.org/abs/2511.00357
作者: Niklas Wölki,Lukas Kondmann,Christian Mollière,Martin Langer,Julia Gottfriedsen,Martin Werner
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: This work was presented at the TerraBytes Workshop at the 42nd International Conference on Machine Learning. This version is not part of the official ICML proceedings

点击查看摘要

[CV-155] Detecting AI-Generated Images via Diffusion Snap-Back Reconstruction: A Forensic Approach CEC

链接: https://arxiv.org/abs/2511.00352
作者: Mohd Ruhul Ameen,Akif Islam
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 6 pages, 8 figures, 4 Tables, submitted to ICECTE 2026

点击查看摘要

[CV-156] OSMGen: Highly Controllable Satellite Image Synthesis using OpenStreetMap Data NEURIPS2025

链接: https://arxiv.org/abs/2511.00345
作者: Amir Ziashahabi,Narges Ghasemi,Sajjad Shahabi,John Krumm,Salman Avestimehr,Cyrus Shahabi
机构: University of Southern California (南加州大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Accepted at NeurIPS 2025 UrbanAI Workshop

点击查看摘要

[CV-157] Federated Dialogue-Semantic Diffusion for Emotion Recognition under Incomplete Modalities

链接: https://arxiv.org/abs/2511.00344
作者: Xihang Qiu,Jiarong Cheng,Yuhao Fang,Wanpeng Zhang,Yao Lu,Ye Zhang,Chun Li
机构: Shenzhen MSU-BIT University (深圳北理莫斯科大学); Beijing Institude of Technology (北京理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-158] A DeepONet joint Neural Tangent Kernel Hybrid Framework for Physics-Informed Inverse Source Problems and Robust Image Reconstruction

链接: https://arxiv.org/abs/2511.00338
作者: Yuhao Fang,Zijian Wang,Yao Lu,Ye Zhang,Chun Li
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-159] Beyond ImageNet: Understanding Cross-Dataset Robustness of Lightweight Vision Models

链接: https://arxiv.org/abs/2511.00335
作者: Weidong Zhang,Pak Lun Kevin Ding,Huan Liu
机构: Arizona State University (亚利桑那州立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 10 pages, 5 tables, 1 figure, 3 equations, 11 mobile models, 7 datasets

点击查看摘要

[CV-160] owards Automated Petrography

链接: https://arxiv.org/abs/2511.00328
作者: Isai Daniel Chacón,Paola Ruiz Puentes,Jillian Pearse,Pablo Arbeláez
机构: Universidad de los Andes, Colombia (安第斯大学, 哥伦比亚); California State University, Long Beach (加州州立大学长滩分校)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-161] Multi-View Consistent Human Image Customization via In-Context Learning

链接: https://arxiv.org/abs/2511.00293
作者: Hengjia Li,Jianjin Xu,Keli Cheng,Lei Wang,Ning Bi,Boxi Wu,Fernando De la Torre,Deng Cai
机构: Zhejiang University (浙江大学); Carnegie Mellon University (卡内基梅隆大学); Qualcomm Inc. (高通公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-162] FedReplay: A Feature Replay Assisted Federated Transfer Learning Framework for Efficient and Privacy-Preserving Smart Agriculture

链接: https://arxiv.org/abs/2511.00269
作者: Long Li,Jiajia Li,Dong Chen,Lina Pu,Haibo Yao,Yanbo Huang
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-163] Spot The Ball: A Benchmark for Visual Social Inference

链接: https://arxiv.org/abs/2511.00261
作者: Neha Balamurugan,Sarah Wu,Adam Chun,Gabe Gaw,Cristobal Eyzaguirre,Tobias Gerstenberg
机构: Stanford University (斯坦福大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Human-Computer Interaction (cs.HC)
备注:

点击查看摘要

[CV-164] MambaNetLK: Enhancing Colonoscopy Point Cloud Registration with Mamba

链接: https://arxiv.org/abs/2511.00260
作者: Linzhe Jiang,Jiayuan Huang,Sophia Bano,Matthew J. Clarkson,Zhehua Mao,Mobarak I. Hoque
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 12 pages, 4 figures, 3 tables, IPCAI conference

点击查看摘要

[CV-165] BeetleFlow: An Integrative Deep Learning Pipeline for Beetle Image Processing NEURIPS2025

链接: https://arxiv.org/abs/2511.00255
作者: Fangxun Liu,S M Rayeed,Samuel Stevens,Alyson East,Cheng Hsuan Chiang,Colin Lee,Daniel Yi,Junke Yang,Tejas Naik,Ziyi Wang,Connor Kilrain,Elijah H Buckwalter,Jiacheng Hou,Saul Ibaven Bueno,Shuheng Wang,Xinyue Ma,Yifan Liu,Zhiyuan Tao,Ziheng Zhang,Eric Sokol,Michael Belitz,Sydne Record,Charles V. Stewart,Wei-Lun Chao
机构: The Ohio State University (俄亥俄州立大学); Rensselaer Polytechnic Institute (伦斯勒理工学院); The University of Maine (缅因大学); National Ecological Observatory Network (NEON), Battelle (国家生态观测网络(巴特尔公司)); Michigan State University (密歇根州立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 4 pages, NeurIPS 2025 Workshop Imageomics

点击查看摘要

[CV-166] Merlin L48 Spectrogram Dataset NEURIPS2025

链接: https://arxiv.org/abs/2511.00252
作者: Aaron Sun,Subhransu Maji,Grant Van Horn
机构: University of Massachusetts Amherst (马萨诸塞大学阿默斯特分校)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Track on Datasets and Benchmarks

点击查看摘要

[CV-167] Object-Aware 4D Human Motion Generation

链接: https://arxiv.org/abs/2511.00248
作者: Shurui Gui,Deep Anil Patel,Xiner Li,Martin Renqiang Min
机构: Texas A&M University (德克萨斯农工大学); NEC Laboratories America (美国电气公司实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR)
备注:

点击查看摘要

[CV-168] Melanoma Classification Through Deep Ensemble Learning and Explainable AI

链接: https://arxiv.org/abs/2511.00246
作者: Wadduwage Shanika Perera,ABM Islam,Van Vung Pham,Min Kyung An
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: Publisher-formatted version provided under CC BY-NC-ND 4.0 license. Original source produced by SciTePress

点击查看摘要

[CV-169] Hyperbolic Optimal Transport

链接: https://arxiv.org/abs/2511.00244
作者: Yan Bin Ng,Xianfeng Gu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 65 pages, 21 figures

点击查看摘要

[CV-170] owards 1000-fold Electron Microscopy Image Compression for Connectomics via VQ-VAE with Transformer Prior

链接: https://arxiv.org/abs/2511.00231
作者: Fuming Yang,Yicong Li,Hanspeter Pfister,Jeff W. Lichtman,Yaron Meirovitch
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-171] DM-QPMNET: Dual-modality fusion network for cell segmentation in quantitative phase microscopy

链接: https://arxiv.org/abs/2511.00218
作者: Rajatsubhra Chakraborty,Ana Espinosa-Momox,Riley Haskin,Depeng Xu,Rosario Porras-Aguilar
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 5 pages, 4 figures

点击查看摘要

[CV-172] An Efficient and Generalizable Transfer Learning Method for Weather Condition Detection on Ground Terminals

链接: https://arxiv.org/abs/2511.00211
作者: Wenxuan Zhang,Peng Hu
机构: Center for Computational Mathematics, Faculty of Mathematics, University of Waterloo, Canada (计算数学中心，数学系，滑铁卢大学，加拿大); Department of Electrical and Computer Engineering, University of Manitoba, Canada (电气与计算机工程系，曼尼托巴大学，加拿大)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-173] A Retrospect to Multi-prompt Learning across Vision and Language ICCV

链接: https://arxiv.org/abs/2511.00191
作者: Ziliang Chen,Xin Huang,Quanlong Guan,Liang Lin,Weiqi Luo
机构: Jinan University (暨南大学); Sun Yat-sen University (中山大学); Pazhou Laboratory (琶洲实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: ICCV

点击查看摘要

[CV-174] From Evidence to Verdict: An Agent -Based Forensic Framework for AI-Generated Image Detection

链接: https://arxiv.org/abs/2511.00181
作者: Mengfei Liang,Yiting Qu,Yukun Jiang,Michael Backes,Yang Zhang
机构: CISPA Helmholtz Center for Information Security (信息安全研究中心)
类目: Computer Vision and Pattern Recognition (cs.CV); Cryptography and Security (cs.CR)
备注: 20 pages, 6 figures

点击查看摘要

[CV-175] CompAgent : An Agent ic Framework for Visual Compliance Verification

链接: https://arxiv.org/abs/2511.00171
作者: Rahul Ghosh,Baishali Chaudhury,Hari Prasanna Das,Meghana Ashok,Ryan Razkenari,Sungmin Hong,Chun-Hao Liu
机构: Amazon Web Services(亚马逊网络服务)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Under review

点击查看摘要

[CV-176] BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing NEURIPS2025

链接: https://arxiv.org/abs/2511.00143
作者: Jinsu Kim,Yunhun Nam,Minseon Kim,Sangpil Kim,Jongheon Jeong
机构: Korea University (韩国大学); Microsoft Research Montréal (微软研究院蒙特利尔)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 36 pages; NeurIPS 2025; Code is available at this https URL

点击查看摘要

[CV-177] FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding

链接: https://arxiv.org/abs/2511.00141
作者: Janghoon Cho,Jungsoo Lee,Munawar Hayat,Kyuwoong Hwang,Fatih Porikli,Sungha Choi
机构: 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)
备注:

点击查看摘要

[CV-178] Integrating ConvNeXt and Vision Transformers for Enhancing Facial Age Estimation

链接: https://arxiv.org/abs/2511.00123
作者: Gaby Maroun,Salah Eddine Bekhouche,Fadi Dornaika
机构: University of the Basque Country(巴斯克大学); IKERBASQUE
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-179] VLM6D: VLM based 6Dof Pose Estimation based on RGB-D Images

链接: https://arxiv.org/abs/2511.00120
作者: Md Selim Sarowar,Sungho Kim
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: This paper has been accepted to IEIE( The Institute Of Electronics and Information Engineering, South Korea) Fall,2025 Conference

点击查看摘要

[CV-180] End-to-End Framework Integrating Generative AI and Deep Reinforcement Learning for Autonomous Ultrasound Scanning

链接: https://arxiv.org/abs/2511.00114
作者: Hanae Elmekki,Amanda Spilkin,Ehsan Zakeri,Antonela Mariel Zanuttini,Ahmed Alagha,Hani Sami,Jamal Bentahar,Lyes Kadem,Wen-Fang Xie,Philippe Pibarot,Rabeb Mizouni,Hadi Otrok,Azzam Mourad,Sami Muhaidat
机构: Concordia University (康考迪亚大学); Université Laval (拉瓦尔大学); Ontario Tech University (安大略理工大学); Khalifa University (哈利法大学); Lebanese American University (美国大学黎巴嫩分校)
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-181] Chain of Time: In-Context Physical Simulation with Image Generation Models

链接: https://arxiv.org/abs/2511.00110
作者: YingQiao Wang,Eric Bigelow,Boyi Li,Tomer Ullman
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-182] AI Powered High Quality Text to Video Generation with Enhanced Temporal Consistency

链接: https://arxiv.org/abs/2511.00107
作者: Piyushkumar Patel
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
备注:

点击查看摘要

[CV-183] FreeSliders: Training-Free Modality-Agnostic Concept Sliders for Fine-Grained Diffusion Control in Images Audio and Video

链接: https://arxiv.org/abs/2511.00103
作者: Rotem Ezra,Hedi Zisling,Nimrod Berman,Ilan Naiman,Alexey Gorkor,Liran Nochumsohn,Eliya Nachmani,Omri Azencot
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-184] Deep recurrent-convolutional neural network learning and physics Kalman filtering comparison in dynamic load identification ALT

链接: https://arxiv.org/abs/2511.00100
作者: Marios Impraimakis
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Signal Processing (eess.SP); Systems and Control (eess.SY); Applications (stat.AP)
备注: 31 pages, 20 figures, published in Structural Health Monitoring

点击查看摘要

[CV-185] A generative adversarial network optimization method for damage detection and digital twinning by deep AI fault learning: Z24 Bridge structural health monitoring benchmark validation

链接: https://arxiv.org/abs/2511.00099
作者: Marios Impraimakis,Evangelia Nektaria Palkanoglou
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Signal Processing (eess.SP); Systems and Control (eess.SY)
备注: 21 pages, 23 figures, published in Structural and Multidisciplinary Optimization

点击查看摘要

[CV-186] A filtering scheme for confocal laser endomicroscopy (CLE)-video sequences for self-supervised learning

链接: https://arxiv.org/abs/2511.00098
作者: Nils Porsche,Flurin Müller-Diesing,Sweta Banerjee,Miguel Goncalves,Marc Aubreville
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-187] SpinalSAM-R1: A Vision-Language Multimodal Interactive System for Spine CT Segmentation

链接: https://arxiv.org/abs/2511.00095
作者: Jiaming Liu,Dingwei Fan,Junyong Zhao,Chunlin Li,Haipeng Si,Liang Sun
机构: 山东大学(Shandong University); 南京航空航天大学(Nanjing University of Aeronautics and Astronautics)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 2 Tables,5 Figures,16 Equations

点击查看摘要

[CV-188] Self-Improving Vision-Language-Action Models with Data Generation via Residual RL

链接: https://arxiv.org/abs/2511.00091
作者: Wenli Xiao,Haotian Lin,Andy Peng,Haoru Xue,Tairan He,Yuqi Xie,Fengyuan Hu,Jimmy Wu,Zhengyi Luo,Linxi “Jim” Fan,Guanya Shi,Yuke Zhu
机构: NVIDIA; CMU; UC Berkeley; UT Austin
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: 26 pages

点击查看摘要

[CV-189] LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation NEURIPS2025

链接: https://arxiv.org/abs/2511.00090
作者: Huanlin Gao,Ping Chen,Fuyuan Shi,Chao Tan,Zhaoxiang Liu,Fang Zhao,Kai Wang,Shiguo Lian
机构: Data Science & Artificial Intelligence Research Institute, China Unicom; Unicom Data Intelligence, China Unicom
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: NeurIPS 2025

点击查看摘要

[CV-190] Habitat and Land Cover Change Detection in Alpine Protected Areas: A Comparison of AI Architectures

链接: https://arxiv.org/abs/2511.00073
作者: Harald Kristen,Daniel Kulmer,Manuela Hirschmugl
机构: University of Graz (格拉茨大学); Joanneum Research (约阿内姆研究所)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-191] LookSync: Large-Scale Visual Product Search System for AI-Generated Fashion Looks KDD

链接: https://arxiv.org/abs/2511.00072
作者: Pradeep M,Ritesh Pallod,Satyen Abrol,Muthu Raman,Ian Anderson
机构: Glance( glance); Glance( glance); Glance( glance); Glance( glance); Glance( glance)
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 4 pages, 5 figures. Accepted at the International Conference on Data Science (IKDD CODS 2025), Demonstration Track. Demo video: this https URL

点击查看摘要

[CV-192] World Simulation with Video Foundation Models for Physical AI

链接: https://arxiv.org/abs/2511.00062
作者: NVIDIA:Arslan Ali,Junjie Bai,Maciej Bala,Yogesh Balaji,Aaron Blakeman,Tiffany Cai,Jiaxin Cao,Tianshi Cao,Elizabeth Cha,Yu-Wei Chao,Prithvijit Chattopadhyay,Mike Chen,Yongxin Chen,Yu Chen,Shuai Cheng,Yin Cui,Jenna Diamond,Yifan Ding,Jiaojiao Fan,Linxi Fan,Liang Feng,Francesco Ferroni,Sanja Fidler,Xiao Fu,Ruiyuan Gao,Yunhao Ge,Jinwei Gu,Aryaman Gupta,Siddharth Gururani,Imad El Hanafi,Ali Hassani,Zekun Hao,Jacob Huffman,Joel Jang,Pooya Jannaty,Jan Kautz,Grace Lam,Xuan Li,Zhaoshuo Li,Maosheng Liao,Chen-Hsuan Lin,Tsung-Yi Lin,Yen-Chen Lin,Huan Ling,Ming-Yu Liu,Xian Liu,Yifan Lu,Alice Luo,Qianli Ma,Hanzi Mao,Kaichun Mo,Seungjun Nah,Yashraj Narang,Abhijeet Panaskar,Lindsey Pavao,Trung Pham,Morteza Ramezanali,Fitsum Reda,Scott Reed,Xuanchi Ren,Haonan Shao,Yue Shen,Stella Shi,Shuran Song,Bartosz Stefaniak,Shangkun Sun,Shitao Tang,Sameena Tasmeen,Lyne Tchapmi,Wei-Cheng Tseng,Jibin Varghese,Andrew Z. Wang,Hao Wang,Haoxiang Wang,Heng Wang,Ting-Chun Wang,Fangyin Wei,Jiashu Xu,Dinghao Yang,Xiaodong Yang,Haotian Ye,Seonghyeon Ye,Xiaohui Zeng,Jing Zhang,Qinsheng Zhang,Kaiwen Zheng,Andrew Zhu,Yuke Zhu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Robotics (cs.RO)
备注:

点击查看摘要

[CV-193] Which LiDAR scanning pattern is better for roadside perception: Repetitive or Non-repetitive?

链接: https://arxiv.org/abs/2511.00060
作者: Zhiqi Qi,Runxin Zhao,Hanyang Zhuang,Chunxiang Wang,Ming Yang
机构: Shanghai Jiao Tong University (上海交通大学); Key Laboratory of System Control and Information Processing, Ministry of Education of China (中国教育部系统控制与信息处理重点实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-194] Enhancing rice leaf images: An overview of image denoising techniques ALT

链接: https://arxiv.org/abs/2511.00046
作者: Rupjyoti Chutia,Dibya Jyoti Bora
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 18 pages, 6 figures. Research Article published in the International Journal of Agricultural and Natural Sciences (IJANS), Vol. 18, Issue 2, 2025. This paper presents a comparative study of image denoising and CLAHE techniques for enhancing rice leaf images corrupted by Gaussian, Salt-and-pepper, Speckle, and Random noise for agricultural analysis

点击查看摘要

[CV-195] Benchmarking Federated Learning Frameworks for Medical Imaging Deployment: A Comparative Study of NVIDIA FLARE Flower and Owkin Substra

链接: https://arxiv.org/abs/2511.00037
作者: Riya Gupta,Alexander Chowdhury,Sahil Nalawade
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Distributed, Parallel, and Cluster Computing (cs.DC)
备注:

点击查看摘要

[CV-196] Mutual Information guided Visual Contrastive Learning

链接: https://arxiv.org/abs/2511.00028
作者: Hanyang Chen,Yanchao Yang
机构: Cranberry-Lemon University (克兰伯里-柠檬大学); University of the Witwatersrand (威特沃特斯兰德大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Tech Report - Undergraduate Thesis - 2023

点击查看摘要

[CV-197] Automating Coral Reef Fish Family Identification on Video Transects Using a YOLOv8-Based Deep Learning Pipeline

链接: https://arxiv.org/abs/2511.00022
作者: Jules Gerard,Leandro Di Bella,Filip Huyghe,Marc Kochzius
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to EUVIP2025, student session

点击查看摘要

[CV-198] Deep Learning Models for Coral Bleaching Classification in Multi-Condition Underwater Image Datasets

链接: https://arxiv.org/abs/2511.00021
作者: Julio Jerison E. Macrohon,Gordon Hung
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 15 pages, 10 figures

点击查看摘要

[CV-199] Generative human motion mimicking through feature extraction in denoising diffusion settings

链接: https://arxiv.org/abs/2511.00011
作者: Alexander Okupnik,Johannes Schneider,Kyriakos Flouris
机构: University of Liechtenstein (列支敦士登大学); University of Cambridge (剑桥大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注:

点击查看摘要

[CV-200] VRScout: Towards Real-Time Autonomous Testing of Virtual Reality Games

链接: https://arxiv.org/abs/2511.00002
作者: Yurun Wu,Yousong Sun,Burkhard Wunsche,Jia Wang,Elliott Wen
机构: 未知
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-201] Few-Shot Multimodal Medical Imaging: A Theoretical Framework

链接: https://arxiv.org/abs/2511.01140
作者: Md Talha Mohsin,Ismail Abdulrashid
机构: 未知
类目: Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Image and Video Processing (eess.IV)
备注: 6 Pages

点击查看摘要

[CV-202] Been There Scanned That: Nostalgia-Driven LiDAR Compression for Self-Driving Cars

链接: https://arxiv.org/abs/2511.00652
作者: Ali Khalid,Jaiaid Mobin,Sumanth Rao Appala,Avinash Maurya,Stephany Berrio Perez,M. Mustafa Rafique,Fawad Ahmad
机构: Rochester Institute of Technology (罗切斯特理工学院); Vellore Institute of Technology (维洛尔理工学院); The University of Sydney (悉尼大学)
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-203] GDROS: A Geometry-Guided Dense Registration Framework for Optical-SAR Images under Large Geometric Transformations

链接: https://arxiv.org/abs/2511.00598
作者: Zixuan Sun,Shuaifeng Zhi,Ruize Li,Jingyuan Xia,Yongxiang Liu,Weidong Jiang
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注: To be published in IEEE Transactions on Geoscience and Remote Sensing (T-GRS) 2025

点击查看摘要

[CV-204] Image-based ground distance detection for crop-residue-covered soil

链接: https://arxiv.org/abs/2511.00548
作者: Baochao Wang,Xingyu Zhang,Qingtao Zong,Alim Pulatov,Shuqi Shang,Dongwei Wang
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR); Systems and Control (eess.SY)
备注: under review at Computers and Electronics in Agriculture

点击查看摘要

[CV-205] Investigating Label Bias and Representational Sources of Age-Related Disparities in Medical Segmentation

链接: https://arxiv.org/abs/2511.00477
作者: Aditya Parikh,Sneha Das,Aasa Feragen
机构: 未知
类目: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: Submitted to ISBI 2026

点击查看摘要

[CV-206] owards Reliable Pediatric Brain Tumor Segmentation: Task-Specific nnU-Net Enhancements

链接: https://arxiv.org/abs/2511.00449
作者: Xiaolong Li,Zhi-Qin John Xu,Yan Ren,Tianming Qiu,Xiaowen Wang
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-207] GeneFlow: Translation of Single-cell Gene Expression to Histopathological Images via Rectified Flow

链接: https://arxiv.org/abs/2511.00119
作者: Mengbo Wang,Shourya Verma,Aditya Malusare,Luopin Wang,Yiyang Lu,Vaneet Aggarwal,Mario Sola,Ananth Grama,Nadia Atallah Lanman
机构: Purdue University (普渡大学)
类目: Quantitative Methods (q-bio.QM); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

人工智能

[AI-0] rove: A Flexible Toolkit for Dense Retrieval

链接: https://arxiv.org/abs/2511.01857
作者: Reza Esfandiarpoor,Max Zuo,Stephen H. Bach
机构: 未知
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-1] SmartMLOps Studio: Design of an LLM -Integrated IDE with Automated MLOps Pipelines for Model Development and Monitoring

链接: https://arxiv.org/abs/2511.01850
作者: Jiawei Jin,Yingxin Su,Xiaotong Zhu
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-2] A Detailed Study on LLM Biases Concerning Corporate Social Responsibility and Green Supply Chains

链接: https://arxiv.org/abs/2511.01840
作者: Greta Ontrup,Annika Bush,Markus Pauly,Meltem Aksoy
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
备注: 37 pages, 2 figures

点击查看摘要

[AI-3] Efficient Vector Symbolic Architectures from Histogram Recovery

【速读】：该论文旨在解决向量符号架构（Vector Symbolic Architectures, VSAs）中因随机线性码在噪声下难以解码而导致的恢复（recovery）能力受限问题，即如何在保持近正交性（quasi-orthogonality）的前提下实现高效且鲁棒的信息对象及其属性的检索。解决方案的关键在于引入编码理论工具，具体为采用Reed-Solomon码与Hadamard码的级联结构，利用其互近正交的码字特性提升抗噪性能，并将恢复问题建模为“直方图恢复”（histogram recovery）——即从有限域上的N个直方图中找出一组长度为N的Reed-Solomon码字，使其逐元素符号频率符合给定分布。作者通过关联列表译码算法提出该问题的最优解法，并分析了其噪声鲁棒性，从而构建了一个无需启发式或训练、具有形式化保证的抗噪VSAs系统，相较传统Hadamard码方案在参数上有所优化。

链接: https://arxiv.org/abs/2511.01838
作者: Zirui Deng,Netanel Raviv
机构: 未知
类目: Information Theory (cs.IT); Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE)
备注:

点击查看摘要

Abstract:Vector symbolic architectures (VSAs) are a family of information representation techniques which enable composition, i.e., creating complex information structures from atomic vectors via binding and superposition, and have recently found wide ranging applications in various neurosymbolic artificial intelligence (AI) systems. Recently, Raviv proposed the use of random linear codes in VSAs, suggesting that their subcode structure enables efficient binding, while preserving the quasi-orthogonality that is necessary for neural processing. Yet, random linear codes are difficult to decode under noise, which severely limits the resulting VSA’s ability to support recovery, i.e., the retrieval of information objects and their attributes from a noisy compositional representation. In this work we bridge this gap by utilizing coding theoretic tools. First, we argue that the concatenation of Reed-Solomon and Hadamard codes is suitable for VSA, due to the mutual quasi-orthogonality of the resulting codewords (a folklore result). Second, we show that recovery of the resulting compositional representations can be done by solving a problem we call histogram recovery. In histogram recovery, a collection of N histograms over a finite field is given as input, and one must find a collection of Reed-Solomon codewords of length N whose entry-wise symbol frequencies obey those histograms. We present an optimal solution to the histogram recovery problem by using algorithms related to list-decoding, and analyze the resulting noise resilience. Our results give rise to a noise-resilient VSA with formal guarantees regarding efficient encoding, quasi-orthogonality, and recovery, without relying on any heuristics or training, and while operating at improved parameters relative to similar solutions such as the Hadamard code. Subjects: Information Theory (cs.IT); Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE) Cite as: arXiv:2511.01838 [cs.IT] (or arXiv:2511.01838v1 [cs.IT] for this version) https://doi.org/10.48550/arXiv.2511.01838 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
zh

[AI-4] Dynamic Routing Between Experts: A Data-Efficient Approach to Continual Learning in Vision-Language Models

【速读】：该论文旨在解决视觉语言模型（Vision-Language Models, VLMs）在顺序微调新任务时出现的灾难性遗忘问题，即模型在学习新任务后会显著退化已习得的基础能力与特定任务性能。解决方案的关键在于提出一种基于路由（routing-based）的方法，通过动态分配网络路径来整合新任务，从而在不同时访问所有任务数据的情况下保留预训练阶段获得的基础知识。该方法不仅避免了传统多任务学习所需的高计算和数据开销，还实现了对通用基准（如ChartQA、MMBench、DocVQA）性能的稳定保持，并提升专用任务准确率，同时展现出良好的可扩展性和跨模态迁移能力。

链接: https://arxiv.org/abs/2511.01831
作者: Jay Mohta,Kenan Emir Ak,Dimitrios Dimitriadis,Yan Xu,Mingwei Shen
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

Abstract:Vision-Language Models (VLMs) suffer from catastrophic forgetting when sequentially fine-tuned on new tasks, degrading performance on previously learned foundational and task-specific capabilities. While multi-task learning can mitigate forgetting, it requires simultaneous access to all datasets and imposes computational overhead that scales linearly with the number of tasks. In this work, we introduce a routing-based approach that enables the integration of new tasks while preserving the foundational knowledge acquired during pretraining. We evaluate our method using InternVL-2 models (2B and 8B parameters) and demonstrate that routing preserves the model’s foundational capabilities by maintaining performance on general-purpose benchmarks such as ChartQA, MMBench, and DocVQA, while simultaneously improving accuracy on specialized tasks. Importantly, our approach achieves this without requiring concurrent access to data from all tasks, avoiding the significant computational and data overhead associated with traditional multi-task learning. We further conduct extensive ablation studies to evaluate the scalability and robustness of routing-based learning, showing that the approach is resilient to a growing number of tasks and performs particularly well when new tasks are semantically related. Finally, we show that the routing mechanism enables superior cross-modal transfer between language and vision capabilities, allowing knowledge learned in one modality to enhance performance in another capability not achieved by existing continual learning methods.
zh

[AI-5] Simulating Environments with Reasoning Models for Agent Training

链接: https://arxiv.org/abs/2511.01824
作者: Yuetai Li,Huseyin A Inan,Xiang Yue,Wei-Ning Chen,Lukas Wutschitz,Janardhan Kulkarni,Radha Poovendran,Robert Sim,Saravan Rajmohan
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-6] Machine and Deep Learning for Indoor UWB Jammer Localization

链接: https://arxiv.org/abs/2511.01819
作者: Hamed Fard,Mahsa Kholghi,Benedikt Groß,Gerhard Wunder
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Accepted at the 20th International Conference on Risks and Security of Internet and Systems (CRiSIS 2025, Gatineau-Canada, this https URL ). The paper will soon be published as post-proceedings in Springer’s LNCS

点击查看摘要

[AI-7] GenDexHand: Generative Simulation for Dexterous Hands

链接: https://arxiv.org/abs/2511.01791
作者: Feng Chen,Zhuxiu Xu,Tianzhe Chu,Xunzhe Zhou,Li Sun,Zewen Wu,Shenghua Gao,Zhongyu Li,Yanchao Yang,Yi Ma
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-8] Context-Guided Decompilation: A Step Towards Re-executability

链接: https://arxiv.org/abs/2511.01763
作者: Xiaohan Wang,Yuxin Hu,Kevin Leach
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-9] SM-based Semantics for Answer Set Programs Containing Conditional Literals and Arithmetic DATE

链接: https://arxiv.org/abs/2511.01753
作者: Zachary Hansen,Yuliya Lierler
机构: 未知
类目: Logic in Computer Science (cs.LO); Artificial Intelligence (cs.AI); Programming Languages (cs.PL)
备注: This version corrects the review of tau for negated atoms, and clarifies the distinction between global and local variables in conditional literals (the supporting proofs are also updated accordingly)

点击查看摘要

[AI-10] Scam Shield: Multi-Model Voting and Fine-Tuned LLM s Against Adversarial Attacks

链接: https://arxiv.org/abs/2511.01746
作者: Chen-Wei Chang,Shailik Sarkar,Hossein Salemi,Hyungmin Kim,Shutonu Mitra,Hemant Purohit,Fengxiu Zhang,Michin Hong,Jin-Hee Cho,Chang-Tien Lu
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注: 8 pages

点击查看摘要

[AI-11] An Open-Access Benchmark of Statistical and Machine-Learning Anomaly Detection Methods for Battery Applications

链接: https://arxiv.org/abs/2511.01745
作者: Mei-Chin Pang,Suraj Adhikari,Takuma Kasahara,Nagihiro Haba,Saneyuki Ohno
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Methodology (stat.ME)
备注:

点击查看摘要

[AI-12] owards Efficient Federated Learning of Networked Mixture-of-Experts for Mobile Edge Computing

链接: https://arxiv.org/abs/2511.01743
作者: Song Gao,Shusen Jing,Shuai Zhang,Yue Wang,Xiangwei Zhou,Songyang Zhang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI)
备注:

点击查看摘要

[AI-13] Solution Space Topology Guides CMTS Search

【速读】：该论文旨在解决搜索引导型人工智能中的核心问题：在谜题求解任务中，应采用何种拓扑结构来指导蒙特卡洛树搜索（Monte Carlo Tree Search, MCTS）以提升搜索效率。此前研究尝试使用网格拓扑（grid topology）——即基于单元格连接性的拉普拉斯谱特性——作为MCTS的引导信号，但未发现性能提升。作者识别出根本原因在于网格拓扑在所有实例中保持不变，无法反映任务难度差异。解决方案的关键在于改用解空间拓扑（solution space topology）——即由检测到的模式规则约束下有效颜色分配构成的结构——替代传统的问题空间拓扑。具体实现上，通过构建兼容图（compatibility graph），其中节点为（单元格，颜色）对，边表示满足模式约束的兼容赋值，从而编码解空间结构；进一步提取可变的拓扑特征（如代数连通性、刚性、颜色结构），并将其整合进MCTS节点选择机制中，采用归一化得分策略增强搜索导向性。实验证明，代数连通性是主导信号，表明拓扑确实影响搜索效果，但必须是正确的拓扑——即解空间结构而非问题空间结构。

链接: https://arxiv.org/abs/2511.01701
作者: Mirco A. Mannucci
机构: 未知
类目: Computational Engineering, Finance, and Science (cs.CE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 15 pages, 3 figures

点击查看摘要

Abstract:A fundamental question in search-guided AI: what topology should guide Monte Carlo Tree Search (MCTS) in puzzle solving? Prior work applied topological features to guide MCTS in ARC-style tasks using grid topology – the Laplacian spectral properties of cell connectivity – and found no benefit. We identify the root cause: grid topology is constant across all instances. We propose measuring \emphsolution space topology instead: the structure of valid color assignments constrained by detected pattern rules. We build this via compatibility graphs where nodes are (cell, color) pairs and edges represent compatible assignments under pattern constraints. Our method: (1) detect pattern rules automatically with 100% accuracy on 5 types, (2) construct compatibility graphs encoding solution space structure, (3) extract topological features (algebraic connectivity, rigidity, color structure) that vary with task difficulty, (4) integrate these features into MCTS node selection via sibling-normalized scores. We provide formal definitions, a rigorous selection formula, and comprehensive ablations showing that algebraic connectivity is the dominant signal. The work demonstrates that topology matters for search – but only the \emphright topology. For puzzle solving, this is solution space structure, not problem space structure. Comments: 15 pages, 3 figures Subjects: Computational Engineering, Finance, and Science (cs.CE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2511.01701 [cs.CE] (or arXiv:2511.01701v1 [cs.CE] for this version) https://doi.org/10.48550/arXiv.2511.01701 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
zh

[AI-14] Bayesian Natural Gradient Fine-Tuning of CLIP Models via Kalman Filtering

链接: https://arxiv.org/abs/2511.01694
作者: Hossein Abdi,Mingfei Sun,Wei Pan
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-15] Student Engagement in AI Assisted Complex Problem Solving: A Pilot Study of Human AI Rubiks Cube Collaboration

链接: https://arxiv.org/abs/2511.01683
作者: Kirk Vanacore,Jaclyn Ocumpaugh,Forest Agostinelli,Dezhi Wu,Sai Vuruma,Matt Irvin
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-16] Hybrid Retrieval-Augmented Generation Agent for Trustworthy Legal Question Answering in Judicial Forensics

【速读】：该论文旨在解决司法场景下法律问答（Legal QA）系统中生成式 AI（Generative AI）易产生幻觉（hallucination）以及静态知识库难以及时更新法规与判例的问题。其核心解决方案是提出一种混合法律问答代理（hybrid legal QA agent），关键在于：1）优先检索机制，即当可信法律资源库提供相关证据时，采用检索增强生成（Retrieval-Augmented Generation, RAG）生成答案；2）多模型集成策略，在无可靠检索结果时，由多个大语言模型（LLMs）生成候选答案，并通过专用选择器评分后选取最优解；3）人机协同的知识更新机制，高质量答案经人工审核后回写至知识库，实现动态演进与溯源追踪。实验证明该方法在F1、ROUGE-L及LLM-as-a-Judge指标上显著优于单一模型和纯RAG方案，有效降低幻觉并提升法律合规性。

链接: https://arxiv.org/abs/2511.01668
作者: Yueqing Xi,Yifan Bai,Huasen Luo,Weiliang Wen,Hui Liu,Haoliang Li
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

Abstract:As artificial intelligence permeates judicial forensics, ensuring the veracity and traceability of legal question answering (QA) has become critical. Conventional large language models (LLMs) are prone to hallucination, risking misleading guidance in legal consultation, while static knowledge bases struggle to keep pace with frequently updated statutes and case law. We present a hybrid legal QA agent tailored for judicial settings that integrates retrieval-augmented generation (RAG) with multi-model ensembling to deliver reliable, auditable, and continuously updatable counsel. The system prioritizes retrieval over generation: when a trusted legal repository yields relevant evidence, answers are produced via RAG; otherwise, multiple LLMs generate candidates that are scored by a specialized selector, with the top-ranked answer returned. High-quality outputs then undergo human review before being written back to the repository, enabling dynamic knowledge evolution and provenance tracking. Experiments on the Law_QA dataset show that our hybrid approach significantly outperforms both a single-model baseline and a vanilla RAG pipeline on F1, ROUGE-L, and an LLM-as-a-Judge metric. Ablations confirm the complementary contributions of retrieval prioritization, model ensembling, and the human-in-the-loop update mechanism. The proposed system demonstrably reduces hallucination while improving answer quality and legal compliance, advancing the practical landing of media forensics technologies in judicial scenarios.
zh

[AI-17] he Ghost in the Keys: A Disklavier Demo for Human-AI Musical Co-Creativity

链接: https://arxiv.org/abs/2511.01663
作者: Louis Bradshaw,Alexander Spangher,Stella Biderman,Simon Colton
机构: 未知
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注:

点击查看摘要

[AI-18] IVGAE-TAMA-BO: A novel temporal dynamic variational graph model for link prediction in global food trade networks with momentum structural memory and Bayesian optimization

链接: https://arxiv.org/abs/2511.01639
作者: Sicheng Wang,Shuhao Chen,Jingran Zhou,Chengyi Tu
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: 26pages,6figures

点击查看摘要

[AI-19] Prompt Injection as an Emerging Threat: Evaluating the Resilience of Large Language Models

链接: https://arxiv.org/abs/2511.01634
作者: Daniyal Ganiuly,Assel Smaiyl
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注: 10 pages, 6 figures

点击查看摘要

[AI-20] Scaling Graph Chain-of-Thought Reasoning : A Multi-Agent Framework with Efficient LLM Serving

链接: https://arxiv.org/abs/2511.01633
作者: Chengying Huan,Ziheng Meng,Yongchao Liu,Zhengyi Yang,Yun Zhu,Yue Yun,Shipeng Li,Rong Gu,Xiabao Wu,Haitao Zhang,Chuntao Hong,Shaonan Ma,Guihai Chen,Chen Tian
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-21] Federated Cyber Defense: Privacy-Preserving Ransomware Detection Across Distributed Systems

链接: https://arxiv.org/abs/2511.01583
作者: Daniel M. Jimenez-Gutierrez,Enrique Zuazua,Joaquin Del Rio,Oleksii Sliusarenko,Xabi Uribe-Etxebarria
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-22] ExplicitLM: Decoupling Knowledge from Parameters via Explicit Memory Banks

【速读】：该论文旨在解决大语言模型（Large Language Models, LLMs）中存在的知识陈旧性（knowledge staleness）和可解释性不足的问题，其根源在于模型通过参数耦合方式隐式存储知识，导致难以进行针对性更新与推理过程的透明化。解决方案的关键在于提出ExplicitLM架构，该架构引入一个百万级规模的外部记忆库（memory bank），以人类可读的token序列形式显式存储知识，并设计了一种可微分的两阶段检索机制：首先利用产品键分解（product key decomposition）实现粗粒度过滤，将复杂度从 $\mathcal{O}(N \cdot |I|)$ 降低至 $\mathcal{O}(\sqrt{N} \cdot |I|)$ ；其次采用Gumbel-Softmax进行细粒度匹配，支持端到端训练。此外，受双系统认知理论启发，将知识分为20%冻结的显式事实与80%可学习的隐式模式，通过指数移动平均（Exponential Moving Average, EMA）更新维持稳定性，从而在保持竞争力的同时显著提升知识透明度与可维护性。

链接: https://arxiv.org/abs/2511.01581
作者: Chengzhang Yu,Zening Lu,Chenyang Zheng,Chiyue Wang,Yiming Zhang,Zhanpeng Jin
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: 12pages, 4figures

点击查看摘要

Abstract:Large language models suffer from knowledge staleness and lack of interpretability due to implicit knowledge storage across entangled network parameters, preventing targeted updates and reasoning transparency. We propose ExplicitLM, a novel architecture featuring a million-scale external memory bank storing human-readable knowledge as token sequences, enabling direct inspection and modification. We design a differentiable two-stage retrieval mechanism with efficient coarse-grained filtering via product key decomposition (reducing complexity from \mathcalO(N \cdot |I|) to \mathcalO(\sqrtN \cdot |I|) ) and fine-grained Gumbel-Softmax matching for end-to-end training. Inspired by dual-system cognitive theory, we partition knowledge into frozen explicit facts (20%) and learnable implicit patterns (80%), maintained through Exponential Moving Average updates for stability. ExplicitLM achieves up to 43.67% improvement on knowledge-intensive tasks versus standard Transformers, with 3.62 \times gains in low-data regimes (10k samples). Analysis shows strong correlations between memory retrieval and performance, with correct predictions achieving 49% higher hit rates. Unlike RAG systems with frozen retrieval, our jointly optimized architecture demonstrates that interpretable, updatable models can maintain competitive performance while providing unprecedented knowledge transparency.
zh

[AI-23] HIT-ROCKET: Hadamard-vector Inner-product Transformer for ROCKET

链接: https://arxiv.org/abs/2511.01572
作者: Wang Hao,Kuang Zhang,Hou Chengyu,Yuan Zhonghao,Tan Chenxing,Fu Weifeng,Zhu Yangying
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-24] Real-time Continual Learning on Intel Loihi 2

链接: https://arxiv.org/abs/2511.01553
作者: Elvin Hajizada,Danielle Rager,Timothy Shea,Leobardo Campos-Macias,Andreas Wild,Eyke Hüllermeier,Yulia Sandamirskaya,Mike Davies
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Neural and Evolutionary Computing (cs.NE)
备注:

点击查看摘要

[AI-25] Analyzing Sustainability Messaging in Large-Scale Corporate Social Media

链接: https://arxiv.org/abs/2511.01550
作者: Ujjwal Sharma,Stevan Rudinac,Ana Mićković,Willemijn van Dolen,Marcel Worring
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-26] PS-Bench: Evaluating AI Agents Tool Planning Scheduling Abilities in Compounding Tasks

【速读】：该论文旨在解决大型语言模型（Large Language Model, LLM）代理在处理复杂现实世界问题时，如何有效进行工具规划（Tool Planning）与调度（Tool Scheduling）的问题。这类问题通常由多个子任务构成，每个子任务需调用不同的基础工具（如网络搜索、地图导航、日历查询等），且要求模型不仅能够识别合适的工具组合，还需优化其执行顺序以提升整体效率。解决方案的关键在于构建一个名为TPS-Bench的基准测试平台，该平台包含200个不同难度级别的复合任务及数百个模型上下文协议（Model Context Protocol, MCP）工具，从而系统评估LLM代理在工具选择与调度上的能力。实验表明，尽管多数模型具备基本的工具规划能力，但在调度策略上存在显著差异；进一步引入强化学习（Reinforcement Learning, RL）方法对调度策略进行优化，在少量训练样本下即可实现执行时间减少14%、任务完成率提升6%的效果，证明了RL在提升调度效率方面的可行性与有效性。

链接: https://arxiv.org/abs/2511.01527
作者: Hanwen Xu,Xuyao Huang,Yuzhe Liu,Kai Yu,Zhijie Deng
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

Abstract:Large language model (LLM) agents have exhibited strong problem-solving competence across domains like research and coding. Yet, it remains underexplored whether LLM agents can tackle compounding real-world problems that require a diverse set of tools to complete. Given a broad, heterogeneous tool repository, LLM agents must not only select appropriate tools based on task planning analysis but also strategically schedule the execution order to ensure efficiency. This paper introduces TPS-Bench to benchmark the ability of LLM agents in solving such problems that demand Tool Planning and Scheduling. TPS-Bench collects 200 compounding tasks of two difficulty levels, based on a tool repository containing hundreds of model context protocol (MCP) tools. In particular, each task is composed of multiple subtasks, such as web search, map navigation, calendar checking, etc., and each subtask can be completed by a basic tool. Our evaluation emphasizes both task completion rate and efficiency. The empirical studies on popular closed-source and open-source LLMs indicate that most models can perform reasonable tool planning, but differ in scheduling. For example, GLM-4.5 achieves an outperforming task completion rate of 64.72% with extensive sequential tool calls, hence suffering from significantly long execution time. By contrast, GPT-4o prioritizes parallel tool calls but achieves only a 45.08% completion rate. Considering reinforcement learning (RL) can be a viable way to improve the scheduling efficiency without compromising performance, we perform an initial study on Qwen3-1.7B and witness a 14% reduction in execution time alongside a 6% gain in task completion rate based on rarely 100 RL training samples. Our code is available this https URL.
zh

[AI-27] MO-SeGMan: Rearrangement Planning Framework for Multi Objective Sequential and Guided Manipulation in Constrained Environments

链接: https://arxiv.org/abs/2511.01476
作者: Cankut Bora Tuncer,Marc Toussaint,Ozgur S. Oguz
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注: 8 pages, 8 figures, website: this https URL

点击查看摘要

[AI-28] DAMBench: A Multi-Modal Benchmark for Deep Learning-based Atmospheric Data Assimilation

【速读】：该论文旨在解决当前基于深度学习的数据同化（Data Assimilation, DA）研究中存在的两大关键问题：一是现有方法多依赖于简化的人工扰动观测数据，难以反映真实大气系统的复杂性；二是缺乏统一的基准测试平台，导致模型间无法进行公平、可复现的比较。其解决方案的核心在于提出首个大规模多模态数据同化基准测试平台DAMBench，该平台整合了来自先进数值预报系统的真实背景场与多源实测观测（如地面气象站和卫星遥感图像），并通过空间重采样和时间对齐处理，构建标准化的数据集与评估协议。DAMBench支持对代表性数据驱动DA模型（包括潜在生成模型和神经过程框架）的系统评估，并引入轻量级多模态插件以验证真实观测融合对基础模型性能的提升效果，从而为未来研究提供可复现、公平且面向实际应用的评估基准。

链接: https://arxiv.org/abs/2511.01468
作者: Hao Wang,Zixuan Weng,Jindong Han,Wei Fan,Hao Liu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

Abstract:Data Assimilation is a cornerstone of atmospheric system modeling, tasked with reconstructing system states by integrating sparse, noisy observations with prior estimation. While traditional approaches like variational and ensemble Kalman filtering have proven effective, recent advances in deep learning offer more scalable, efficient, and flexible alternatives better suited for complex, real-world data assimilation involving large-scale and multi-modal observations. However, existing deep learning-based DA research suffers from two critical limitations: (1) reliance on oversimplified scenarios with synthetically perturbed observations, and (2) the absence of standardized benchmarks for fair model comparison. To address these gaps, in this work, we introduce DAMBench, the first large-scale multi-modal benchmark designed to evaluate data-driven DA models under realistic atmospheric conditions. DAMBench integrates high-quality background states from state-of-the-art forecasting systems and real-world multi-modal observations (i.e., real-world weather stations and satellite imagery). All data are resampled to a common grid and temporally aligned to support systematic training, validation, and testing. We provide unified evaluation protocols and benchmark representative data assimilation approaches, including latent generative models and neural process frameworks. Additionally, we propose a lightweight multi-modal plugin to demonstrate how integrating realistic observations can enhance even simple baselines. Through comprehensive experiments, DAMBench establishes a rigorous foundation for future research, promoting reproducibility, fair comparison, and extensibility to real-world multi-modal scenarios. Our dataset and code are publicly available at this https URL.
zh

[AI-29] From Passive to Proactive: A Multi-Agent System with Dynamic Task Orchestration for Intelligent Medical Pre-Consultation

链接: https://arxiv.org/abs/2511.01445
作者: ChengZhang Yu,YingRu He,Hongyan Cheng,nuo Cheng,Zhixing Liu,Dongxu Mu,Zhangrui Shen,Zhanpeng Jin
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: 14pages, 7 figures, 7 tables

点击查看摘要

[AI-30] Robust Multimodal Sentiment Analysis via Double Information Bottleneck

链接: https://arxiv.org/abs/2511.01444
作者: Huiting Huang,Tieliang Gong,Kai He,Jialun Wu,Erik Cambria,Mengling Feng
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-31] Modulation of temporal decision-making in a deep reinforcement learning agent under the dual-task paradigm NEURIPS2025

链接: https://arxiv.org/abs/2511.01415
作者: Amrapali Pednekar,Álvaro Garrido-Pérez,Yara Khaluf,Pieter Simoens
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: Accepted at CogInterp workshop @ NeurIPS 2025

点击查看摘要

[AI-32] FoldPath: End-to-End Object-Centric Motion Generation via Modulated Implicit Paths IROS2025

链接: https://arxiv.org/abs/2511.01407
作者: Paolo Rabino,Gabriele Tiboni,Tatiana Tommasi
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注: Accepted at 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)

点击查看摘要

[AI-33] Relaxing partition admissibility in Cluster-DAGs: a causal calculus with arbitrary variable clustering NEURIPS2025

链接: https://arxiv.org/abs/2511.01396
作者: Clément Yvernes(APTIKAL),Emilie Devijver(APTIKAL),Adèle H. Ribeiro,Marianne Clausel–Lesourd(IECL),Éric Gaussier(LIG, APTIKAL)
机构: 未知
类目: Artificial Intelligence (cs.AI); Methodology (stat.ME)
备注: Accepted at The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS2025)

点击查看摘要

[AI-34] Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM Judges

链接: https://arxiv.org/abs/2511.01375
作者: Hamin Koo,Minseon Kim,Jaehyung Kim
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: under review, 28 pages

点击查看摘要

[AI-35] Automatic Minds: Cognitive Parallels Between Hypnotic States and Large Language Model Processing

链接: https://arxiv.org/abs/2511.01363
作者: Giuseppe Riva,Brenda K. Wiederhold,Fabrizia Mantovani
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: 4 Tables

点击查看摘要

[AI-36] AI Literacy in UAE Libraries: Assessing Competencies Training Needs and Ethical Considerations for the Digital Age

链接: https://arxiv.org/abs/2511.01353
作者: Zafar Imam Khan
机构: 未知
类目: Digital Libraries (cs.DL); Artificial Intelligence (cs.AI)
备注: This is the accepted manuscript version. The final published version will appear in College Research Libraries, November 2026

点击查看摘要

[AI-37] he Future of Generative AI in Software Engineering: A Vision from Industry and Academia in the European GENIUS Project

链接: https://arxiv.org/abs/2511.01348
作者: Robin Gröpler,Steffen Klepke,Jack Johns,Andreas Dreschinski,Klaus Schmid,Benedikt Dornauer,Eray Tüzün,Joost Noppen,Mohammad Reza Mousavi,Yongjian Tang,Johannes Viehmann,Selin Şirin Aslangül,Beum Seuk Lee,Adam Ziolkowski,Eric Zie
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注: Submitted to 2nd IEEE/ACM International Conference on AI-powered Software (AIware 2025)

点击查看摘要

[AI-38] Beyond Permissions: Investigating Mobile Personalization with Simulated Personas CCS2025

链接: https://arxiv.org/abs/2511.01336
作者: Ibrahim Khalilov,Chaoran Chen,Ziang Xiao,Tianshi Li,Toby Jia-Jun Li,Yaxing Yao
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: 8 pages, 7 figures. Accepted to the ACM Workshop on Human-Centered AI Privacy and Security (HAIPS @ CCS 2025). DOI: https://doi.org/10.1145/3733816.3760758 (ACM Digital Library link pending activation)

点击查看摘要

[AI-39] Embodied Cognition Augmented End2End Autonomous Driving

链接: https://arxiv.org/abs/2511.01334
作者: Ling Niu,Xiaoji Zheng,Han Wang,Chen Zheng,Ziyuan Yang,Bokui Chen,Jiangtao Gong
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注: 24 pages,4 pages

点击查看摘要

[AI-40] Unbiased Platform-Level Causal Estimation for Search Systems: A Competitive Isolation PSM-DID Framework

链接: https://arxiv.org/abs/2511.01329
作者: Ying Song,Yijing Wang,Hui Yang,Weihan Jin,Jun Xiong,Congyi Zhou,Jialin Zhu,Xiang Gao,Rong Chen,HuaGuang Deng,Ying Dai,Fei Xiao,Haihong Tang,Bo Zheng,KaiFu Zhang
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-41] AI for Requirements Engineering: Industry adoption and Practitioner perspectives

链接: https://arxiv.org/abs/2511.01324
作者: Lekshmi Murali Rani,Richard Berntsson Svensson,Robert Feldt
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注: Accepted at the Intelligent Software Engineering (ISE) 2025 Workshop at the Automated Software Engineering (ASE) 2025 Conference

点击查看摘要

[AI-42] OmniFuser: Adaptive Multimodal Fusion for Service-Oriented Predictive Maintenance

链接: https://arxiv.org/abs/2511.01320
作者: Ziqi Wang,Hailiang Zhao,Yuhao Yang,Daojiang Hu,Cheng Bao,Mingyi Liu,Kai Di,Schahram Dustdar,Zhongjie Wang,Shuiguang Deng
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-43] Exploringand Unleashing the Power of Large Language Models in CI/CD Configuration Translation

链接: https://arxiv.org/abs/2511.01316
作者: Chong Wang,Chen Zhang,Jiajun Wu,Wunan Guo,Jianfeng Qu,Yewen Tian,Yang Liu
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-44] mSHAP: A Principled Approach to LLM Explainability

链接: https://arxiv.org/abs/2511.01311
作者: Filip Naudot,Tobias Sundqvist,Timotheus Kampik
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-45] LSHFed: Robust and Communication-Efficient Federated Learning with Locally-Sensitive Hashing Gradient Mapping

链接: https://arxiv.org/abs/2511.01296
作者: Guanjie Cheng,Mengzhen Yang,Xinkui Zhao,Shuyi Yu,Tianyu Du,Yangyang Wu,Mengying Zhu,Shuiguang Deng
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-46] Adversarial Spatio-Temporal Attention Networks for Epileptic Seizure Forecasting

链接: https://arxiv.org/abs/2511.01275
作者: Zan Li,Kyongmin Yeo,Wesley Gifford,Lara Marcuse,Madeline Fields,Bülent Yener
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-47] Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems ACSA

链接: https://arxiv.org/abs/2511.01268
作者: Minseok Kim,Hankook Lee,Hyungjoon Koo
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
备注: 15 pages, 7 figures, 10 tables. To appear in the Proceedings of the 2025 Annual Computer Security Applications Conference (ACSAC)

点击查看摘要

[AI-48] Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play

链接: https://arxiv.org/abs/2511.01261
作者: Jiatong Shi,Jionghao Han,Yichen Lu,Santiago Pascual,Pengfei Wu,Chenye Cui,Shinji Watanabe,Chao Weng,Cong Zhou
机构: 未知
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS)
备注: 67 pages

点击查看摘要

[AI-49] Graph Neural Network-Based Semi-Supervised Open-Set Fault Diagnosis for Marine Machinery Systems

链接: https://arxiv.org/abs/2511.01258
作者: Chuyue Lou,M. Amine Atoui
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-50] Influence-aware Causal Autoencoder Network for Node Importance Ranking in Complex Networks

链接: https://arxiv.org/abs/2511.01228
作者: Jiahui Gao,Kuang Zhou,Yuchen Zhu
机构: 未知
类目: ocial and Information Networks (cs.SI); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-51] Forget BIT It is All about TOKEN: Towards Semantic Information Theory for LLM s

链接: https://arxiv.org/abs/2511.01202
作者: Bo Bai
机构: 未知
类目: Information Theory (cs.IT); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-52] QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code NEURIPS2025

链接: https://arxiv.org/abs/2511.01183
作者: Hainan Fang,Yuanbo Wen,Jun Bi,Yihan Wang,Tonghui He,Yanlin Tang,Di Huang,Jiaming Guo,Rui Zhang,Qi Guo,Yunji Chen
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: Accepted at NeurIPS 2025

点击查看摘要

[AI-53] MiRAG E: Misconception Detection with Retrieval-Guided Multi-Stage Reasoning and Ensemble Fusion

链接: https://arxiv.org/abs/2511.01182
作者: Cuong Van Duc,Thai Tran Quoc,Minh Nguyen Dinh Tuan,Tam Vu Duc,Son Nguyen Van,Hanh Nguyen Thi
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-54] Adapt under Attack and Domain Shift: Unified Adversarial Meta-Learning and Domain Adaptation for Robust Automatic Modulation Classification

链接: https://arxiv.org/abs/2511.01172
作者: Ali Owfi,Amirmohammad Bamdad,Tolunay Seyfi,Fatemeh Afghah
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Signal Processing (eess.SP)
备注:

点击查看摘要

[AI-55] DART: Difficulty-Adaptive Reasoning Truncation for Efficient Large Language Models

链接: https://arxiv.org/abs/2511.01170
作者: Ruofan Zhang,Bin Xia,Zhen Cheng,Cairen Jian,Minglun Yang,Ngai Wong,Yuan Cheng
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-56] A High-Throughput Spiking Neural Network Processor Enabling Synaptic Delay Emulation

链接: https://arxiv.org/abs/2511.01158
作者: Faquan Chen,Qingyang Tian,Ziren Wu,Rendong Ying,Fei Wen,Peilin Liu
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-57] Modular Task Decomposition and Dynamic Collaboration in Multi-Agent Systems Driven by Large Language Models

链接: https://arxiv.org/abs/2511.01149
作者: Shuaidong Pan,Di Wu
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-58] AthenaBench: A Dynamic Benchmark for Evaluating LLM s in Cyber Threat Intelligence

链接: https://arxiv.org/abs/2511.01144
作者: Md Tanvirul Alam,Dipkamal Bhusal,Salman Ahmad,Nidhi Rastogi,Peter Worth
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-59] Continual Learning Not Training: Online Adaptation For Agents

链接: https://arxiv.org/abs/2511.01093
作者: Aman Jaglan,Jarrod Barnes
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 12 pages, 4 figures

点击查看摘要

[AI-60] Energy-Efficient Deep Learning Without Backpropagation: A Rigorous Evaluation of Forward-Only Algorithms

链接: https://arxiv.org/abs/2511.01061
作者: Przemysław Spyra,Witold Dzwinel
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-61] Efficient Test-Time Retrieval Augmented Generation

链接: https://arxiv.org/abs/2511.01059
作者: Hailong Yin,Bin Zhu,Jingjing Chen,Chong-Wah Ngo
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-62] Knowledge Elicitation with Large Language Models for Interpretable Cancer Stage Identification from Pathology Reports

链接: https://arxiv.org/abs/2511.01052
作者: Yeawon Lee,Christopher C. Yang,Chia-Hsuan Chang,Grace Lu-Yao
机构: 未知
类目: Artificial Intelligence (cs.AI); Medical Physics (physics.med-ph)
备注:

点击查看摘要

[AI-63] HAFixAgent : History-Aware Automated Program Repair Agent

链接: https://arxiv.org/abs/2511.01047
作者: Yu Shi,Hao Li,Bram Adams,Ahmed E. Hassan
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注: 31 pages, 6 figures

点击查看摘要

[AI-64] AI for pRedicting Exacerbations in KIDs with aSthma (AIRE-KIDS)

链接: https://arxiv.org/abs/2511.01018
作者: Hui-Lee Ooi,Nicholas Mitsakakis,Margerie Huet Dastarac,Roger Zemek,Amy C. Plint,Jeff Gilchrist,Khaled El Emam,Dhenuka Radhakrishnan
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-65] Aligning LLM agents agent s with human learning and adjustment behavior: a dual agent approach

链接: https://arxiv.org/abs/2511.00993
作者: Tianming Liu,Jirong Yang,Yafeng Yin,Manzi Li,Linghao Wang,Zheng Zhu
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 32 pages, 6 figures, 7 tables

点击查看摘要

[AI-66] Keys in the Weights: Transformer Authentication Using Model-Bound Latent Representations

【速读】：该论文旨在解决安全关键领域中人工智能（AI）模型部署的认证与访问控制问题，特别是在模型架构和训练数据公开的情况下如何实现轻量级、高效的模型绑定机制。解决方案的关键在于提出一种称为Model-Bound Latent Exchange (MoBLE)的新范式，其核心是零样本解码非转移性（Zero-Shot Decoder Non-Transferability, ZSDN）——即同一编码器生成的潜在表示仅能被对应特定解码器在零样本场景下正确重建，而其他解码器即使结构相同也无法复现，从而实现基于隐空间的模型绑定认证。此特性无需注入秘密或对抗训练即可稳定出现，并可通过权重空间距离与注意力差异诊断验证，为安全敏感应用（如航空和网络物理系统）提供可部署的轻量级安全保障。

链接: https://arxiv.org/abs/2511.00973
作者: Ayşe S. Okatan,Mustafa İlhan Akbaş,Laxima Niure Kandel,Berker Peköz
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Signal Processing (eess.SP)
备注: Cite as A. S. Okatan, M. I. Akbas, L. N. Kandel, and B. Pekoz, “Keys in the weights: Transformer authentication using model-bound latent representations,” in Proc. 2025 Cyber Awareness and Research Symp. (IEEE CARS 2025), Grand Forks, ND, Oct. 2025, pp. 6

点击查看摘要

Abstract:We introduce Model-Bound Latent Exchange (MoBLE), a decoder-binding property in Transformer autoencoders formalized as Zero-Shot Decoder Non-Transferability (ZSDN). In identity tasks using iso-architectural models trained on identical data but differing in seeds, self-decoding achieves more than 0.91 exact match and 0.98 token accuracy, while zero-shot cross-decoding collapses to chance without exact matches. This separation arises without injected secrets or adversarial training, and is corroborated by weight-space distances and attention-divergence diagnostics. We interpret ZSDN as model binding, a latent-based authentication and access-control mechanism, even when the architecture and training recipe are public: encoder’s hidden state representation deterministically reveals the plaintext, yet only the correctly keyed decoder reproduces it in zero-shot. We formally define ZSDN, a decoder-binding advantage metric, and outline deployment considerations for secure artificial intelligence (AI) pipelines. Finally, we discuss learnability risks (e.g., adapter alignment) and outline mitigations. MoBLE offers a lightweight, accelerator-friendly approach to secure AI deployment in safety-critical domains, including aviation and cyber-physical systems.
zh

[AI-67] Using Synthetic Data to estimate the True Error is theoretically and practically doable ACML

链接: https://arxiv.org/abs/2511.00964
作者: Hai Hoang Thanh,Duy-Tung Nguyen,Hung The Tran,Khoat Than
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: To appear at Machine Learning journal and ACML

点击查看摘要

[AI-68] he Hidden Power of Normalization: Exponential Capacity Control in Deep Neural Networks

链接: https://arxiv.org/abs/2511.00958
作者: Khoat Than
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-69] URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model NEURIPS2025

链接: https://arxiv.org/abs/2511.00940
作者: Zhe Li,Xiang Bai,Jieyu Zhang,Zhuangzhe Wu,Che Xu,Ying Li,Chengkai Hou,Shanghang Zhang
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注: Accepted to the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

点击查看摘要

[AI-70] Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robots

链接: https://arxiv.org/abs/2511.00917
作者: Junyao Shi,Rujia Yang,Kaitian Chao,Selina Bingqing Wan,Yifei Shao,Jiahui Lei,Jianing Qian,Long Le,Pratik Chaudhari,Kostas Daniilidis,Chuan Wen,Dinesh Jayaraman
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注: Project website: this https URL

点击查看摘要

[AI-71] Dynamic Logic of Trust-Based Beliefs

链接: https://arxiv.org/abs/2511.00899
作者: Junli Jiang,Pavel Naumov,Wenxuan Zhang
机构: 未知
类目: Logic in Computer Science (cs.LO); Artificial Intelligence (cs.AI); Logic (math.LO)
备注:

点击查看摘要

[AI-72] Android Malware Detection: A Machine Leaning Approach

链接: https://arxiv.org/abs/2511.00894
作者: Hasan Abdulla
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-73] KFCPO: Kronecker-Factored Approximated Constrained Policy Optimization ECAI2025

链接: https://arxiv.org/abs/2511.00880
作者: Joonyoung Lim,Younghwan Yoo
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 12 pages, 8 figures, submitted to ECAI 2025

点击查看摘要

[AI-74] Fast Stochastic Greedy Algorithm for k-Submodular Cover Problem

链接: https://arxiv.org/abs/2511.00869
作者: Hue T. Nguyen,Tan D. Tran,Nguyen Long Giang,Canh V. Pham
机构: 未知
类目: Data Structures and Algorithms (cs.DS); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-75] Pay for The Second-Best Service: A Game-Theoretic Approach Against Dishonest LLM Providers

链接: https://arxiv.org/abs/2511.00847
作者: Yuhan Cao,Yu Wang,Sitong Liu,Miao Li,Yixin Tao,Tianxing He
机构: 未知
类目: Computer Science and Game Theory (cs.GT); Artificial Intelligence (cs.AI)
备注: 13 pages, 4 figures

点击查看摘要

[AI-76] CodeClash: Benchmarking Goal-Oriented Software Engineering

链接: https://arxiv.org/abs/2511.00839
作者: John Yang,Kilian Lieret,Joyce Yang,Carlos E. Jimenez,Ofir Press,Ludwig Schmidt,Diyi Yang
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-77] owards Ultra-Low Latency: Binarized Neural Network Architectures for In-Vehicle Network Intrusion Detection

链接: https://arxiv.org/abs/2511.00828
作者: Huiyao Dong,Igor Kotenko
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注: 6 pages, accepted and presented at INISTA 2025 ( this https URL )

点击查看摘要

[AI-78] Do Math Reasoning LLM s Help Predict the Impact of Public Transit Events?

链接: https://arxiv.org/abs/2511.00808
作者: Bowen Fang,Ruijian Zha,Xuan Di
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-79] Logic-informed reinforcement learning for cross-domain optimization of large-scale cyber-physical systems

链接: https://arxiv.org/abs/2511.00806
作者: Guangxi Wan,Peng Zeng,Xiaoting Dong,Chunhe Song,Shijie Cui,Dong Li,Qingwei Dong,Yiyang Liu,Hongfei Bai
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-80] Attention Saturation and Gradient Suppression at Inflection Layers: Diagnosing and Mitigating Bottlenecks in Transformer Adaptation

链接: https://arxiv.org/abs/2511.00797
作者: Wang Zixian
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-81] Efficient Reinforcement Learning for Large Language Models with Intrinsic Exploration

链接: https://arxiv.org/abs/2511.00794
作者: Yan Sun,Jia Guo,Stanley Kok,Zihao Wang,Zujie Wen,Zhiqiang Zhang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-82] Fast PINN Eigensolvers via Biconvex Reformulation NEURIPS2025

链接: https://arxiv.org/abs/2511.00792
作者: Akshay Sai Banderwaar,Abhishek Gupta
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE)
备注: 7 pages, 3 figures, Machine Learning and the Physical Sciences Workshop NeurIPS 2025

点击查看摘要

[AI-83] Count-Based Approaches Remain Strong: A Benchmark Against Transformer and LLM Pipelines on Structured EHR

链接: https://arxiv.org/abs/2511.00782
作者: Jifan Gao,Michael Rosenthal,Brian Wolpin,Simona Cristea
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-84] Quantifying truth and authenticity in AI-assisted candidate evaluation: A multi-domain pilot analysis

链接: https://arxiv.org/abs/2511.00774
作者: Eldred Lee,Nicholas Worley,Koshu Takatsuji
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: 10 pages, 10 tables, 2 figures, and 1 page of supplemental materials

点击查看摘要

[AI-85] How Focused Are LLM s? A Quantitative Study via Repetitive Deterministic Prediction Tasks

链接: https://arxiv.org/abs/2511.00763
作者: Wanda Hou,Leon Zhou,Hong-Ye Hu,Yi-Zhuang You,Xiao-Liang Qi
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-86] Active Thinking Model: A Goal-Directed Self-Improving Framework for Real-World Adaptive Intelligence

链接: https://arxiv.org/abs/2511.00758
作者: Hong Su
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-87] A CPU-Centric Perspective on Agent ic AI

链接: https://arxiv.org/abs/2511.00739
作者: Ritik Raj,Hong Wang,Tushar Krishna
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
备注:

点击查看摘要

[AI-88] EP-HDC: Hyperdimensional Computing with Encrypted Parameters for High-Throughput Privacy-Preserving Inference

链接: https://arxiv.org/abs/2511.00737
作者: Jaewoo Park,Chenghao Quan,Jongeun Lee
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注: To appear on ASP-DAC 2026

点击查看摘要

[AI-89] FeNN-DMA: A RISC-V SoC for SNN acceleration

链接: https://arxiv.org/abs/2511.00732
作者: Zainab Aizaz,James C. Knight,Thomas Nowotny
机构: 未知
类目: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR)
备注:

点击查看摘要

[AI-90] RISKELION-1: Unified Descriptive-Predictive-Generative AI

链接: https://arxiv.org/abs/2511.00711
作者: Nardeep Kumar,Arun Kanwar
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 12 pages, 18 figures, submitted to arXiv (2025)

点击查看摘要

[AI-91] Ariadne: A Controllable Framework for Probing and Extending VLM Reasoning Boundaries

链接: https://arxiv.org/abs/2511.00710
作者: Minghe Shen,Zhuo Zhi,Chonghan Liu,Shuo Xing,Zhengzhong Tu,Che Liu
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-92] A Voice-Enabled Virtual Patient System for Interactive Training in Standardized Clinical Assessment

链接: https://arxiv.org/abs/2511.00709
作者: Veronica Bossio Botero,Vijay Yadav,Jacob Ouyang,Anzar Abbas,Michelle Worthington
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-93] Lifted Successor Generation in Numeric Planning

链接: https://arxiv.org/abs/2511.00673
作者: Dominik Drexler
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-94] ShadowLogic: Backdoors in Any Whitebox LLM

链接: https://arxiv.org/abs/2511.00664
作者: Kasimir Schulz,Amelia Kawasaki,Leo Ring
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-95] Lessons Learned from the Use of Generative AI in Engineering and Quality Assurance of a WEB System for Healthcare

链接: https://arxiv.org/abs/2511.00658
作者: Guilherme H. Travassos,Sabrina Rocha,Rodrigo Feitosa,Felipe Assis,Patricia Goncalves,Andre Gheventer,Larissa Galeno,Arthur Sasse,Julio Cesar Guimaraes,Carlos Brito,Joao Pedro Wieland
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET)
备注: 11 pages, 2 figures, in Portuguese language

点击查看摘要

[AI-96] More Than A Shortcut: A Hyperbolic Approach To Early-Exit Networks

链接: https://arxiv.org/abs/2511.00641
作者: Swapnil Bhosale,Cosmin Frateanu,Camilla Clark,Arnoldas Jasonas,Chris Mitchell,Xiatian Zhu,Vamsi Krishna Ithapu,Giacomo Ferroni,Cagdas Bilen,Sanjeel Parekh
机构: 未知
类目: ound (cs.SD); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-97] Node Preservation and its Effect on Crossover in Cartesian Genetic Programming

链接: https://arxiv.org/abs/2511.00634
作者: Mark Kocherovsky,Illya Bakurov,Wolfgang Banzhaf
机构: 未知
类目: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Draft to cite in another paper before both papers are peer-reviewed for the evo*2026 conference, 21 pages, 5 figures

点击查看摘要

[AI-98] Agent Git: A Version Control Framework for Reliable and Scalable LLM -Powered Multi-Agent Systems

链接: https://arxiv.org/abs/2511.00628
作者: Yang Li,Siqi Ping,Xiyu Chen,Xiaojian Qi,Zigan Wang,Ye Luo,Xiaowei Zhang
机构: 未知
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Software Engineering (cs.SE)
备注:

点击查看摘要

[AI-99] PreferThinker: Reasoning -based Personalized Image Preference Assessment

链接: https://arxiv.org/abs/2511.00609
作者: Shengqi Xu,Xinpeng Zhou,Yabo Zhang,Ming Liu,Tao Liang,Tianyu Zhang,Yalong Bai,Zuxuan Wu,Wangmeng Zuo
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-100] EPARA: Parallelizing Categorized AI Inference in Edge Clouds

链接: https://arxiv.org/abs/2511.00603
作者: Yubo Wang,Yubo Cui,Tuo Shi,Danyang Li,Wenxin Li,Lide Suo,Tao Wang,Xin Xie
机构: 未知
类目: Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI)
备注: 15 pages,20 figures

点击查看摘要

[AI-101] Diagnosing Hallucination Risk in AI Surgical Decision-Support: A Sequential Framework for Sequential Validation

链接: https://arxiv.org/abs/2511.00588
作者: Dong Chen,Yanzhe Wei,Zonglin He,Guan-Ming Kuang,Canhua Ye,Meiru An,Huili Peng,Yong Hu,Huiren Tao,Kenneth MC Cheung
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注:

点击查看摘要

[AI-102] FTT-GRU: A Hybrid Fast Temporal Transformer with GRU for Remaining Useful Life Prediction

链接: https://arxiv.org/abs/2511.00564
作者: Varun Teja Chirukiri,Udaya Bhasker Cheerala,Sandeep Kanta,Abdul Karim,Praveen Damacharla
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Systems and Control (eess.SY)
备注: 5 pages, The 2025 International Conference on Computational Science and Computational Intelligence

点击查看摘要

[AI-103] Red-teaming Activation Probes using Prompted LLM s

链接: https://arxiv.org/abs/2511.00554
作者: Phil Blandfort,Robert Graham
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-104] mporal Fusion Transformer for Multi-Horizon Probabilistic Forecasting of Weekly Retail Sales

链接: https://arxiv.org/abs/2511.00552
作者: Santhi Bharath Punati,Sandeep Kanta,Udaya Bhasker Cheerala,Madhusudan G Lanjewar,Praveen Damacharla
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); General Economics (econ.GN)
备注: 5 pages, 2025 6th International Conference on Data Analytics for Business and Industry (ICDABI)

点击查看摘要

[AI-105] Single-agent Reinforcement Learning Model for Regional Adaptive Traffic Signal Control

链接: https://arxiv.org/abs/2511.00551
作者: Qiang Li,Ningjing Zeng,Lina Yu
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-106] Robust Single-Agent Reinforcement Learning for Regional Traffic Signal Control Under Demand Fluctuations

链接: https://arxiv.org/abs/2511.00549
作者: Qiang Li,Jin Niu,Lina Yu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-107] Efficient Generation of Binary Magic Squares

链接: https://arxiv.org/abs/2511.00547
作者: Alain Riou
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-108] Air Pollution Forecasting in Bucharest

链接: https://arxiv.org/abs/2511.00532
作者: Dragoş-Andrei Şerban,Răzvan-Alexandru Smădu,Dumitru-Clementin Cercel
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Applications (stat.AP)
备注: 14 pages 3 figures

点击查看摘要

[AI-109] On Improvisation and Open-Endedness: Insights for Experiential AI AAAI2026

链接: https://arxiv.org/abs/2511.00529
作者: Botao ‘Amber’ Hu
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE); Systems and Control (eess.SY)
备注: Submitted to AAAI 2026 Creative AI for Live Interactive Performances Workshop (CLIP) as a work-in-progress paper

点击查看摘要

[AI-110] HIP-LLM : A Hierarchical Imprecise Probability Approach to Reliability Assessment of Large Language Models

链接: https://arxiv.org/abs/2511.00527
作者: Robab Aghazadeh-Chakherlou,Qing Guo,Siddartha Khastgir,Peter Popov,Xiaoge Zhang,Xingyu Zhao
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注: under review

点击查看摘要

[AI-111] Reimagining Safety Alignment with An Image

链接: https://arxiv.org/abs/2511.00509
作者: Yifan Xia,Guorui Chen,Wenqian Yu,Zhijiang Li,Philip Torr,Jindong Gu
机构: 未知
类目: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
备注:

点击查看摘要

[AI-112] Why Federated Optimization Fails to Achieve Perfect Fitting? A Theoretical Perspective on Client-Side Optima

链接: https://arxiv.org/abs/2511.00469
作者: Zhongxiang Lei,Qi Yang,Ping Qiu,Gang Zhang,Yuanchi Ma,Jinyan Liu
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-113] Proactive DDoS Detection and Mitigation in Decentralized Software-Defined Networking via Port-Level Monitoring and Zero-Training Large Language Models

链接: https://arxiv.org/abs/2511.00460
作者: Mohammed N. Swileh,Shengli Zhang
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-114] GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining

链接: https://arxiv.org/abs/2511.00457
作者: Chunyu Wei,Wenji Hu,Xingjia Hao,Xin Wang,Yifan Yang,Yueguo Chen,Yang Tian,Yunhai Wang
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-115] DRIP: Defending Prompt Injection via De-instruction Training and Residual Fusion Model Architecture

链接: https://arxiv.org/abs/2511.00447
作者: Ruofan Liu,Yun Lin,Jin Song Dong
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-116] LIR: The First Workshop on Late Interaction and Multi Vector Retrieval @ ECIR 2026 ECIR2026

链接: https://arxiv.org/abs/2511.00444
作者: Benjamin Clavié,Xianming Li,Antoine Chaffin,Omar Khattab,Tom Aarsen,Manuel Faysse,Jing Li
机构: 未知
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
备注: Accepted workshop at ECIR 2026

点击查看摘要

[AI-117] A Multimodal Framework for Depression Detection during Covid-19 via Harvesting Social Media: A Novel Dataset and Method

链接: https://arxiv.org/abs/2511.00424
作者: Ashutosh Anshul,Gumpili Sai Pranav,Mohammad Zia Ur Rehman,Nagendra Kumar
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-118] Bootstrap Off-policy with World Model NEURIPS2025

链接: https://arxiv.org/abs/2511.00423
作者: Guojian Zhan,Likun Wang,Xiangteng Zhang,Jiaxin Gao,Masayoshi Tomizuka,Shengbo Eben Li
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO)
备注: NeurIPS 2025

点击查看摘要

[AI-119] Human-AI Programming Role Optimization: Developing a Personality-Driven Self-Determination Framework CCS2012

链接: https://arxiv.org/abs/2511.00417
作者: Marcel Valovy
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注: PhD Dissertation, Prague University of Economics and Business, 2025. 323 pages. ACM CCS 2012: Human-computer interaction, Collaborative interaction, Human-AI collaborative systems, Pair programming, AI-assisted software engineering

点击查看摘要

[AI-120] UME-R1: Exploring Reasoning -Driven Generative Multimodal Embeddings

链接: https://arxiv.org/abs/2511.00405
作者: Zhibin Lan,Liqiang Niu,Fandong Meng,Jie Zhou,Jinsong Su
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-121] Emotion Detection in Speech Using Lightweight and Transformer-Based Models: A Comparative and Ablation Study

链接: https://arxiv.org/abs/2511.00402
作者: Lucky Onyekwelu-Udoka,Md Shafiqul Islam,Md Shahedul Hasan
机构: 未知
类目: ound (cs.SD); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-122] Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLM s

链接: https://arxiv.org/abs/2511.00382
作者: Mina Taraghi,Yann Pequignot,Amin Nikanjam,Mohamed Amine Merzouk,Foutse Khomh
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-123] Balancing Interpretability and Performance in Motor Imagery EEG Classification: A Comparative Study of ANFIS-FBCSP-PSO and EEGNet CEC

链接: https://arxiv.org/abs/2511.00369
作者: Farjana Aktar,Mohd Ruhul Ameen,Akif Islam,Md Ekramul Hamid
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE)
备注: 6 pages, 3 figures, 8 tables, Submitted to ICECTE 2026

点击查看摘要

[AI-124] MalDataGen: A Modular Framework for Synthetic Tabular Data Generation in Malware Detection

链接: https://arxiv.org/abs/2511.00361
作者: Kayua Oleques Paim,Angelo Gaspar Diniz Nogueira,Diego Kreutz,Weverton Cordeiro,Rodrigo Brandao Mansilha
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 10 pages, 6 figures, 2 tables. Published at the Brazilian Symposium on Cybersecurity (SBSeg 2025)

点击查看摘要

[AI-125] Mind the Gap: Missing Cyber Threat Coverag e in NIDS Datasets for the Energy Sector

链接: https://arxiv.org/abs/2511.00360
作者: Adrita Rahman Tory,Khondokar Fida Hasan,Md Saifur Rahman,Nickolaos Koroniotis,Mohammad Ali Moni
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 13 pages

点击查看摘要

[AI-126] oward Unifying Group Fairness Evaluation from a Sparsity Perspective

链接: https://arxiv.org/abs/2511.00359
作者: Zhecheng Sheng,Jiawei Zhang,Enmao Diao
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: 30 pages, 14 figures

点击查看摘要

[AI-127] Exploiting Latent Space Discontinuities for Building Universal LLM Jailbreaks and Data Extraction Attacks

链接: https://arxiv.org/abs/2511.00346
作者: Kayua Oleques Paim,Rodrigo Brandao Mansilha,Diego Kreutz,Muriel Figueredo Franco,Weverton Cordeiro
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 10 pages, 5 figures, 4 tables, Published at the Brazilian Symposium on Cybersecurity (SBSeg 2025)

点击查看摘要

[AI-128] MH-1M: A 1.34 Million-Sample Comprehensive Multi-Feature Android Malware Dataset for Machine Learning Deep Learning Large Language Models and Threat Intelligence Research

链接: https://arxiv.org/abs/2511.00342
作者: Hendrio Braganca,Diego Kreutz,Vanderson Rocha,Joner Assolin,and Eduardo Feitosa
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Performance (cs.PF)
备注: 17 pages, 7 figures, 13 tables, submitted to the Scientific Data journal published by Nature Research

点击查看摘要

[AI-129] Better Call CLAUSE: A Discrepancy Benchmark for Auditing LLM s Legal Reasoning Capabilities

链接: https://arxiv.org/abs/2511.00340
作者: Manan Roy Choudhury,Adithya Chandramouli,Mannan Anand,Vivek Gupta
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: 41 pages, 4 images

点击查看摘要

[AI-130] Scalable Processing-Near-Memory for 1M-Token LLM Inference: CXL-Enabled KV-Cache Management Beyond GPU Limits

链接: https://arxiv.org/abs/2511.00321
作者: Dowon Kim,MinJae Lee,Janghyeon Kim,HyuckSung Kwon,Hyeonggyu Jeong,Sang-Soo Park,Minyong Yoon,Si-Dong Roh,Yongsuk Kwon,Jinin So,Jungwook Choi
机构: 未知
类目: Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-131] A Technical Exploration of Causal Inference with Hybrid LLM Synthetic Data

链接: https://arxiv.org/abs/2511.00318
作者: Dana Kim,Yichen Xu,Tiffany Lin
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
备注: 9 pages, 4 figures

点击查看摘要

[AI-132] Advancing AI Challenges for the United States Department of the Air Force

链接: https://arxiv.org/abs/2511.00267
作者: Christian Prothmann,Vijay Gadepally,Jeremy Kepner,Koley Borchard,Luca Carlone,Zachary Folcik,J. Daniel Grith,Michael Houle,Jonathan P. How,Nathan Hughes,Ifueko Igbinedion,Hayden Jananthan,Tejas Jayashankar,Michael Jones,Sertac Karaman,Binoy G. Kurien,Alejandro Lancho,Giovanni Lavezzi,Gary C. F. Lee,Charles E. Leiserson,Richard Linares,Lindsey McEvoy,Peter Michaleas,Chasen Milner,Alex Pentland,Yury Polyanskiy,Jovan Popovich,Jeffrey Price,Tim W. Reid,Stephanie Riley,Siddharth Samsi,Peter Saunders,Olga Simek,Mark S. Veillette,Amir Weiss,Gregory W. Wornell,Daniela Rus,Scott T. Ruppel
机构: 未知
类目: Artificial Intelligence (cs.AI); Computers and Society (cs.CY); General Literature (cs.GL); Machine Learning (cs.LG)
备注: 8 pages, 8 figures, 59 references. To appear in IEEE HPEC 2025

点击查看摘要

[AI-133] Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI

链接: https://arxiv.org/abs/2511.00230
作者: Sheer Karny,Anthony Baez,Pat Pataranutaporn
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: SK and AB are co-first authors

点击查看摘要

[AI-134] Diffusion Models at the Drug Discovery Frontier: A Review on Generating Small Molecules versus Therapeutic Peptides

链接: https://arxiv.org/abs/2511.00209
作者: Yiquan Wang,Yahui Ma,Yuhan Chang,Jiayao Yan,Jialin Zhang,Minnuo Cai,Kai Wei
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Biomolecules (q-bio.BM); Quantitative Methods (q-bio.QM)
备注: 21 pages, 3 figures

点击查看摘要

[AI-135] Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories

链接: https://arxiv.org/abs/2511.00197
作者: Oorja Majgaonkar,Zhiwei Fei,Xiang Li,Federica Sarro,He Ye
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-136] Incremental Selection of Most-Filtering Conjectures and Proofs of the Selected Conjectures

链接: https://arxiv.org/abs/2511.00194
作者: Jovial Cheukam Ngouonou,Ramiz Gindullin,Claude-Guy Quimper,Nicolas Beldiceanu,Remi Douence
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-137] EL-MIA: Quantifying Membership Inference Risks of Sensitive Entities in LLM s

链接: https://arxiv.org/abs/2511.00192
作者: Ali Satvaty,Suzan Verberne,Fatih Turkmen
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-138] Effectiveness of LLM s in Temporal User Profiling for Recommendation ICDM ICDM2025

链接: https://arxiv.org/abs/2511.00176
作者: Milad Sabouri,Masoud Mansoury,Kun Lin,Bamshad Mobasher
机构: 未知
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
备注: Accepted to the IEEE International Conference on Data Mining (ICDM 2025), Workshop on User Modeling and Recommendation (UMRec). To appear in the IEEE ICDMW 2025 proceedings

点击查看摘要

[AI-139] ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus

链接: https://arxiv.org/abs/2511.00162
作者: Michael D. Moffitt
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-140] What a diff makes: automating code migration with large language models

链接: https://arxiv.org/abs/2511.00160
作者: Katherine A. Rosenfeld,Cliff C. Kerr,Jessica Lundin
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注: 10 pages, 8 figures

点击查看摘要

[AI-141] End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collection

链接: https://arxiv.org/abs/2511.00139
作者: Yu Cui,Yujian Zhang,Lina Tao,Yang Li,Xinyu Yi,Zhibin Li
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-142] A Dual Large Language Models Architecture with Herald Guided Prompts for Parallel Fine Grained Traffic Signal Control

链接: https://arxiv.org/abs/2511.00136
作者: Qing Guo,Xinhang Li,Junyu Chen,Zheng Guo,Xiaocong Li,Lin Zhang,Lei Li
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-143] Feature Importance Guided Random Forest Learning with Simulated Annealing Based Hyperparameter Tuning

链接: https://arxiv.org/abs/2511.00133
作者: Kowshik Balasubramanian,Andre Williams,Ismail Butun
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 10 pages, 2 figures, 3 tables, submitted to IEEE Intelligent Systems journal

点击查看摘要

[AI-144] Casing Collar Identification using AlexNet-based Neural Networks for Depth Measurement in Oil and Gas Wells

链接: https://arxiv.org/abs/2511.00129
作者: Siyu Xiao,Xindi Zhao,Tianhao Mao,Yiwei Wang,Yuqiao Chen,Hongyun Zhang,Jian Wang,Junjie Wang,Shuang Liu,Tupei Chen,Yang Liu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Signal Processing (eess.SP)
备注:

点击查看摘要

[AI-145] Dynamic Model Selection for Trajectory Prediction via Pairwise Ranking and Meta-Features

链接: https://arxiv.org/abs/2511.00126
作者: Lu Bowen
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-146] Inferring multiple helper Dafny assertions with LLM s

链接: https://arxiv.org/abs/2511.00125
作者: Álvaro Silva,Alexandra Mendes,Ruben Martins
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO); Programming Languages (cs.PL)
备注:

点击查看摘要

[AI-147] Cross-fluctuation phase transitions reveal sampling dynamics in diffusion models NEURIPS2025

链接: https://arxiv.org/abs/2511.00124
作者: Sai Niranjan Ramachandran,Manish Krishan Lal,Suvrit Sra
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Accepted at NeurIPS 2025. 10 pages, camera-ready version. appendices included

点击查看摘要

[AI-148] Engineering.ai: A Platform for Teams of AI Engineers in Computational Design

链接: https://arxiv.org/abs/2511.00122
作者: Ran Xu,Yupeng Qi,Jingsen Feng,Xu Chu
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-149] DCcluster-Opt: Benchmarking Dynamic Multi-Objective Optimization for Geo-Distributed Data Center Workloads NEURIPS2025

链接: https://arxiv.org/abs/2511.00117
作者: Antonio Guillen-Perez,Avisek Naug,Vineet Gundecha,Sahand Ghorbanpour,Ricardo Luna Gutierrez,Ashwin Ramesh Babu,Munther Salim,Shubhanker Banerjee,Eoin H. Oude Essink,Damien Fay,Soumyendu Sarkar
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Systems and Control (eess.SY)
备注: Submitted to the NeurIPS 2025 conference

点击查看摘要

[AI-150] LC-Opt: Benchmarking Reinforcement Learning and Agent ic AI for End-to-End Liquid Cooling Optimization in Data Centers NEURIPS2025

链接: https://arxiv.org/abs/2511.00116
作者: Avisek Naug,Antonio Guillen,Vineet Kumar,Scott Greenwood,Wesley Brewer,Sahand Ghorbanpour,Ashwin Ramesh Babu,Vineet Gundecha,Ricardo Luna Gutierrez,Soumyendu Sarkar
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Systems and Control (eess.SY)
备注: Submitted to the NeurIPS 2025 conference

点击查看摘要

[AI-151] Real-DRL: Teach and Learn in Reality

链接: https://arxiv.org/abs/2511.00112
作者: Yanbing Mao,Yihao Cai,Lui Sha
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注: 37 pages

点击查看摘要

[AI-152] Pelican-VL 1.0: A Foundation Brain Model for Embodied Intelligence

链接: https://arxiv.org/abs/2511.00108
作者: Yi Zhang,Che Liu,Xiancong Ren,Hanchu Ni,Shuai Zhang,Zeyuan Ding,Jiayu Hu,Hanzhe Shan,Zhenwei Niu,Zhaoyang Liu,Yue Zhao,Junbo Qi,Qinfan Zhang,Dengjie Li,Yidong Wang,Jiachen Luo,Yong Dai,Jian Tang,Xiaozhu Ju
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-153] Artificial Intelligence in Elementary STEM Education: A Systematic Review of Current Applications and Future Challenges

链接: https://arxiv.org/abs/2511.00105
作者: Majid Memari,Krista Ruggles
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-154] Automated Discovery of Conservation Laws via Hybrid Neural ODE-Transformers NEURIPS2025

链接: https://arxiv.org/abs/2511.00102
作者: Vivan Doshi
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 5th Math-AI Workshop - Neural Information Processing Systems (NeurIPS 2025)

点击查看摘要

[AI-155] Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving NEURIPS2025

链接: https://arxiv.org/abs/2511.00101
作者: Yuchen Zhang,Hanyue Du,Chun Cao,Jingwei Xu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 26 pages including 10 pages of main text, 6 figures, 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

点击查看摘要

[AI-156] GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation NEURIPS-2025

链接: https://arxiv.org/abs/2511.00097
作者: Zihao Guo,Qingyun Sun,Ziwei Zhang,Haonan Yuan,Huiping Zhuang,Xingcheng Fu,Jianxin Li
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Accepted by the Main Track of NeurIPS-2025

点击查看摘要

[AI-157] Urban-MAS: Human-Centered Urban Prediction with LLM -Based Multi-Agent System

链接: https://arxiv.org/abs/2511.00096
作者: Shangyu Lou
机构: 未知
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注: Accepted to The 3rd ACM SIGSPATIAL International Workshop on Advances in Urban AI (UrbanAI’25)

点击查看摘要

[AI-158] Digital Twin based Automatic Reconfiguration of Robotic Systems in Smart Environments

链接: https://arxiv.org/abs/2511.00094
作者: Angelos Alexopoulos,Agorakis Bompotas,Nikitas Rigas Kalogeropoulos,Panagiotis Kechagias,Athanasios P. Kalogeras,Christos Alexakos
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Systems and Control (eess.SY)
备注: Accepted for presentation to 11th IEEE International Smart Cities Conference (ISC2 2025)

点击查看摘要

[AI-159] Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail

链接: https://arxiv.org/abs/2511.00088
作者: NVIDIA:Yan Wang,Wenjie Luo,Junjie Bai,Yulong Cao,Tong Che,Ke Chen,Yuxiao Chen,Jenna Diamond,Yifan Ding,Wenhao Ding,Liang Feng,Greg Heinrich,Jack Huang,Peter Karkus,Boyi Li,Pinyi Li,Tsung-Yi Lin,Dongran Liu,Ming-Yu Liu,Langechuan Liu,Zhijian Liu,Jason Lu,Yunxiang Mao,Pavlo Molchanov,Lindsey Pavao,Zhenghao Peng,Mike Ranzinger,Ed Schmerling,Shida Shen,Yunfei Shi,Sarah Tariq,Ran Tian,Tilman Wekel,Xinshuo Weng,Tianjun Xiao,Eric Yang,Xiaodong Yang,Yurong You,Xiaohui Zeng,Wenyuan Zhang,Boris Ivanovic,Marco Pavone
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-160] Adding New Capability in Existing Scientific Application with LLM Assistance

链接: https://arxiv.org/abs/2511.00087
作者: Anshu Dubey,Akash Dhruv
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注: 8 pages, 4 figures, submitted to The 1st International Workshop on Foundational large Language Models Advances for HPC in Asia

点击查看摘要

[AI-161] MaGNet: A Mamba Dual-Hypergraph Network for Stock Prediction via Temporal-Causal and Global Relational Learning

链接: https://arxiv.org/abs/2511.00085
作者: Peilin Tan,Chuanqi Shi,Dian Tu,Liang Xie
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-162] Application of predictive machine learning in pen paper RPG game design

链接: https://arxiv.org/abs/2511.00084
作者: Jolanta Śliwa
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Master’s thesis submitted at AGH University of Science and Technology

点击查看摘要

[AI-163] Fixed-point graph convolutional networks against adversarial attacks

链接: https://arxiv.org/abs/2511.00083
作者: Shakib Khan,A. Ben Hamza,Amr Youssef
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-164] RailEstate: An Interactive System for Metro Linked Property Trends

链接: https://arxiv.org/abs/2511.00078
作者: Chen-Wei Chang,Yu-Chieh Cheng,Yun-En Tsai,Fanglan Chen,Chang-Tien Lu
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Databases (cs.DB)
备注:

点击查看摘要

[AI-165] Benchmarking Generative AI Against Bayesian Optimization for Constrained Multi-Objective Inverse Design

链接: https://arxiv.org/abs/2511.00070
作者: Muhammad Bilal Awan,Abdul Razzaq,Abdul Shahid
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 17 pages, 2 Figures

点击查看摘要

[AI-166] Latent Domain Prompt Learning for Vision-Language Models

链接: https://arxiv.org/abs/2511.00067
作者: Zhixing Li,Arsham Gholamzadeh Khoee,Yinan Yu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-167] Aligning Brain Signals with Multimodal Speech and Vision Embeddings

链接: https://arxiv.org/abs/2511.00065
作者: Kateryna Shapovalenko,Quentin Auster
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-168] Automatically Finding Rule-Based Neurons in OthelloGPT NEURIPS2025

链接: https://arxiv.org/abs/2511.00059
作者: Aditya Singh,Zihang Wen,Srujananjali Medicherla,Adam Karvonen,Can Rager
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 Mechanistic interpretability

点击查看摘要

[AI-169] MISA: Memory-Efficient LLM s Optimization with Module-wise Importance Sampling

链接: https://arxiv.org/abs/2511.00056
作者: Yuxi Liu,Renjia Deng,Yutong He,Xue Wang,Tao Yao,Kun Yuan
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-170] Exploring Federated Learning for Thermal Urban Feature Segmentation – A Comparison of Centralized and Decentralized Approaches

链接: https://arxiv.org/abs/2511.00055
作者: Leonhard Duda,Khadijeh Alibabaei,Elena Vollmer,Leon Klug,Valentin Kozlov,Lisana Berberi,Mishal Benz,Rebekka Volk,Juan Pedro Gutiérrez Hermosillo Muriedas,Markus Götz,Judith Sáínz-Pardo Díaz,Álvaro López García,Frank Schultmann,Achim Streit
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-171] SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation NEURIPS2025

链接: https://arxiv.org/abs/2511.00054
作者: Gio Huh,Dhruv Sheth,Rayhan Zirvi,Frank Xiao
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Accepted to the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop on Efficient Reasoning

点击查看摘要

[AI-172] Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models

链接: https://arxiv.org/abs/2511.00053
作者: Hao Wang,Licheng Pan,Yuan Lu,Zhichao Chen,Tianqiao Liu,Shuting He,Zhixuan Chu,Qingsong Wen,Haoxuan Li,Zhouchen Lin
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-173] Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT

链接: https://arxiv.org/abs/2511.00051
作者: Da Chang,Peng Xue,Yu Li,Yongxiang Liu,Pengxiang Xu,Shixun Zhang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-174] FLoRA: Fused forward-backward adapters for parameter efficient fine-tuning and reducing inference-time latencies of LLM s

链接: https://arxiv.org/abs/2511.00050
作者: Dhananjaya Gowda,Seoha Song,Junhyun Lee,Harshith Goka
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-175] Adaptive Spatio-Temporal Graphs with Self-Supervised Pretraining for Multi-Horizon Weather Forecasting

链接: https://arxiv.org/abs/2511.00049
作者: Yao Liu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-176] GEPOC Parameters - Open Source Parametrisation and Validation for Austria Version 2.0

链接: https://arxiv.org/abs/2511.00048
作者: Martin Bicher,Maximilian Viehauser,Daniele Giannandrea,Hannah Kastinger,Dominik Brunmeir,Claire Rippinger,Christoph Urach,Niki Popper
机构: 未知
类目: Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注: 134 pages, 75 figures, 19 tables

点击查看摘要

[AI-177] DynBERG: Dynamic BERT-based Graph neural network for financial fraud detection

链接: https://arxiv.org/abs/2511.00047
作者: Omkar Kulkarni,Rohitash Chandra
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE)
备注:

点击查看摘要

[AI-178] Endowing GPT -4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World

链接: https://arxiv.org/abs/2511.00041
作者: Yingzhao Jian,Zhongan Wang,Yi Yang,Hehe Fan
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-179] Semi-Supervised Preference Optimization with Limited Feedback

链接: https://arxiv.org/abs/2511.00040
作者: Seonggyun Lee,Sungjun Lim,Seojin Park,Soeun Cheon,Kyungwoo Song
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-180] Graph-Attentive MAPPO for Dynamic Retail Pricing

链接: https://arxiv.org/abs/2511.00039
作者: Krishna Kumar Neelakanta Pillai Santha Kumari Amma
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-181] STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization

链接: https://arxiv.org/abs/2511.00033
作者: Diqi He,Xuehao Gao,Hao Li,Junwei Han,Dingwen Zhang
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-182] From Uniform to Adaptive: General Skip-Block Mechanisms for Efficient PDE Neural Operators

链接: https://arxiv.org/abs/2511.00032
作者: Lei Liu,Zhongyi Yu,Hong Wang,Huanshuo Dong,Haiyang Xin,Hongwei Zhao,Bin Li
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-183] Probing Knowledge Holes in Unlearned LLM s

链接: https://arxiv.org/abs/2511.00030
作者: Myeongseob Ko,Hoang Anh Just,Charles Fleming,Ming Jin,Ruoxi Jia
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: The Thirty-ninth Annual Conference on Neural Information Processing Systems

点击查看摘要

[AI-184] Feature-Guided SAE Steering for Refusal-Rate Control using Contrasting Prompts

链接: https://arxiv.org/abs/2511.00029
作者: Samaksh Bhargav,Zining Zhu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 12 pages, 6 figures

点击查看摘要

[AI-185] Position Paper: If Innovation in AI Systematically Violates Fundamental Rights Is It Innovation at All? NEURIPS2025

链接: https://arxiv.org/abs/2511.00027
作者: Josu Eguiluz Castañeira,Axel Brando,Migle Laukyte,Marc Serra-Vidal
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Applications (stat.AP)
备注: NeurIPS 2025 Position Paper track; accepted for oral and poster presentation at the Thirty-Ninth Annual Conference on Neural Information Processing Systems

点击查看摘要

[AI-186] Sorting by Strip Swaps is NP-Hard

链接: https://arxiv.org/abs/2511.00015
作者: Swapnoneel Roy,Asai Asaithambi,Debajyoti Mukhopadhyay
机构: 未知
类目: Data Structures and Algorithms (cs.DS); Artificial Intelligence (cs.AI); Computational Complexity (cs.CC)
备注: 4 pages

点击查看摘要

[AI-187] A Two Level Neural Approach Combining Off-Chip Prediction with Adaptive Prefetch Filtering HPCA

链接: https://arxiv.org/abs/2403.15181
作者: Alexandre Valentin Jamet,Georgios Vavouliotis,Daniel A. Jiménez,Lluc Alvarez,Marc Casas
机构: 未知
类目: Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI)
备注: To appear in 30th International Symposium on High-Performance Computer Architecture (HPCA), 2024

点击查看摘要

[AI-188] Spin-Adapted Neural Network Wavefunctions in Real Space

链接: https://arxiv.org/abs/2511.01671
作者: Ruichen Li,Yuzhi Liu,Du Jiang,Yixiao Chen,Xuelan Wen,Wenrui Li,Di He,Liwei Wang,Ji Chen,Weiluo Ren
机构: 未知
类目: Chemical Physics (physics.chem-ph); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-189] Quantum Deep Learning Still Needs a Quantum Leap

链接: https://arxiv.org/abs/2511.01253
作者: Hans Gundlach,Hrvoje Kukina,Jayson Lynch,Neil Thompson
机构: 未知
类目: Quantum Physics (quant-ph); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-190] An Interdisciplinary and Cross-Task Review on Missing Data Imputation

链接: https://arxiv.org/abs/2511.01196
作者: Jicong Fan
机构: 未知
类目: Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-191] Seed-Induced Uniqueness in Transformer Models: Subspace Alignment Governs Subliminal Transfer

链接: https://arxiv.org/abs/2511.01023
作者: Ayşe Selin Okatan,Mustafa İlhan Akbaş,Laxima Niure Kandel,Berker Peköz
机构: 未知
类目: ignal Processing (eess.SP); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Machine Learning (cs.LG)
备注: Cite as A. S. Okatan, M. I. Akbaş, L. N. Kandel, and B. Peköz, “Seed-Induced Uniqueness in Transformer Models: Subspace Alignment Governs Subliminal Transfer,” in Proc. 2025 Cyber Awareness and Research Symp. (IEEE CARS 2025), Grand Forks, ND, Oct. 2025, pp. 6

点击查看摘要

[AI-192] Deep Generative Models for Enhanced Vitreous OCT Imaging

链接: https://arxiv.org/abs/2511.00881
作者: Simone Sarrocco,Philippe C. Cattin,Peter M. Maloca,Paul Friedrich,Philippe Valmaggia
机构: 未知
类目: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-193] Isotropic Curvature Model for Understanding Deep Learning Optimization: Is Gradient Orthogonalization Optimal?

链接: https://arxiv.org/abs/2511.00674
作者: Weijie Su
机构: 未知
类目: Optimization and Control (math.OC); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-194] A Multimodal Dataset for Indoor Radio Mapping with 3D Point Clouds and RSSI

链接: https://arxiv.org/abs/2511.00494
作者: Ljupcho Milosheski,Kuon Akiyama,Blaž Bertalanič,Jernej Hribar,Ryoichi Shinkuma
机构: 未知
类目: ignal Processing (eess.SP); Artificial Intelligence (cs.AI)
备注: 11 pages, 7 figures, 3 tables, under review to Nature Scientific Data

点击查看摘要

[AI-195] Quantum Machine Unlearning: Foundations Mechanisms and Taxonomy

链接: https://arxiv.org/abs/2511.00406
作者: Thanveer Shaik,Xiaohui Tao,Haoran Xie,Robert Sang
机构: 未知
类目: Quantum Physics (quant-ph); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-196] Generative Modeling Enables Molecular Structure Retrieval from Coulomb Explosion Imaging

链接: https://arxiv.org/abs/2511.00179
作者: Xiang Li,Till Jahnke,Rebecca Boll,Jiaqi Han,Minkai Xu,Michael Meyer,Maria Novella Piancastelli,Daniel Rolles,Artem Rudenko,Florian Trinter,Thomas J.A. Wolf,Jana B. Thayer,James P. Cryan,Stefano Ermon,Phay J. Ho
机构: 未知
类目: Chemical Physics (physics.chem-ph); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

机器学习

[LG-0] Coordinate ascent neural Kalman-MLE for state estimation

链接: https://arxiv.org/abs/2511.01855
作者: Bettina Hanlon,Angel Garcia Fernandez
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

Abstract:This paper presents a coordinate ascent algorithm to learn dynamic and measurement models in dynamic state estimation using maximum likelihood estimation in a supervised manner. In particular, the dynamic and measurement models are assumed to be Gaussian and the algorithm learns the neural network parameters that model the dynamic and measurement functions, and also the noise covariance matrices. The trained dynamic and measurement models are then used with a non-linear Kalman filter algorithm to estimate the state during the testing phase.

[LG-1] Proximal Regret and Proximal Correlated Equilibria: A New Tractable Solution Concept for Online Learning and Games NEURIPS

链接: https://arxiv.org/abs/2511.01852
作者: Yang Cai,Constantinos Daskalakis,Haipeng Luo,Chen-Yu Wei,Weiqiang Zheng
类目: Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG)
*备注: This paper presents proximal regret and proximal correlated equilibria results that do not appear in the NeurIPS version of arXiv:2403.08171

点击查看摘要

Abstract:Learning and computation of equilibria are central problems in algorithmic game theory. In this work, we introduce proximal regret, a new notion of regret based on proximal operators that lies strictly between external and swap regret. When every player employs a no-proximal-regret algorithm in a general convex game, the empirical distribution of play converges to proximal correlated equilibria (PCE), a refinement of coarse correlated equilibria. Our framework unifies several emerging notions in online learning and game theory – such as gradient equilibrium and semicoarse correlated equilibrium – and introduces new ones. Our main result shows that the classic Online Gradient Descent (GD) algorithm achieves an optimal O(\sqrtT) bound on proximal regret, revealing that GD, without modification, minimizes a stronger regret notion than external regret. This provides a new explanation for the empirically superior performance of gradient descent in online learning and games. We further extend our analysis to Mirror Descent in the Bregman setting and to Optimistic Gradient Descent, which yields faster convergence in smooth convex games.

[LG-2] Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measure

链接: https://arxiv.org/abs/2511.01847
作者: Zhi Wang,Chicheng Zhang,Ramya Korlakai Vinayak
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-3] Interpretable Machine Learning for Reservoir Water Temperatures in the U.S. Red River Basin of the South

链接: https://arxiv.org/abs/2511.01837
作者: Isabela Suaza-Sierra,Hernan A. Moreno,Luis A De la Fuente,Thomas M. Neeson
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-4] Priors in Time: Missing Inductive Biases for Language Model Interpretability

链接: https://arxiv.org/abs/2511.01836
作者: Ekdeep Singh Lubana,Can Rager,Sai Sumedh R. Hindupur,Valerie Costa,Greta Tuckute,Oam Patel,Sonia Krishna Murthy,Thomas Fel,Daniel Wurgaft,Eric J. Bigelow,Johnny Lin,Demba Ba,Martin Wattenberg,Fernanda Viegas,Melanie Weber,Aaron Mueller
类目: Machine Learning (cs.LG)
*备注: Preprint

点击查看摘要

[LG-5] owards Multi-Fidelity Scaling Laws of Neural Surrogates in CFD

链接: https://arxiv.org/abs/2511.01830
作者: Paul Setinek,Gianluca Galletti,Johannes Brandstetter
类目: Machine Learning (cs.LG); Fluid Dynamics (physics.flu-dyn)
*备注:

点击查看摘要

Abstract:Scaling laws describe how model performance grows with data, parameters and compute. While large datasets can usually be collected at relatively low cost in domains such as language or vision, scientific machine learning is often limited by the high expense of generating training data through numerical simulations. However, by adjusting modeling assumptions and approximations, simulation fidelity can be traded for computational cost, an aspect absent in other domains. We investigate this trade-off between data fidelity and cost in neural surrogates using low- and high-fidelity Reynolds-Averaged Navier-Stokes (RANS) simulations. Reformulating classical scaling laws, we decompose the dataset axis into compute budget and dataset composition. Our experiments reveal compute-performance scaling behavior and exhibit budget-dependent optimal fidelity mixes for the given dataset configuration. These findings provide the first study of empirical scaling laws for multi-fidelity neural surrogate datasets and offer practical considerations for compute-efficient dataset generation in scientific machine learning.

[LG-6] No-rank Tensor Decomposition Using Metric Learning

链接: https://arxiv.org/abs/2511.01816
作者: Maryam Bagherian
类目: Machine Learning (cs.LG); Optimization and Control (math.OC)
*备注:

点击查看摘要

Abstract:Tensor decomposition faces fundamental challenges in analyzing high-dimensional data, where traditional methods based on reconstruction and fixed-rank constraints often fail to capture semantically meaningful structures. This paper introduces a no-rank tensor decomposition framework grounded in metric learning, which replaces reconstruction objectives with a discriminative, similarity-based optimization. The proposed approach learns data-driven embeddings by optimizing a triplet loss with diversity and uniformity regularization, creating a feature space where distance directly reflects semantic similarity. We provide theoretical guarantees for the framework’s convergence and establish bounds on its metric properties. Evaluations across diverse domains --including face recognition (LFW, Olivetti), brain connectivity analysis (ABIDE), and simulated data (galaxy morphology, crystal structures)-- demonstrate that our method outperforms baseline techniques, including PCA, t-SNE, UMAP, and tensor decomposition baselines (CP and Tucker). Results show substantial improvements in clustering metrics (Silhouette Score, Davies–Bouldin Index, Calinski–Harabasz Index, Separation Ratio, Adjusted Rand Index, Normalized Mutual Information) and reveal a fundamental trade-off: while metric learning optimizes global class separation, it deliberately transforms local geometry to align with semantic relationships. Crucially, our approach achieves superior performance with smaller training datasets compared to transformer-based methods, offering an efficient alternative for domains with limited labeled data. This work establishes metric learning as a paradigm for tensor-based analysis, prioritizing semantic relevance over pixel-level fidelity while providing computational advantages in data-scarce scenarios.

[LG-7] Dynamic Reconstruction of Ultrasound-Derived Flow Fields With Physics-Informed Neural Fields

链接: https://arxiv.org/abs/2511.01804
作者: Viraj Patel,Lisa Kreusser,Katharine Fraser
类目: Machine Learning (cs.LG)
*备注: 29 pages, 18 figures

点击查看摘要

[LG-8] Bayesian Coreset Optimization for Personalized Federated Learning ICLR2024

链接: https://arxiv.org/abs/2511.01800
作者: Prateek Chanda,Shrey Modi,Ganesh Ramakrishnan
类目: Machine Learning (cs.LG)
*备注: 9 pages, 5 figures, ICLR 2024

点击查看摘要

[LG-9] Hybrid Neural Network-Based Indoor Localisation System for Mobile Robots Using CSI Data in a Robotics Simulator

链接: https://arxiv.org/abs/2511.01797
作者: Javier Ballesteros-Jerez,Jesus Martínez-Gómez,Ismael García-Varea,Luis Orozco-Barbosa,Manuel Castillo-Cara
类目: Robotics (cs.RO); Machine Learning (cs.LG)
*备注: 13 pages, 7 figures. Conference paper (ROBOVIS 2025)

点击查看摘要

[LG-10] ADNAC: Audio Denoiser using Neural Audio Codec

链接: https://arxiv.org/abs/2511.01773
作者: Daniel Jimon,Mircea Vaida,Adriana Stan
类目: ound (cs.SD); Machine Learning (cs.LG)
*备注: Accepted and presented at the 13th International Conference on Speech Technology and Human-Computer Dialogue (SpeD), Cluj-Napoca, Romania, October 19-22, 2025. 4 pages, 1 figure. IEEE Catalog Number: CFP2555H-USB, ISBN: 979-8-3315-7485-7

点击查看摘要

[LG-11] HyperNQ: A Hypergraph Neural Network Decoder for Quantum LDPC Codes

链接: https://arxiv.org/abs/2511.01741
作者: Ameya S. Bhave,Navnil Choudhury,Kanad Basu
类目: Machine Learning (cs.LG); Information Theory (cs.IT); Quantum Physics (quant-ph)
*备注: 6 pages, 4 figures, Submitted to the IEEE International Conference on Communications (ICC 2026). Preprint version

点击查看摘要

Abstract:Quantum computing requires effective error correction strategies to mitigate noise and decoherence. Quantum Low-Density Parity-Check (QLDPC) codes have emerged as a promising solution for scalable Quantum Error Correction (QEC) applications by supporting constant-rate encoding and a sparse parity-check structure. However, decoding QLDPC codes via traditional approaches such as Belief Propagation (BP) suffers from poor convergence in the presence of short cycles. Machine learning techniques like Graph Neural Networks (GNNs) utilize learned message passing over their node features; however, they are restricted to pairwise interactions on Tanner graphs, which limits their ability to capture higher-order correlations. In this work, we propose HyperNQ, the first Hypergraph Neural Network (HGNN)- based QLDPC decoder that captures higher-order stabilizer constraints by utilizing hyperedges-thus enabling highly expressive and compact decoding. We use a two-stage message passing scheme and evaluate the decoder over the pseudo-threshold region. Below the pseudo-threshold mark, HyperNQ improves the Logical Error Rate (LER) up to 84% over BP and 50% over GNN-based strategies, demonstrating enhanced performance over the existing state-of-the-art decoders.

[LG-12] Game-theoretic distributed learning of generative models for heterogeneous data collections

链接: https://arxiv.org/abs/2511.01740
作者: Dmitrij Schlesinger,Boris Flach
类目: Machine Learning (cs.LG)
*备注: The manuscript is accepted for publishing at the 2025 Symposium on Federated Learning and Intelligent Computing Systems (FLICS 2025)

点击查看摘要

[LG-13] Edge AI in Highly Volatile Environments: Is Fairness Worth the Accuracy Trade-off?

链接: https://arxiv.org/abs/2511.01737
作者: Obaidullah Zaland,Feras M. Awaysheh,Sawsan Al Zubi,Abdul Rahman Safi,Monowar Bhuyan
类目: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注: Presented at IEEE FLTA 2025

点击查看摘要

Abstract:Federated learning (FL) has emerged as a transformative paradigm for edge intelligence, enabling collaborative model training while preserving data privacy across distributed personal devices. However, the inherent volatility of edge environments, characterized by dynamic resource availability and heterogeneous client capabilities, poses significant challenges for achieving high accuracy and fairness in client participation. This paper investigates the fundamental trade-off between model accuracy and fairness in highly volatile edge environments. This paper provides an extensive empirical evaluation of fairness-based client selection algorithms such as RBFF and RBCSF against random and greedy client selection regarding fairness, model performance, and time, in three benchmarking datasets (CIFAR10, FashionMNIST, and EMNIST). This work aims to shed light on the fairness-performance and fairness-speed trade-offs in a volatile edge environment and explore potential future research opportunities to address existing pitfalls in \textitfair client selection strategies in FL. Our results indicate that more equitable client selection algorithms, while providing a marginally better opportunity among clients, can result in slower global training in volatile environments\footnoteThe code for our experiments can be found at this https URL.

[LG-14] SemBench: A Benchmark for Semantic Query Processing Engines

链接: https://arxiv.org/abs/2511.01716
作者: Jiale Lao,Andreas Zimmerer,Olga Ovcharenko,Tianji Cong,Matthew Russo,Gerardo Vitagliano,Michael Cochez,Fatma Özcan,Gautam Gupta,Thibaud Hottelier,H. V. Jagadish,Kris Kissel,Sebastian Schelter,Andreas Kipf,Immanuel Trummer
类目: Databases (cs.DB); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-15] Collaborative Large Language Model Inference via Resource-Aware Parallel Speculative Decoding

链接: https://arxiv.org/abs/2511.01695
作者: Jungyeon Koh,Hyun Jong Yang
类目: Machine Learning (cs.LG); Signal Processing (eess.SP)
*备注:

点击查看摘要

[LG-16] Panther: A Cost-Effective Privacy-Preserving Framework for GNN Training and Inference Services in Cloud Environments

链接: https://arxiv.org/abs/2511.01654
作者: Congcong Chen,Xinyu Liu,Kaifeng Huang,Lifei Wei,Yang Shi
类目: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
*备注: Accepted for publication in IEEE Transactions on Services Computing (TSC)

点击查看摘要

[LG-17] Cross-Treatment Effect Estimation for Multi-Category Multi-Valued Causal Inference via Dynamic Neural Masking

链接: https://arxiv.org/abs/2511.01641
作者: Xiaopeng Ke,Yihan Yu,Ruyue Zhang,Zhishuo Zhou,Fangzhou Shi,Chang Men,Zhengdan Zhu
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-18] Estimation of Toeplitz Covariance Matrices using Overparameterized Gradient Descent

链接: https://arxiv.org/abs/2511.01605
作者: Daniel Busbib,Ami Wiesel
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-19] L2T-Tune:LLM -Guided Hybrid Database Tuning with LHS and TD3

链接: https://arxiv.org/abs/2511.01602
作者: Xinyue Yang,Chen Zheng,Yaoyang Hou,Renhao Zhang,Yiyan Zhang,Yanjun Wu,Heng Zhang
类目: Databases (cs.DB); Machine Learning (cs.LG)
*备注:

点击查看摘要

Abstract:Configuration tuning is critical for database performance. Although recent advancements in database tuning have shown promising results in throughput and latency improvement, challenges remain. First, the vast knob space makes direct optimization unstable and slow to converge. Second, reinforcement learning pipelines often lack effective warm-start guidance and require long offline training. Third, transferability is limited: when hardware or workloads change, existing models typically require substantial retraining to recover performance. To address these limitations, we propose L2T-Tune, a new LLM-guided hybrid database tuning framework that features a three-stage pipeline: Stage one performs a warm start that simultaneously generates uniform samples across the knob space and logs them into a shared pool; Stage two leverages a large language model to mine and prioritize tuning hints from manuals and community documents for rapid convergence. Stage three uses the warm-start sample pool to reduce the dimensionality of knobs and state features, then fine-tunes the configuration with the Twin Delayed Deep Deterministic Policy Gradient algorithm. We conduct experiments on L2T-Tune and the state-of-the-art models. Compared with the best-performing alternative, our approach improves performance by an average of 37.1% across all workloads, and by up to 73% on TPC-C. Compared with models trained with reinforcement learning, it achieves rapid convergence in the offline tuning stage on a single server. Moreover, during the online tuning stage, it only takes 30 steps to achieve best results. Subjects: Databases (cs.DB); Machine Learning (cs.LG) Cite as: arXiv:2511.01602 [cs.DB] (or arXiv:2511.01602v1 [cs.DB] for this version) https://doi.org/10.48550/arXiv.2511.01602 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

[LG-20] Defining Energy Indicators for Impact Identification on Aerospace Composites: A Physics-Informed Machine Learning Perspective

链接: https://arxiv.org/abs/2511.01592
作者: Natália Ribeiro Marinho,Richard Loendersloot,Frank Grooteman,Jan Willem Wiegman,Uraz Odyurt,Tiedo Tinga
类目: Machine Learning (cs.LG); Applied Physics (physics.app-ph)
*备注:

点击查看摘要

[LG-21] Gated Fusion Enhanced Multi-Scale Hierarchical Graph Convolutional Network for Stock Movement Prediction

链接: https://arxiv.org/abs/2511.01570
作者: Xiaosha Xue,Peibo Duan,Zhipeng Liu,Qi Chu,Changsheng Zhang,Bin zhang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-22] Learning what to say and how precisely: Efficient Communication via Differentiable Discrete Communication Learning

链接: https://arxiv.org/abs/2511.01554
作者: Aditya Kapoor,Yash Bhisikar,Benjamin Freed,Jan Peters,Mingfei Sun
类目: Multiagent Systems (cs.MA); Information Theory (cs.IT); Machine Learning (cs.LG)
*备注: 30 pages, 12 figures, 6 tables

点击查看摘要

Abstract:Effective communication in multi-agent reinforcement learning (MARL) is critical for success but constrained by bandwidth, yet past approaches have been limited to complex gating mechanisms that only decide \textitwhether to communicate, not \textithow precisely. Learning to optimize message precision at the bit-level is fundamentally harder, as the required discretization step breaks gradient flow. We address this by generalizing Differentiable Discrete Communication Learning (DDCL), a framework for end-to-end optimization of discrete messages. Our primary contribution is an extension of DDCL to support unbounded signals, transforming it into a universal, plug-and-play layer for any MARL architecture. We verify our approach with three key results. First, through a qualitative analysis in a controlled environment, we demonstrate \textithow agents learn to dynamically modulate message precision according to the informational needs of the task. Second, we integrate our variant of DDCL into four state-of-the-art MARL algorithms, showing it reduces bandwidth by over an order of magnitude while matching or exceeding task performance. Finally, we provide direct evidence for the \enquoteBitter Lesson in MARL communication: a simple Transformer-based policy leveraging DDCL matches the performance of complex, specialized architectures, questioning the necessity of bespoke communication designs.

[LG-23] Deep Learning Prediction of Beam Coherence Time for Near-FieldTeraHertz Networks

链接: https://arxiv.org/abs/2511.01491
作者: Irched Chafaa,E. Veronica Belmega,Giacomo Bacci
类目: ystems and Control (eess.SY); Machine Learning (cs.LG)
*备注: IEEE Wireless Communication Letters (accepted October 2025)

点击查看摘要

[LG-24] Efficient Curvature-aware Graph Network

链接: https://arxiv.org/abs/2511.01443
作者: Chaoqun Fei,Tinglve Zhou,Tianyong Hao,Yangyang Li
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-25] he Curvature Rate λ: A Scalar Measure of Input-Space Sharpness in Neural Networks

链接: https://arxiv.org/abs/2511.01438
作者: Jacob Poschl
类目: Machine Learning (cs.LG)
*备注: 14 pages

点击查看摘要

[LG-26] CG-FKAN: Compressed-Grid Federated Kolmogorov-Arnold Networks for Communication Constrained Environment

链接: https://arxiv.org/abs/2511.01433
作者: Seunghun Yu,Youngjoon Lee,Jinu Gong,Joonhyuk Kang
类目: Machine Learning (cs.LG)
*备注: 5 pages

点击查看摘要

[LG-27] Leverag ing Compact Satellite Embeddings and Graph Neural Networks for Large-Scale Poverty Mapping

链接: https://arxiv.org/abs/2511.01408
作者: Markus B. Pettersson,Adel Daoud
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-28] Memory-Efficient Training with In-Place FFT Implementation NEURIPS2025

链接: https://arxiv.org/abs/2511.01385
作者: Xinyu Ding,Bangtian Liu,Siyu Liao,Zhongfeng Wang
类目: Machine Learning (cs.LG)
*备注: Accepted at NeurIPS 2025. Presents a real-domain in-place FFT (rdFFT) operator for memory-efficient fine-tuning of large language models

点击查看摘要

Abstract:Fast Fourier Transforms (FFT) are widely used to reduce memory and computational costs in deep learning. However, existing implementations, including standard FFT and real FFT (rFFT), cannot achieve true in-place computation. In particular, rFFT maps an input of size n to a complex output of size n/2+1, causing dimensional mismatch and requiring additional memory allocation. We propose the first real-domain, fully in-place FFT framework (rdFFT) that preserves input-output memory space consistency. By leveraging butterfly operation symmetry and conjugate properties in the frequency domain, we design an implicit complex encoding scheme that eliminates intermediate cache usage entirely. Experiments on multiple natural language understanding tasks demonstrate the method effectiveness in reducing training memory cost, offering a promising direction for frequency-domain lightweight adaptation.

[LG-29] Protecting the Neural Networks against FGSM Attack Using Machine Unlearning

链接: https://arxiv.org/abs/2511.01377
作者: Amir Hossein Khorasani,Ali Jahanian,Maryam Rastgarpour
类目: Machine Learning (cs.LG)
*备注: 7 pages, 9 figures, 1 table

点击查看摘要

[LG-30] Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization NEURIPS2025

链接: https://arxiv.org/abs/2511.01374
作者: Ziqi Wang,Jiashun Liu,Ling Pan
类目: Machine Learning (cs.LG)
*备注: NeurIPS 2025

点击查看摘要

[LG-31] A semantic-based deep learning approach for mathematical expression retrieval

链接: https://arxiv.org/abs/2511.01364
作者: Pavan Kumar Perepu
类目: Information Retrieval (cs.IR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-32] Verifiable Split Learning via zk-SNARKs

链接: https://arxiv.org/abs/2511.01356
作者: Rana Alaa,Darío González-Ferreiro,Carlos Beis-Penedo,Manuel Fernández-Veiga,Rebeca P. Díaz-Redondo,Ana Fernández-Vilas
类目: Machine Learning (cs.LG)
*备注: Submitted to CAI’26 (IEEE Conference on Artificial Intelligence 2026)

点击查看摘要

[LG-33] MiniFool - Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks

链接: https://arxiv.org/abs/2511.01352
作者: Lucie Flek,Oliver Janik,Philipp Alexander Jung,Akbar Karimi,Timo Saala,Alexander Schmidt,Matthias Schott,Philipp Soldin,Matthias Thiesmeyer,Christopher Wiebusch,Ulrich Willemsen
类目: Machine Learning (cs.LG); High Energy Astrophysical Phenomena (astro-ph.HE); Instrumentation and Methods for Astrophysics (astro-ph.IM); High Energy Physics - Experiment (hep-ex); Data Analysis, Statistics and Probability (physics.data-an)
*备注: Submitted to Computing and Software for Big Science

点击查看摘要

[LG-34] Diffusion-Based Solver for CNF Placement on the Cloud-Continuum

链接: https://arxiv.org/abs/2511.01343
作者: Álvaro Vázquez Rodríguez,Manuel Fernández-Veiga,Carlos Giraldo-Rodríguez
类目: Machine Learning (cs.LG)
*备注: 7 pages, 7 figures. Presented at PE-WASUN’25 (IEEE International Symposium on Performance Evaluation of Wireless Ad Hoc, Sensor, and Ubiquitous Networks)

点击查看摘要

[LG-35] RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models

链接: https://arxiv.org/abs/2511.01331
作者: Hongyin Zhang,Shuo Zhang,Junxi Jin,Qixin Zeng,Runze Li,Donglin Wang
类目: Robotics (cs.RO); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-36] Black-Box Differentially Private Nonparametric Confidence Intervals Under Minimal Assumptions

链接: https://arxiv.org/abs/2511.01303
作者: Tomer Shoham,Moshe Shenfeld,Noa Velner-Harris,Katrina Ligett
类目: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-37] Koopman-based Prediction of Connectivity for Flying Ad Hoc Networks

链接: https://arxiv.org/abs/2511.01286
作者: Sivaram Krishnan,Jinho Choi,Jihong Park,Gregory Sherman,Benjamin Campbell
类目: Machine Learning (cs.LG); Systems and Control (eess.SY)
*备注:

点击查看摘要

[LG-38] Lyapunov Stability Learning with Nonlinear Control via Inductive Biases

链接: https://arxiv.org/abs/2511.01283
作者: Yupu Lu,Shijie Lin,Hao Xu,Zeqing Zhang,Jia Pan
类目: Machine Learning (cs.LG); Robotics (cs.RO)
*备注: Accepted by IEEE Robio 2025

点击查看摘要

[LG-39] Identification of Capture Phases in Nanopore Protein Sequencing Data Using a Deep Learning Model

链接: https://arxiv.org/abs/2511.01277
作者: Annabelle Martin,Daphne Kontogiorgos-Heintz,Jeff Nivala
类目: Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
*备注:

点击查看摘要

[LG-40] A Spatio-Temporal Online Robust Tensor Recovery Approach for Streaming Traffic Data Imputation

链接: https://arxiv.org/abs/2511.01267
作者: Yiyang Yang,Xiejian Chi,Shanxing Gao,Kaidong Wang,Yao Wang
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-41] KAT-GNN: A Knowledge-Augmented Temporal Graph Neural Network for Risk Prediction in Electronic Health Records

链接: https://arxiv.org/abs/2511.01249
作者: Kun-Wei Lin,Yu-Chen Kuo,Hsin-Yao Wang,Yi-Ju Tseng
类目: Machine Learning (cs.LG)
*备注: 10 pages, 3 figures

点击查看摘要

[LG-42] A Saddle Point Remedy: Power of Variable Elimination in Non-convex Optimization

链接: https://arxiv.org/abs/2511.01234
作者: Min Gan,Guang-Yong Chen,Yang Yi,Lin Yang
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-43] WindMiL: Equivariant Graph Learning for Wind Loading Prediction

链接: https://arxiv.org/abs/2511.01226
作者: Themistoklis Vargiemezis,Charilaos Kanatsoulis,Catherine Gorlé
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-44] Optimizing Electric Vehicle Charging Station Placement Using Reinforcement Learning and Agent -Based Simulations

链接: https://arxiv.org/abs/2511.01218
作者: Minh-Duc Nguyen,Dung D. Le,Phi Long Nguyen
类目: Machine Learning (cs.LG)
*备注: Under Review

点击查看摘要

[LG-45] ransmitter Identification and Protocol Categorization in Shared Spectrum via Multi-Task RF Classification at the Network Edge

链接: https://arxiv.org/abs/2511.01198
作者: Tariq Abdul-Quddoos,Tasnia Sharmin,Xiangfang Li,Lijun Qian
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-46] Analyzing the Power of Chain of Thought through Memorization Capabilities

链接: https://arxiv.org/abs/2511.01190
作者: Lijia Yu,Xiao-Shan Gao,Lijun Zhang
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-47] A Comparative Study of Model Adaptation Strategies for Multi-Treatment Uplift Modeling

链接: https://arxiv.org/abs/2511.01185
作者: Ruyue Zhang,Xiaopeng Ke,Ming Liu,Fangzhou Shi,Chang Men,Zhengdan Zhu
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-48] Regularization Implies balancedness in the deep linear network

链接: https://arxiv.org/abs/2511.01137
作者: Kathryn Lindsey,Govind Menon
类目: Machine Learning (cs.LG); Algebraic Geometry (math.AG); Dynamical Systems (math.DS); Machine Learning (stat.ML)
*备注: 18 pages, 3 figures

点击查看摘要

[LG-49] Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization NEURIPS2025

链接: https://arxiv.org/abs/2511.01126
作者: Parvin Nazari,Bojian Hou,Davoud Ataee Tarzanagh,Li Shen,George Michailidis
类目: Machine Learning (cs.LG); Numerical Analysis (math.NA); Optimization and Control (math.OC); Statistics Theory (math.ST)
*备注: Published at NeurIPS 2025. 88 pages and 3 figures

点击查看摘要

[LG-50] One model to solve them all: 2BSDE families via neural operators

链接: https://arxiv.org/abs/2511.01125
作者: Takashi Furuya,Anastasis Kratsios,Dylan Possamaï,Bogdan Raonić
类目: Machine Learning (cs.LG); Analysis of PDEs (math.AP); Numerical Analysis (math.NA); Probability (math.PR); Computational Finance (q-fin.CP)
*备注:

点击查看摘要

[LG-51] SLAP: Shortcut Learning for Abstract Planning

链接: https://arxiv.org/abs/2511.01107
作者: Y. Isabel Liu,Bowen Li,Benjamin Eysenbach,Tom Silver
类目: Robotics (cs.RO); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-52] AI Progress Should Be Measured by Capability-Per-Resource Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLM s NEURIPS2025

链接: https://arxiv.org/abs/2511.01077
作者: David McCoy,Yulun Wu,Zachary Butzin-Dozier
类目: Machine Learning (cs.LG); Computation (stat.CO)
*备注: 9 pages (main) + appendix, 3 figures. Accepted at NeurIPS 2025 (Position Paper Track), submission #491. OpenReview: this https URL

点击查看摘要

[LG-53] Happiness as a Measure of Fairness

链接: https://arxiv.org/abs/2511.01069
作者: Georg Pichler,Marco Romanelli,Pablo Piantanida
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-54] Window-Based Feature Engineering for Cognitive Workload Detection

链接: https://arxiv.org/abs/2511.01060
作者: Andrew Hallam,R G Gayathri,Glory Lee,Atul Sajjanhar
类目: Machine Learning (cs.LG)
*备注: 9 pages, 3 figures

点击查看摘要

[LG-55] MedEqualizer: A Framework Investigating Bias in Synthetic Medical Data and Mitigation via Augmentation

链接: https://arxiv.org/abs/2511.01054
作者: Sama Salarian,Yue Zhang,Swati Padhee,Srinivasan Parthasarathy
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-56] SARIMAX-Based Power Outage Prediction During Extreme Weather Events

链接: https://arxiv.org/abs/2511.01017
作者: Haoran Ye,Qiuzhuang Sun,Yang Yang
类目: Machine Learning (cs.LG)
*备注: 12 pages, 3 figures. This paper presents the solution of Team 12 for the 2025 INFORMS Data Mining Society Data Challenge. The open-source code is available at: this https URL

点击查看摘要

[LG-57] Whats the next frontier for Data-centric AI? Data Savvy Agents ICLR2025

链接: https://arxiv.org/abs/2511.01015
作者: Nabeel Seedat,Jiashuo Liu,Mihaela van der Schaar
类目: Machine Learning (cs.LG)
*备注: Presented at ICLR 2025 Data-FM. Seedat Liu contributed equally

点击查看摘要

[LG-58] Equality Graph Assisted Symbolic Regression

链接: https://arxiv.org/abs/2511.01009
作者: Fabricio Olivetti de Franca,Gabriel Kronberger
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-59] None To Optima in Few Shots: Bayesian Optimization with MDP Priors

链接: https://arxiv.org/abs/2511.01006
作者: Diantong Li,Kyunghyun Cho,Chong Liu
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-60] ransformer-Based Decoding in Concatenated Coding Schemes Under Synchronization Errors

链接: https://arxiv.org/abs/2511.00999
作者: Julian Streit,Franziska Weindel,Reinhard Heckel
类目: Information Theory (cs.IT); Machine Learning (cs.LG)
*备注: 16 pages, 19 figures, a shortened version was published in the ISIT 2025 conference

点击查看摘要

[LG-61] Hydra: Dual Exponentiated Memory for Multivariate Time Series Analysis

链接: https://arxiv.org/abs/2511.00989
作者: Asal Meskin,Alireza Mirrokni,Ali Najar,Ali Behrouz
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-62] Balanced Multimodal Learning via Mutual Information

链接: https://arxiv.org/abs/2511.00987
作者: Rongrong Xie,Guido Sanguinetti
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-63] Modeling Microenvironment Trajectories on Spatial Transcriptomics with NicheFlow NEURIPS2025

链接: https://arxiv.org/abs/2511.00977
作者: Kristiyan Sakalyan,Alessandro Palma,Filippo Guerranti,Fabian J. Theis,Stephan Günnemann
类目: Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
*备注: 37 pages, 15 figures, to appear in NeurIPS 2025

点击查看摘要

[LG-64] Motion-Robust Multimodal Fusion of PPG and Accelerometer Signals for Three-Class Heart Rhythm Classification ISWC2025

链接: https://arxiv.org/abs/2511.00949
作者: Yangyang Zhao,Matti Kaisti,Olli Lahdenoja,Tero Koivisto
类目: Machine Learning (cs.LG)
*备注: Accepted for publication in the Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2025 International Symposium on Wearable Computers (UbiComp/ISWC 2025 Companion). 5 pages, 3 figures. Author’s accepted manuscript (AAM)

点击查看摘要

[LG-65] ransformers as Intrinsic Optimizers: Forward Inference through the Energy Principle

链接: https://arxiv.org/abs/2511.00907
作者: Ruifeng Ren,Sheng Ouyang,Huayi Tang,Yong Liu
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-66] Random Spiking Neural Networks are Stable and Spectrally Simple

链接: https://arxiv.org/abs/2511.00904
作者: Ernesto Araya,Massimiliano Datres,Gitta Kutyniok
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-67] HEATNETs: Explainable Random Feature Neural Networks for High-Dimensional Parabolic PDEs

链接: https://arxiv.org/abs/2511.00886
作者: Kyriakos Georgiou,Gianluca Fabiani,Constantinos Siettos,Athanasios N. Yannacopoulos
类目: Numerical Analysis (math.NA); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-68] SpEx: A Spectral Approach to Explainable Clustering NEURIPS2025

链接: https://arxiv.org/abs/2511.00885
作者: Tal Argov,Tal Wagner
类目: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS)
*备注: NeurIPS 2025

点击查看摘要

[LG-69] Controlling Gender Bias in Retrieval via a Backpack Architecture

链接: https://arxiv.org/abs/2511.00875
作者: Amirabbas Afzali,Amirreza Velae,Iman Ahmadi,Mohammad Aliannejadi
类目: Information Retrieval (cs.IR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-70] raining with Fewer Bits: Unlocking Edge LLM s Training with Stochastic Rounding

链接: https://arxiv.org/abs/2511.00874
作者: Taowen Liu,Marta Andronic,Deniz Gündüz,George A. Constantinides
类目: Machine Learning (cs.LG); Numerical Analysis (math.NA)
*备注:

点击查看摘要

[LG-71] FlexiCache: Leverag ing Temporal Stability of Attention Heads for Efficient KV Cache Management

链接: https://arxiv.org/abs/2511.00868
作者: Nazmul Takbir,Hamidreza Alikhani,Nikil Dutt,Sangeetha Abdu Jyothi
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-72] Identifying Slug Formation in Oil Well Pipelines: A Use Case from Industrial Analytics KDD

链接: https://arxiv.org/abs/2511.00851
作者: Abhishek Patange,Sharat Chidambaran,Prabhat Shankar,Manjunath G.B.,Anindya Chatterjee
类目: Machine Learning (cs.LG)
*备注: This paper ID 254 has been accepted for presentation in the Demonstration Track of the 13th ACM IKDD CODS Conference on Data Science CODS 2025, IISER Pune, India, from December 17 to 20, 2025

点击查看摘要

[LG-73] Real-Time Learning of Predictive Dynamic Obstacle Models for Robotic Motion Planning ICRA

链接: https://arxiv.org/abs/2511.00814
作者: Stella Kombo,Masih Haseli,Skylar Wei,Joel W. Burdick
类目: Robotics (cs.RO); Machine Learning (cs.LG); Systems and Control (eess.SY)
*备注: 10 pages, 6 figures, submitted to IEEE International Conference on Robotics and Automation (ICRA) 2025

点击查看摘要

[LG-74] Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games

链接: https://arxiv.org/abs/2511.00811
作者: Runyu Lu,Peng Zhang,Ruochuan Shi,Yuanheng Zhu,Dongbin Zhao,Yang Liu,Dong Wang,Cesare Alippi
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-75] AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs

链接: https://arxiv.org/abs/2511.00796
作者: Ran Yan,Youhe Jiang,Tianyuan Wu,Jiaxuan Gao,Zhiyu Mei,Wei Fu,Haohui Mai,Wei Wang,Yi Wu,Binhang Yuan
类目: Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-76] Reliable Curation of EHR Dataset via Large Language Models under Environmental Constraints

链接: https://arxiv.org/abs/2511.00772
作者: Raymond M. Xiong,Panyu Chen,Tianze Dong,Jian Lu,Benjamin Goldstein,Danyang Zhuo,Anru R. Zhang
类目: Databases (cs.DB); Machine Learning (cs.LG); Applications (stat.AP)
*备注:

点击查看摘要

[LG-77] A Framework Based on Graph Cellular Automata for Similarity Evaluation in Urban Spatial Networks

链接: https://arxiv.org/abs/2511.00768
作者: Peiru Wu,Maojun Zhai,Lingzhu Zhang
类目: ocial and Information Networks (cs.SI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-78] rust Region-Based Bayesian Optimisation to Discover Diverse Solutions

链接: https://arxiv.org/abs/2511.00750
作者: Kokila Kasuni Perera,Frank Neumann,Aneta Neumann
类目: Neural and Evolutionary Computing (cs.NE); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-79] Effective Series Decomposition and Components Learning for Time Series Generation ICDM2025

链接: https://arxiv.org/abs/2511.00747
作者: Zixuan Ma,Chenfeng Huang
类目: Machine Learning (cs.LG)
*备注: Accepted at IEEE International Conference on Data Mining (ICDM 2025). Camera-ready version to appear

点击查看摘要

[LG-80] Enhancing Heavy Rain Nowcasting with Multimodal Data: Integrating Radar and Satellite Observations ICML

链接: https://arxiv.org/abs/2511.00716
作者: Rama Kassoumeh,David Rügamer,Henning Oppel
类目: Machine Learning (cs.LG)
*备注: accepted to ICMLA 2025

点击查看摘要

[LG-81] Investigating the Robustness of Knowledge Tracing Models in the Presence of Student Concept Drift

链接: https://arxiv.org/abs/2511.00704
作者: Morgan Lee,Artem Frenk,Eamon Worden,Karish Gupta,Thinh Pham,Ethan Croteau,Neil Heffernan
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 10 pages, 6 figures

点击查看摘要

[LG-82] Privacy-Aware Time Series Synthesis via Public Knowledge Distillation

链接: https://arxiv.org/abs/2511.00700
作者: Penghang Liu,Haibei Zhu,Eleonora Kreacic,Svitlana Vyetrenko
类目: Machine Learning (cs.LG)
*备注: Published on Transactions on Machine Learning Research (TMLR)

点击查看摘要

[LG-83] Inference-Time Chain-of-Thought Pruning with Latent Informativeness Signals

链接: https://arxiv.org/abs/2511.00699
作者: Sophie Li(1),Nicholas Huang(2),Nayan Saxena(3),Nina Luo(4),Vincent Lin(5),Kevin Zhu(3),Sunishchal Dev(3) ((1) Columbia University, (2) University of British Columbia, (3) Algoverse AI Research, (4) Harvey Mudd College, (5) University of Florida)
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-84] Filtered Neural Galerkin model reduction schemes for efficient propagation of initial condition uncertainties in digital twins

链接: https://arxiv.org/abs/2511.00670
作者: Zhiyang Ning,Benjamin Peherstorfer
类目: Numerical Analysis (math.NA); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-85] Sensitivity Analysis for Climate Science with Generative Flow Models

链接: https://arxiv.org/abs/2511.00663
作者: Alex Dobra,Jakiw Pidstrigach,Tim Reichelt,Paolo Fraccaro,Johannes Jakubik,Anne Jones,Christian Schroeder de Witt,Philip Stier,Philip Torr
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-86] Reviving Stale Updates: Data-Free Knowledge Distillation for Asynchronous Federated Learning

链接: https://arxiv.org/abs/2511.00655
作者: Baris Askin,Holger R. Roth,Zhenyu Sun,Carlee Joe-Wong,Gauri Joshi,Ziyue Xu
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-87] Diluting Restricted Boltzmann Machines

链接: https://arxiv.org/abs/2511.00648
作者: C. Díaz-Faloh,R. Mulet
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-88] Stochastic Shortest Path with Sparse Adversarial Costs

链接: https://arxiv.org/abs/2511.00637
作者: Emmeran Johnson,Alberto Rumi,Ciara Pike-Burke,Patrick Rebeschini
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-89] Gaining Momentum: Uncovering Hidden Scoring Dynamics in Hockey through Deep Neural Sequencing and Causal Modeling

链接: https://arxiv.org/abs/2511.00615
作者: Daniel Griffiths,Piper Moskow
类目: Machine Learning (cs.LG)
*备注: 5 Pages, 4 Figures, 2 Tables

点击查看摘要

[LG-90] Agent ic Auto-Scheduling: An Experimental Study of LLM -Guided Loop Optimization

链接: https://arxiv.org/abs/2511.00592
作者: Massinissa Merouani,Islem Kara Bernou,Riyadh Baghdadi
类目: Programming Languages (cs.PL); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG); Performance (cs.PF)
*备注: Accepted at the 34th International Conference on Parallel Architectures and Compilation Techniques (PACT 2025). 12 pages, plus appendix

点击查看摘要

[LG-91] Sparse and nonparametric estimation of equations governing dynamical systems with applications to biology

链接: https://arxiv.org/abs/2511.00579
作者: G. Pillonetto,A. Giaretta,A. Aravkin,M. Bisiacco,T. Elston
类目: Machine Learning (cs.LG); Quantitative Methods (q-bio.QM); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-92] Bayesian Network Structure Discovery Using Large Language Models

链接: https://arxiv.org/abs/2511.00574
作者: Yinghuan Zhang,Yufei Zhang,Parisa Kordjamshidi,Zijun Cui
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-93] Variational Autoencoder for Calibration: A New Approach

链接: https://arxiv.org/abs/2511.00475
作者: Travis Barrett,Amit Kumar Mishra,Joyce Mwangama
类目: Machine Learning (cs.LG)
*备注: 6 pages, 5 figures

点击查看摘要

[LG-94] Deep Learning Approach to Anomaly Detection in Enterprise ETL Processes with Autoencoders

链接: https://arxiv.org/abs/2511.00462
作者: Xin Chen,Saili Uday Gadgil,Kangning Gao,Yi Hu,Cong Nie
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

Abstract:An anomaly detection method based on deep autoencoders is proposed to address anomalies that often occur in enterprise-level ETL data streams. The study first analyzes multiple types of anomalies in ETL processes, including delays, missing values, duplicate loading, and sudden abnormal changes, and applies data standardization and feature modeling to ensure stable and usable inputs. In the method design, the encoder-decoder structure compresses high-dimensional inputs into latent representations and reconstructs them, while reconstruction error is used to measure anomaly levels. Regularization constraints are introduced in the latent space to enhance feature sparsity and distribution learning, thereby improving robustness in complex data streams. Systematic analyses under different hyperparameter settings, environmental changes, and data characteristics show that the proposed method achieves superior performance in AUC, ACC, Precision, and Recall. The results demonstrate that the deep autoencoder-based detection mechanism can effectively capture latent distribution patterns in enterprise-level ETL data streams and accurately identify diverse anomalies, providing reliable support for enterprise data processing and intelligent analysis.

[LG-95] rust-Region Methods with Low-Fidelity Objective Models

链接: https://arxiv.org/abs/2511.00434
作者: Andrea Angino,Matteo Aurina,Alena Kopaničáková,Matthias Voigt,Marco Donatelli,Rolf Krause
类目: Numerical Analysis (math.NA); Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: Submitted to the Proceedings of Domain Decomposition Methods in Science and Engineering XXIX

点击查看摘要

[LG-96] Structure-Preserving Physics-Informed Neural Network for the Korteweg–de Vries (KdV) Equation

链接: https://arxiv.org/abs/2511.00418
作者: Victory Obieke,Emmanuel Oguadimma
类目: Machine Learning (cs.LG); Mathematical Physics (math-ph); Pattern Formation and Solitons (nlin.PS); Fluid Dynamics (physics.flu-dyn)
*备注: 9 Pages, 11 figures

点击查看摘要

[LG-97] ree Training: Accelerating Agent ic LLM s Training via Shared Prefix Reuse

链接: https://arxiv.org/abs/2511.00413
作者: Shaojie Wang,Jinghui Wang,Yinghan Cui,Xuxing Chen,Chao Wang,Liang Huang,Xiaojiang Zhang,Junyi Peng,Li Wan,Haotian Zhang,Bin Chen
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-98] PolyRecommender: A Multimodal Recommendation System for Polymer Discovery

链接: https://arxiv.org/abs/2511.00375
作者: Xin Wang,Yunhao Xiao,Rui Qiao
类目: Machine Learning (cs.LG); Information Retrieval (cs.IR)
*备注:

点击查看摘要

[LG-99] Split Learning-Enabled Framework for Secure and Light-weight Internet of Medical Things Systems

链接: https://arxiv.org/abs/2511.00336
作者: Siva Sai,Manish Prasad,Animesh Bhargava,Vinay Chamola,Rajkumar Buyya
类目: Cryptography and Security (cs.CR); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG)
*备注: 11 pages, 5 figures, Under review in an IEEE Transactions journal

点击查看摘要

[LG-100] A systematic evaluation of uncertainty quantification techniques in deep learning: a case study in photoplethysmography signal analysis

链接: https://arxiv.org/abs/2511.00301
作者: Ciaran Bench,Oskar Pfeffer,Vivek Desai,Mohammad Moulaeifard,Loïc Coquelin,Peter H. Charlton,Nils Strodthoff,Nando Hegemann,Philip J. Aston,Andrew Thompson
类目: Machine Learning (cs.LG); Medical Physics (physics.med-ph)
*备注:

点击查看摘要

[LG-101] Improving the Robustness of Control of Chaotic Convective Flows with Domain-Informed Reinforcement Learning

链接: https://arxiv.org/abs/2511.00272
作者: Michiel Straat,Thorben Markmann,Sebastian Peitz,Barbara Hammer
类目: Machine Learning (cs.LG); Fluid Dynamics (physics.flu-dyn)
*备注:

点击查看摘要

[LG-102] X-TRACK: Physics-Aware xLSTM for Realistic Vehicle Trajectory Prediction

链接: https://arxiv.org/abs/2511.00266
作者: Aanchal Rajesh Chugh,Marion Neumeier,Sebastian Dorn
类目: Machine Learning (cs.LG); Robotics (cs.RO)
*备注:

点击查看摘要

[LG-103] A Tight Lower Bound for Non-stochastic Multi-armed Bandits with Expert Advice

链接: https://arxiv.org/abs/2511.00257
作者: Zachary Chase,Shinji Ito,Idan Mehalel
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-104] Iterative Foundation Model Fine-Tuning on Multiple Rewards NEURIPS2025

链接: https://arxiv.org/abs/2511.00220
作者: Pouya M. Ghari,Simone Sciabola,Ye Wang
类目: Machine Learning (cs.LG)
*备注: Accepted to NeurIPS 2025

点击查看摘要

[LG-105] Diffusion LLM s are Natural Adversaries for any LLM

链接: https://arxiv.org/abs/2511.00203
作者: David Lüdke,Tom Wollschläger,Paul Ungermann,Stephan Günnemann,Leo Schwinn
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-106] Position: Vibe Coding Needs Vibe Reasoning : Improving Vibe Coding with Formal Verification

链接: https://arxiv.org/abs/2511.00202
作者: Jacqueline Mitchell,Yasser Shaaban
类目: oftware Engineering (cs.SE); Machine Learning (cs.LG); Logic in Computer Science (cs.LO)
*备注: 7 pages, 3 figures, In Proceedings of the 1st ACM SIGPLAN International Workshop on Language Models and Programming Languages (LMPL’25), October 12-18, 2025, Singapore, Singapore. ACM, New York, NY, USA

点击查看摘要

[LG-107] Reducing Robotic Upper-Limb Assessment Time While Maintaining Precision: A Time Series Foundation Model Approach

链接: https://arxiv.org/abs/2511.00193
作者: Faranak Akbarifar,Nooshin Maghsoodi,Sean P Dukelow,Stephen Scott,Parvin Mousavi
类目: Robotics (cs.RO); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-108] PDE-SHARP: PDE Solver Hybrids Through Analysis Refinement Passes

链接: https://arxiv.org/abs/2511.00183
作者: Shaghayegh Fazliani,Madeleine Udell
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-109] Study on Supply Chain Finance Decision-Making Model and Enterprise Economic Performance Prediction Based on Deep Reinforcement Learning

链接: https://arxiv.org/abs/2511.00166
作者: Shiman Zhang,Jinghan Zhou,Zhoufan Yu,Ningai Leng
类目: Machine Learning (cs.LG)
*备注: 9 pages, 3 figures

点击查看摘要

[LG-110] Physiologically Active Vegetation Reverses Its Cooling Effect in Humid Urban Climates

链接: https://arxiv.org/abs/2511.00134
作者: Angana Borah,Adrija Datta,Ashish S. Kumar,Raviraj Dave,Udit Bhatia
类目: Machine Learning (cs.LG)
*备注: 27 pages, 5 figures

点击查看摘要

[LG-111] A Comparative Analysis of LLM Adaptation: SFT LoRA and ICL in Data-Scarce Scenarios

链接: https://arxiv.org/abs/2511.00130
作者: Bernd Bohnet,Rumen Dangovski,Kevin Swersky,Sherry Moore,Arslan Chaudhry,Kathleen Kenealy,Noah Fiedel
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-112] Analysis of Line Break prediction models for detecting defensive breakthrough in football

链接: https://arxiv.org/abs/2511.00121
作者: Shoma Yagi,Jun Ichikawa,Genki Ichinose
类目: Machine Learning (cs.LG); Physics and Society (physics.soc-ph); Applications (stat.AP)
*备注: 14 pages, 8 figures

点击查看摘要

[LG-113] MeixnerNet: Adaptive and Robust Spectral Graph Neural Networks with Discrete Orthogonal Polynomials

链接: https://arxiv.org/abs/2511.00113
作者: Huseyin Goksu
类目: Machine Learning (cs.LG); Signal Processing (eess.SP)
*备注:

点击查看摘要

[LG-114] Forecasting Occupational Survivability of Rickshaw Pullers in a Changing Climate with Wearable Data

链接: https://arxiv.org/abs/2511.00081
作者: Masfiqur Rahaman,Maoyejatun Hasana,Shahad Shahriar Rahman,MD Sajid Mostafiz Noor,Razin Reaz Abedin,Md Toki Tahmid,Duncan Watson Parris,Tanzeem Choudhury,A. B. M. Alim Al Islam,Tauhidur Rahman
类目: Computers and Society (cs.CY); Human-Computer Interaction (cs.HC); Information Retrieval (cs.IR); Machine Learning (cs.LG); Applications (stat.AP)
*备注: This is a preprint version of a manuscript accepted and to be published in the Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT)

点击查看摘要

[LG-115] flowengineR: A Modular and Extensible Framework for Fair and Reproducible Workflow Design in R

链接: https://arxiv.org/abs/2511.00079
作者: Maximilian Willer,Peter Ruckdeschel
类目: Machine Learning (cs.LG); Computers and Society (cs.CY); Methodology (stat.ME)
*备注: 27 pages, 7 figures, 1 table

点击查看摘要

[LG-116] Bridging Vision Language and Mathematics: Pictographic Character Reconstruction with Bézier Curves

链接: https://arxiv.org/abs/2511.00076
作者: Zihao Wan,Pau Tong Lin Xu,Fuwen Luo,Ziyue Wang,Peng Li,Yang Liu
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-117] PDA-LSTM: Knowledge-driven page data arrangement based on LSTM for LCM supression in QLC 3D NAND flash memories

链接: https://arxiv.org/abs/2511.00075
作者: Qianhui Li,Weiya Wang,Qianqi Zhao,Tong Qu,Jing He,Xuhong Qiang,Jingwen Hou,Ke Chen,Bao Zhang,Qi Wang
类目: Hardware Architecture (cs.AR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-118] Wavelet-Based Feature Extraction and Unsupervised Clustering for Parity Detection: A Feature Engineering Perspective

链接: https://arxiv.org/abs/2511.00071
作者: Ertugrul Mutlu
类目: Machine Learning (cs.LG); Signal Processing (eess.SP)
*备注: 8 pages, 2 figures. Code: this http URL

点击查看摘要

[LG-119] oken-Regulated Group Relative Policy Optimization for Stable Reinforcement Learning in Large Language Models

链接: https://arxiv.org/abs/2511.00066
作者: Tue Le,Nghi D.Q.Bui,Linh Ngo Van,Trung Le
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-120] EVINGCA: Adaptive Graph Clustering with Evolving Neighborhood Statistics

链接: https://arxiv.org/abs/2511.00064
作者: Randolph Wiredu-Aidoo
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-121] Feature-Guided Analysis of Neural Networks: A Replication Study

链接: https://arxiv.org/abs/2511.00052
作者: Federico Formica,Stefano Gregis,Aurora Francesca Zanenga,Andrea Rota,Mark Lawford,Claudio Menghi
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-122] ReLaX-Net: Reusing Layers for Parameter-Efficient Physical Neural Networks

链接: https://arxiv.org/abs/2511.00044
作者: Kohei Tsuchiyama,Andre Roehm,Takatomo Mihana,Ryoichi Horisaki
类目: Machine Learning (cs.LG); Adaptation and Self-Organizing Systems (nlin.AO)
*备注:

点击查看摘要

[LG-123] Physics-Informed Neural Network Frameworks for the Analysis of Engineering and Biological Dynamical Systems Governed by Ordinary Differential Equations

链接: https://arxiv.org/abs/2511.00043
作者: Tyrus Whitman,Andrew Particka,Christopher Diers,Ian Griffin,Charuka Wickramasinghe,Pradeep Ranaweera
类目: Machine Learning (cs.LG)
*备注: 21 pages, 10 figures, 5 tables

点击查看摘要

[LG-124] Neural Architecture Search for global multi-step Forecasting of Energy Production Time Series

链接: https://arxiv.org/abs/2511.00035
作者: Georg Velev,Stefan Lessmann
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-125] On the Fundamental Limitations of Decentralized Learnable Reward Shaping in Cooperative Multi-Agent Reinforcement Learning

链接: https://arxiv.org/abs/2511.00034
作者: Aditya Akella
类目: Multiagent Systems (cs.MA); Machine Learning (cs.LG)
*备注: 8 pages, 5 figures, 2 tables

点击查看摘要

[LG-126] On the Structure of Floating-Point Noise in Batch-Invariant GPU Matrix Multiplication

链接: https://arxiv.org/abs/2511.00025
作者: Tadisetty Sai Yashwanth
类目: Numerical Analysis (math.NA); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-127] Matrix Phylogeny: Compact Spectral Fingerprints for Trap-Robust Preconditioner Selection

链接: https://arxiv.org/abs/2511.00012
作者: Jinwoo Baek
类目: Numerical Analysis (math.NA); Machine Learning (cs.LG)
*备注: 16 Pages

点击查看摘要

[LG-128] Disciplined Biconvex Programming

链接: https://arxiv.org/abs/2511.01813
作者: Hao Zhu,Joschka Boedecker
类目: Optimization and Control (math.OC); Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG); Mathematical Software (cs.MS)
*备注:

点击查看摘要

[LG-129] Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach

链接: https://arxiv.org/abs/2511.01680
作者: Jacob Carlson
类目: Econometrics (econ.EM); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-130] Partial Trace-Class Bayesian Neural Networks

链接: https://arxiv.org/abs/2511.01628
作者: Arran Carter,Torben Sell
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Methodology (stat.ME)
*备注: 10 pages, 4 figures

点击查看摘要

[LG-131] Fast memory-efficient genomic interval tokenizers for modern machine learning

链接: https://arxiv.org/abs/2511.01555
作者: Nathan J. LeRoy,Donald R. Campbell Jr,Seth Stadick,Oleksandr Khoroshevskyi,Sang-Hoon Park,Ziyang Hu,Nathan C. Sheffield
类目: Genomics (q-bio.GN); Machine Learning (cs.LG)
*备注: 4 pages, 1 figure

点击查看摘要

[LG-132] Quantum Blackwells Ordering and Differential Privacy

链接: https://arxiv.org/abs/2511.01467
作者: Ayanava Dasgupta,Naqueeb Ahmad Warsi,Masahito Hayashi
类目: Quantum Physics (quant-ph); Information Theory (cs.IT); Machine Learning (cs.LG)
*备注: 46 pages, 3 figures

点击查看摘要

[LG-133] Split-Flows: Measure Transport and Information Loss Across Molecular Resolutions

链接: https://arxiv.org/abs/2511.01464
作者: Sander Hummerich,Tristan Bereau,Ullrich Köthe
类目: Chemical Physics (physics.chem-ph); Machine Learning (cs.LG); Computational Physics (physics.comp-ph)
*备注:

点击查看摘要

[LG-134] Optimal Attention Temperature Enhances In-Context Learning under Distribution Shift

链接: https://arxiv.org/abs/2511.01292
作者: Samet Demir,Zafer Dogan
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: 26 pages, 6 figures

点击查看摘要

[LG-135] Stability of the Kim–Milman flow map

链接: https://arxiv.org/abs/2511.01154
作者: Sinho Chewi,Aram-Alexandre Pooladian,Matthew S. Zhang
类目: Probability (math.PR); Machine Learning (cs.LG); Statistics Theory (math.ST)
*备注:

点击查看摘要

[LG-136] Generative Machine Learning Models for the Deconvolution of Charge Carrier Dynamics in Organic Photovoltaic Cells

链接: https://arxiv.org/abs/2511.01118
作者: Li Raymond,Salim Flora,Wang Sijin,Wright Brendan
类目: Materials Science (cond-mat.mtrl-sci); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-137] Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point Processes

链接: https://arxiv.org/abs/2511.01096
作者: Alex Boyd,Andrew Warrington,Taha Kass-Hout,Parminder Bhatia,Danica Xiao
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-138] Generalized Guarantees for Variational Inference in the Presence of Even and Elliptical Symmetry

链接: https://arxiv.org/abs/2511.01064
作者: Charles C. Margossian,Lawrence K. Saul
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Computation (stat.CO)
*备注:

点击查看摘要

[LG-139] Binary perceptron computational gap – a parametric fl RDT view

链接: https://arxiv.org/abs/2511.01037
作者: Mihailo Stojnic
类目: Machine Learning (stat.ML); Disordered Systems and Neural Networks (cond-mat.dis-nn); Information Theory (cs.IT); Machine Learning (cs.LG); Probability (math.PR)
*备注:

点击查看摘要

[LG-140] owards Channel Charting Enhancement with Non-Reconfigurable Intelligent Surfaces

链接: https://arxiv.org/abs/2511.00919
作者: Mahdi Maleki,Reza Agahzadeh Ayoubi,Marouan Mizmizi,Umberto Spagnolini
类目: ignal Processing (eess.SP); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-141] Perturbations in the Orthogonal Complement Subspace for Efficient Out-of-Distribution Detection

链接: https://arxiv.org/abs/2511.00849
作者: Zhexiao Huang,Weihao He,Shutao Deng,Junzhe Chen,Chao Yuan,Hongxin Wang,Changsheng Zhou
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-142] Correspondence Between Ising Machines and Neural Networks

链接: https://arxiv.org/abs/2511.00746
作者: Andrew G. Moore
类目: Disordered Systems and Neural Networks (cond-mat.dis-nn); Emerging Technologies (cs.ET); Machine Learning (cs.LG); Quantum Physics (quant-ph)
*备注: 22 pages, 4 figures

点击查看摘要

[LG-143] SOCRATES: Simulation Optimization with Correlated Replicas and Adaptive Trajectory Evaluations

链接: https://arxiv.org/abs/2511.00685
作者: Haoting Zhang,Haoxian Chen,Donglin Zhan,Hanyang Zhao,Henry Lam,Wenpin Tang,David Yao,Zeyu Zheng
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-144] Accuracy estimation of neural networks by extreme value theory

链接: https://arxiv.org/abs/2511.00490
作者: Gero Junike,Marco Oesting
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Probability (math.PR)
*备注:

点击查看摘要

[LG-145] A Streaming Sparse Cholesky Method for Derivative-Informed Gaussian Process Surrogates Within Digital Twin Applications

链接: https://arxiv.org/abs/2511.00366
作者: Krishna Prasath Logakannan,Shridhar Vashishtha,Jacob Hochhalter,Shandian Zhe,Robert M. Kirby
类目: Machine Learning (stat.ML); Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-146] NaturalVoices: A Large-Scale Spontaneous and Emotional Podcast Dataset for Voice Conversion

链接: https://arxiv.org/abs/2511.00256
作者: Zongyang Du,Shreeram Suresh Chandra,Ismail Rasim Ulgen,Aurosweta Mahapatra,Ali N. Salman,Carlos Busso,Berrak Sisman
类目: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)
*备注: Under review for IEEE Transactions on Affective Computing

点击查看摘要

[LG-147] Gradient Boosted Mixed Models: Flexible Joint Estimation of Mean and Variance Components for Clustered Data

链接: https://arxiv.org/abs/2511.00217
作者: Mitchell L. Prevett,Francis K. C. Hui,Zhi Yang Tho,A. H. Welsh,Anton H. Westveld
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Computation (stat.CO); Methodology (stat.ME)
*备注:

点击查看摘要

[LG-148] ransfer learning discovery of molecular modulators for perovskite solar cells

链接: https://arxiv.org/abs/2511.00204
作者: Haoming Yan,Xinyu Chen,Yanran Wang,Zhengchao Luo,Weizheng Huang,Hongshuai Wang,Peng Chen,Yuzhi Zhang,Weijie Sun,Jinzhuo Wang,Qihuang Gong,Rui Zhu,Lichen Zhao
类目: Materials Science (cond-mat.mtrl-sci); Machine Learning (cs.LG); Applied Physics (physics.app-ph)
*备注:

点击查看摘要

[LG-149] Using machine learning methods to predict cognitive age from psychophysiological tests

链接: https://arxiv.org/abs/2511.00013
作者: Daria D. Tyurina,Sergey V. Stasenko,Konstantin V. Lushnikov,Maria V. Vedunova
类目: Neurons and Cognition (q-bio.NC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-150] Group-Equivariant Diffusion Models for Lattice Field Theory

链接: https://arxiv.org/abs/2510.26081
作者: Octavio Vega,Javad Komijani,Aida El-Khadra,Marina Marinkovic
类目: High Energy Physics - Lattice (hep-lat); Machine Learning (cs.LG)
*备注: 45 pages, 12 figures

点击查看摘要

信息检索

[IR-0] Calculating Web Impact Factor for University Websites of Jammu and Kashmir: A Study

链接: https://arxiv.org/abs/2511.01496
作者: Muneer Ahmad,M Sadik Batcha,Wasim Rashid,Obaid Hafiz
类目: Digital Libraries (cs.DL); Information Retrieval (cs.IR)
*备注: 11 pages, Research Paper

点击查看摘要

[IR-1] Impact and Relevance of Cognition Journal in the Field of Cognitive Science: An Evaluation

链接: https://arxiv.org/abs/2511.01485
作者: M Sadik Batcha,Younis Rashid Dar,Muneer Ahmad
类目: Digital Libraries (cs.DL); Information Retrieval (cs.IR)
*备注: 8 pages, 4 figures, Research Paper. arXiv admin note: substantial text overlap with arXiv:2102.12912 , arXiv:2102.09900 , arXiv:2102.09894

点击查看摘要

[IR-2] CAT-ID2: Category-Tree Integrated Document Identifier Learning for Generative Retrieval In E-commerce WSDM’26

链接: https://arxiv.org/abs/2511.01461
作者: Xiaoyu Liu,Fuwei Zhang,Yiqing Wu,Xinyu Jia,Zenghua Xia,Fuzhen Zhuang,Zhao Zhang,Fei Jiang,Wei Lin
类目: Information Retrieval (cs.IR)
*备注: Accepted by WSDM’26

点击查看摘要

[IR-3] LiCoMemory: Lightweight and Cognitive Agent ic Memory for Efficient Long-Term Reasoning

链接: https://arxiv.org/abs/2511.01448
作者: Zhengjun Huang,Zhoujin Tian,Qintian Guo,Fangyuan Zhang,Yingli Zhou,Di Jiang,Xiaofang Zhou
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-4] A Soft-partitioned Semi-supervised Collaborative Transfer Learning Approach for Multi-Domain Recommendation CIKM’25

链接: https://arxiv.org/abs/2511.01404
作者: Xiaoyu Liu,Yiqing Wu,Ruidong Han,Fuzhen Zhuang,Xiang Li,Wei Lin
类目: Information Retrieval (cs.IR)
*备注: Accepted by CIKM’25

点击查看摘要

[IR-5] Contextual Relevance and Adaptive Sampling for LLM -Based Document Reranking

链接: https://arxiv.org/abs/2511.01208
作者: Jerry Huang,Siddarth Madala,Cheng Niu,Julia Hockenmaier,Tong Zhang
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-6] REaR: Retrieve Expand and Refine for Effective Multitable Retrieval

链接: https://arxiv.org/abs/2511.00805
作者: Rishita Agarwal,Himanshu Singhal,Peter Baile Chen,Manan Roy Choudhury,Dan Roth,Vivek Gupta
类目: Information Retrieval (cs.IR)
*备注: 13 pages, 2 figures, 8 tables

点击查看摘要

[IR-7] axonomy-based Negative Sampling In Personalized Semantic Search for E-commerce

链接: https://arxiv.org/abs/2511.00694
作者: Uthman Jinadu,Siawpeng Er,Le Yu,Chen Liang,Bingxin Li,Yi Ding,Aleksandar Velkoski
类目: Information Retrieval (cs.IR)
*备注: Accepted at 2025 IEEE International Conference on Big Data

点击查看摘要

[IR-8] Object-Centric Analysis of XES Event Logs: Integrating OCED Modeling with SPARQL Queries

链接: https://arxiv.org/abs/2511.00693
作者: Saba Latif,Huma Latif,Muhammad Rameez Ur Rahman
类目: Databases (cs.DB); Information Retrieval (cs.IR)
*备注: 12 pages, 4 figures, PROFES2025 conference

点击查看摘要

Abstract:Object Centric Event Data (OCED) has gained attention in recent years within the field of process mining. However, there are still many challenges, such as connecting the XES format to object-centric approaches to enable more insightful analysis. It is important for a process miner to understand the insights and dependencies of events in the event log to see what is going on in our processes. In previous standards, the dependencies of event logs are only used to show events, but not their dependencies among each other and actions in detail as described in OCEDO. There is more information in the event log when it is revealed using the OCEDO model. It becomes more understandable and easier to grasp the concepts and deal with the processes. This paper proposes the use of Object-Centric Event Data Ontology (OCEDO) to overcome the limitations of the XES standard in event logs for process mining. We demonstrate how the OCEDO approach, integrated with SPARQL queries, can be applied to the BPIC 2013 dataset to make the relationships between events and objects more explicit. It describes dealing with the meta descriptions of the OCEDO model on a business process challenge as an event log. It improves the completeness and readability of process data, suggesting that object-centric modeling allows for richer analyses than traditional approaches.

[IR-9] Listwise Preference Diffusion Optimization for User Behavior Trajectories Prediction

链接: https://arxiv.org/abs/2511.00530
作者: Hongtao Huang,Chengkai Huang,Junda Wu,Tong Yu,Julian McAuley,Lina Yao
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-10] Simple and Behavior-Driven Augmentation for Recommendation with Rich Collaborative Signals

链接: https://arxiv.org/abs/2511.00436
作者: Doyun Choi,Cheonwoo Lee,Jaemin Yoo
类目: Information Retrieval (cs.IR)
*备注: 10 pages. This paper is accepted at IEEE BigData 2025 (Short)

点击查看摘要