Arxiv今日论文 | 2025-03-11

本篇博文主要内容为 2025-03-11 从Arxiv.org论文网站获取的最新论文列表，自动更新，按照NLP、CV、ML、AI、IR五个大方向区分，若需要邮件定时接收，请在评论区留下你的邮箱号。

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

友情提示: 如何您需要邮箱接收每日论文数据，请在评论处留下你的邮箱。

目录

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

概览 (2025-03-11)

今日共更新1150篇论文,其中:

• 自然语言处理共154篇(Computation and Language (cs.CL))
• 人工智能共339篇(Artificial Intelligence (cs.AI))
• 计算机视觉共382篇(Computer Vision and Pattern Recognition (cs.CV))
• 机器学习共301篇(Machine Learning (cs.LG))

自然语言处理

[NLP-0] SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models

链接: https://arxiv.org/abs/2503.07605
作者: Xun Liang,Hanyu Wang,Huayi Lai,Simin Niu,Shichao Song,Jiawei Yang,Jihao Zhao,Feiyu Xiong,Bo Tang,Zhiyu Li
机构: School of Information, Renmin University of China (中国人民大学信息学院); Institute for Advanced Algorithms Research (上海先进算法研究所)
类目: Computation and Language (cs.CL)
备注: 15 pages, 7 figures, 8 tables

点击查看摘要

[NLP-1] Implicit Reasoning in Transformers is Reasoning through Shortcuts

链接: https://arxiv.org/abs/2503.07604
作者: Tianhe Lin,Jian Xie,Siyu Yuan,Deqing Yang
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-2] Detection Avoidance Techniques for Large Language Models

链接: https://arxiv.org/abs/2503.07595
作者: Sinclair Schneider,Florian Steuber,Joao A. G. Schneider,Gabi Dreo Rodosek
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-3] VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models

链接: https://arxiv.org/abs/2503.07575
作者: Jen-tse Huang,Jiantong Qin,Jianping Zhang,Youliang Yuan,Wenxuan Wang,Jieyu Zhao
机构: University of Southern California (南加州大学); University of Bristol (布里斯托尔大学); Independent Researcher (独立研究员); Centre National de la Recherche Scientifique (法国国家科学研究中心); University of California, Los Angeles (加州大学洛杉矶分校)
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注: 9 pages

点击查看摘要

[NLP-4] Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

链接: https://arxiv.org/abs/2503.07572
作者: Yuxiao Qu,Matthew Y. R. Yang,Amrith Setlur,Lewis Tunstall,Edward Emanuel Beeching,Ruslan Salakhutdinov,Aviral Kumar
机构: Carnegie Mellon University (卡内基梅隆大学); Hugging Face; 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:

点击查看摘要

[NLP-5] KSOD: Knowledge Supplement for LLM s On Demand

链接: https://arxiv.org/abs/2503.07550
作者: Haoran Li,Junfeng Hu
机构: National Key Laboratory for Multimedia Information Processing (国家重点实验室), School of Computer Science (计算机科学学院), Peking University (北京大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-6] XIFBench: Evaluating Large Language Models on Multilingual Instruction Following

链接: https://arxiv.org/abs/2503.07539
作者: Zhenyu Li,Kehai Chen,Yunfei Long,Xuefeng Bai,Yaoyin Zhang,Xuchen Wei,Juntao Li,Min Zhang
机构: Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China (哈尔滨工业大学（深圳）计算与智能研究所); School of Computer Science and Electronic Engineering, University of Essex, Colchester, United Kingdom (英国埃塞克斯大学计算机科学与电子工程学院); School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China (哈尔滨工业大学（深圳）计算机科学与技术学院); School of Computer Science and Technology, Soochow University, China (苏州大学计算机科学与技术学院)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-7] LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL

【速读】： 该论文旨在解决增强大型多模态模型（Large Multimodal Models, LMMs）推理能力所面临的独特挑战，特别是在参数规模为30亿（3B）的紧凑架构中，由于视觉感知与逻辑推理之间复杂交互的影响，以及架构约束限制了推理能力和模态对齐。论文指出，虽然基于规则的强化学习（Reinforcement Learning, RL）在纯文本领域表现出色，但在多模态扩展时面临两个关键障碍：(1) 由于答案模糊和复杂推理示例稀缺导致的数据局限性；(2) 多模态预训练引起的底层推理能力下降。为应对这些挑战，论文提出了一种名为“方法”的两阶段框架，通过基础推理增强（Foundational Reasoning Enhancement, FRE）和多模态泛化训练（Multimodal Generalization Training, MGT）来适配基于规则的RL用于多模态推理。其中，FRE阶段首先利用纯文本数据并通过基于规则的RL加强推理能力，随后MGT阶段将这些推理能力推广到多模态领域。实验结果表明，该方法在多模态和纯文本基准测试中分别实现了4.83%和4.5%的平均性能提升，并在复杂的足球比赛任务中提升了3.63%，验证了基于文本的推理增强能够有效实现多模态泛化，提供了一种无需昂贵高质量多模态训练数据的数据高效范式。

链接: https://arxiv.org/abs/2503.07536
作者: Yingzhe Peng,Gongrui Zhang,Miaosen Zhang,Zhiyuan You,Jie Liu,Qipeng Zhu,Kai Yang,Xingzhong Xu,Xin Geng,Xu Yang
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

Abstract:Enhancing reasoning in Large Multimodal Models (LMMs) faces unique challenges from the complex interplay between visual perception and logical reasoning, particularly in compact 3B-parameter architectures where architectural constraints limit reasoning capacity and modality alignment. While rule-based reinforcement learning (RL) excels in text-only domains, its multimodal extension confronts two critical barriers: (1) data limitations due to ambiguous answers and scarce complex reasoning examples, and (2) degraded foundational reasoning induced by multimodal pretraining. To address these challenges, we propose \textbf\method, a two-stage framework adapting rule-based RL for multimodal reasoning through \textbfFoundational Reasoning Enhancement (FRE) followed by \textbfMultimodal Generalization Training (MGT). The FRE stage first strengthens reasoning abilities using text-only data with rule-based RL, then the MGT stage generalizes these reasoning capabilities to multimodal domains. Experiments on Qwen2.5-VL-Instruct-3B demonstrate that \method achieves 4.83% and 4.5% average improvements over baselines in multimodal and text-only benchmarks, respectively, with a 3.63% gain in complex Football Game tasks. These results validate that text-based reasoning enhancement enables effective multimodal generalization, offering a data-efficient paradigm that bypasses costly high-quality multimodal training data. Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI) Cite as: arXiv:2503.07536 [cs.CL] (or arXiv:2503.07536v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2503.07536 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Yingzhe Peng [view email] [v1] Mon, 10 Mar 2025 17:04:14 UTC (9,790 KB)
zh

[NLP-8] GRITHopper: Decomposition-Free Multi-Hop Dense Retrieval ACL

链接: https://arxiv.org/abs/2503.07519
作者: Justus-Jonas Erker,Nils Reimers,Iryna Gurevych
机构: Ubiquitous Knowledge Processing Lab (UKP Lab) (普适知识处理实验室); Department of Computer Science and Hessian Center for AI (hessian.AI) (计算机科学系和黑森人工智能中心); Technical University of Darmstadt (达姆施塔特工业大学); cohere (Cohere)
类目: Information Retrieval (cs.IR); Computation and Language (cs.CL)
备注: Under Review at ACL Rolling Review (ARR)

点击查看摘要

[NLP-9] okenButler: Token Importance is Predictable

链接: https://arxiv.org/abs/2503.07518
作者: Yash Akhauri,Ahmed F AbouElhamayed,Yifei Gao,Chi-Chih Chang,Nilesh Jain,Mohamed S. Abdelfattah
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-10] Language Models Fail to Introspect About Their Knowledge of Language

【速读】： 该论文试图解决的问题是大型语言模型（Large Language Models, LLMs）是否能够内省其自身的内部状态。这种能力不仅能使LLMs更具可解释性，还能验证在语言学中使用标准内省方法来评估模型语法知识的有效性。论文的关键解决方案在于通过系统性地研究21个开源LLMs在两个理论上有意义的领域——语法知识和单词预测中的内省能力，并提出一个新的内省衡量标准：即模型在受到元语言提示后的响应能够在多大程度上预测自身字符串概率，而不仅仅是依赖于另一个具有几乎相同内部知识的模型所预测的结果。尽管元语言提示和概率比较都达到了高任务准确性，但研究并未发现证据表明LLMs拥有特权的“自我访问”能力。这一发现复杂化了近期关于模型能够内省的研究结果，并为避免将提示响应与模型的语言概括混淆提供了新的证据。

链接: https://arxiv.org/abs/2503.07513
作者: Siyuan Song,Jennifer Hu,Kyle Mahowald
机构: Department of Linguistics, The University of Texas at Austin (德克萨斯大学奥斯汀分校语言学系); Kempner Institute, Harvard University (哈佛大学 Kepner 研究所); Department of Linguistics, The University of Texas at Austin (德克萨斯大学奥斯汀分校语言学系)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

Abstract:There has been recent interest in whether large language models (LLMs) can introspect about their own internal states. Such abilities would make LLMs more interpretable, and also validate the use of standard introspective methods in linguistics to evaluate grammatical knowledge in models (e.g., asking “Is this sentence grammatical?”). We systematically investigate emergent introspection across 21 open-source LLMs, in two domains where introspection is of theoretical interest: grammatical knowledge and word prediction. Crucially, in both domains, a model’s internal linguistic knowledge can be theoretically grounded in direct measurements of string probability. We then evaluate whether models’ responses to metalinguistic prompts faithfully reflect their internal knowledge. We propose a new measure of introspection: the degree to which a model’s prompted responses predict its own string probabilities, beyond what would be predicted by another model with nearly identical internal knowledge. While both metalinguistic prompting and probability comparisons lead to high task accuracy, we do not find evidence that LLMs have privileged “self-access”. Our findings complicate recent results suggesting that models can introspect, and add new evidence to the argument that prompted responses should not be conflated with models’ linguistic generalizations.
zh

[NLP-11] Sometimes the Model doth Preach: Quantifying Religious Bias in Open LLM s through Demographic Analysis in Asian Nations

链接: https://arxiv.org/abs/2503.07510
作者: Hari Shankar,Vedanta S P,Tejas Cavale,Ponnurangam Kumaraguru,Abhijnan Chakraborty
机构: 未知
类目: Computers and Society (cs.CY); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-12] MedAgents Bench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning

链接: https://arxiv.org/abs/2503.07459
作者: Xiangru Tang,Daniel Shao,Jiwoong Sohn,Jiapeng Chen,Jiayi Zhang,Jinyu Xiang,Fang Wu,Yilun Zhao,Chenglin Wu,Wenqi Shi,Arman Cohan,Mark Gerstein
机构: Yale University (耶鲁大学); Stanford University (斯坦福大学); UT Southwestern Medical Center (德克萨斯大学西南医学中心)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-13] LLM s syntactically adapt their language use to their conversational partner ACL

链接: https://arxiv.org/abs/2503.07457
作者: Florian Kandra,Vera Demberg,Alexander Koller
机构: Saarland University (萨尔兰大学), Saarbrücken, Germany
类目: Computation and Language (cs.CL)
备注: 4 pages, 1 table, 1 figure, submitted to ACL

点击查看摘要

[NLP-14] Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration

链接: https://arxiv.org/abs/2503.07453
作者: Dylan J. Foster,Zakaria Mhammedi,Dhruv Rohatgi
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Statistics Theory (math.ST)
备注:

点击查看摘要

[NLP-15] Revisiting Noise in Natural Language Processing for Computational Social Science

链接: https://arxiv.org/abs/2503.07395
作者: Nadav Borenstein
机构: 未知
类目: Computation and Language (cs.CL)
备注: PhD thesis. Under the supervision of Prof. Isabelle Augenstein

点击查看摘要

[NLP-16] Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLM s

链接: https://arxiv.org/abs/2503.07384
作者: Gonzalo Mancera,Daniel de Alcala,Julian Fierrez,Ruben Tolosana,Aythami Morales
机构: Biometrics and Data Pattern Analytics Lab, Universidad Autónoma de Madrid (生物特征与数据模式分析实验室, 马德里自治大学), Spain
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-17] RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing

链接: https://arxiv.org/abs/2503.07358
作者: Yiqing Xie,Alex Xie,Divyanshu Sheth,Pengfei Liu,Daniel Fried,Carolyn Rose
机构: Carnegie Mellon University (卡内基梅隆大学); Shanghai Jiao Tong University (上海交通大学)
类目: Computation and Language (cs.CL); Software Engineering (cs.SE)
备注:

点击查看摘要

[NLP-18] Assessing the Macro and Micro Effects of Random Seeds on Fine-Tuning Large Language Models

链接: https://arxiv.org/abs/2503.07329
作者: Hao Zhou,Guergana Savova,Lijing Wang
机构: New Jersey Institute of Technology (新泽西理工学院); Boston Children’s Hospital (波士顿儿童医院); Harvard Medical School (哈佛医学院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 7 pages, 5 tables, 3 figures

点击查看摘要

[NLP-19] Benchmarking Chinese Medical LLM s: A Medbench-based Analysis of Performance Gaps and Hierarchical Optimization Strategies

链接: https://arxiv.org/abs/2503.07306
作者: Luyi Jiang,Jiayuan Chen,Lu Lu,Xinwei Peng,Lihao Liu,Junjun He,Jie Xu
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-20] An Information-Theoretic Approach to Identifying Formulaic Clusters in Textual Data

链接: https://arxiv.org/abs/2503.07303
作者: Gideon Yoffe,Yair Segev,Barak Sober
机构: Department of Statistics and Data Science, The Hebrew University of Jerusalem (希伯来大学耶路撒冷分校统计与数据科学系); Faculty of Theology, Carl von Ossietzky Universität Oldenburg (奥尔登堡卡尔·冯·奥斯瑟茨基大学神学院)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-21] A Graph-based Verification Framework for Fact-Checking

链接: https://arxiv.org/abs/2503.07282
作者: Yani Huang,Richong Zhang,Zhijie Nie,Junfan Chen,Xuefeng Zhang
机构: CCSE, School of Computer Science and Engineering, Beihang University (北京航空航天大学); Zhongguancun Laboratory (中关村实验室); School of Software, Beihang University (北京航空航天大学)
类目: Computation and Language (cs.CL)
备注: 13pages, 4figures

点击查看摘要

[NLP-22] VizTrust: A Visual Analytics Tool for Capturing User Trust Dynamics in Human-AI Communication

链接: https://arxiv.org/abs/2503.07279
作者: Xin Wang,Stephanie Tulk Jesso,Sadamori Kojaku,David M Neyens,Min Sun Kim
机构: School of Systems Science and Industrial Engineering, Binghamton University (宾厄姆顿大学); Department of Industrial Engineering, Clemson University (克莱姆森大学); School of Communication and Information, University of Hawaii at Manoa (夏威夷大学马诺阿分校)
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Accepted by ACM CHI conference 2025

点击查看摘要

[NLP-23] SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection SEMEVAL2025

链接: https://arxiv.org/abs/2503.07269
作者: Shamsuddeen Hassan Muhammad,Nedjma Ousidhoum,Idris Abdulmumin,Seid Muhie Yimam,Jan Philip Wahle,Terry Ruas,Meriem Beloucif,Christine De Kock,Tadesse Destaw Belay,Ibrahim Said Ahmad,Nirmal Surange,Daniela Teodorescu,David Ifeoluwa Adelani,Alham Fikri Aji,Felermino Ali,Vladimir Araujo,Abinew Ali Ayele,Oana Ignat,Alexander Panchenko,Yi Zhou,Saif M. Mohammad
机构: Imperial College London; Bayero University Kano; Cardiff University; DSFSI, University of Pretoria; University of Hamburg; University of Göttingen; Uppsala University; University of Melbourne; Instituto Politécnico Nacional; Wollo University; Northeastern University; IIIT Hyderabad; University of Alberta; MILA; McGill University; Canada CIFAR AI Chair; MBZUAI; LIACC, FEUP, University of Porto; Sailplane AI; Bahir Dar University; Santa Clara University; Skoltech; AIRI; National Research Council Canada
类目: Computation and Language (cs.CL)
备注: SemEval2025 Task11 (Task Description Paper). arXiv admin note: text overlap with arXiv:2502.11926

点击查看摘要

[NLP-24] WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation

链接: https://arxiv.org/abs/2503.07265
作者: Yuwei Niu,Munan Ning,Mengren Zheng,Bin Lin,Peng Jin,Jiaqi Liao,Kunpeng Ning,Bin Zhu,Li Yuan
机构: Peking University (北京大学); Chongqing University (重庆大学); PengCheng Laboratory (鹏城实验室); Rabbitpre AI (兔波智能)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Code, data and leaderboard: this https URL

点击查看摘要

[NLP-25] LLM -C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation NAACL2025

链接: https://arxiv.org/abs/2503.07237
作者: Junyeong Park,Seogyeong Jeong,Seyoung Song,Yohan Lee,Alice Oh
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Accepted to NAACL 2025 Workshop - C3NLP (Workshop on Cross-Cultural Considerations in NLP)

点击查看摘要

[NLP-26] Cross-Lingual IPA Contrastive Learning for Zero-Shot NER

链接: https://arxiv.org/abs/2503.07214
作者: Jimin Sohn,David R. Mortensen
机构: LG Innotek (LG Innotek); Carnegie Mellon University (卡内基梅隆大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 17 pages, 6 figures

点击查看摘要

[NLP-27] Contextual Cues in Machine Translation: Investigating the Potential of Multi-Source Input Strategies in LLM s and NMT Systems

链接: https://arxiv.org/abs/2503.07195
作者: Lia Shahnazaryan,Patrick Simianer,Joern Wuebker
机构: LILT (LILT)
类目: Computation and Language (cs.CL)
备注: 11 pages

点击查看摘要

[NLP-28] Multi-Modal 3D Mesh Reconstruction from Images and Text

链接: https://arxiv.org/abs/2503.07190
作者: Melvin Reka,Tessa Pulli,Markus Vincze
机构: Automation and Control Institute, TU Wien (自动化与控制研究所, 维也纳技术大学); ACIN, TU Wien (自动化与控制研究所, 维也纳技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注: under review

点击查看摘要

[NLP-29] Strategies for political-statement segmentation and labelling in unstructured text NAACL2025

链接: https://arxiv.org/abs/2503.07179
作者: Dmitry Nikolaev,Sean Papay
机构: University of Manchester (曼彻斯特大学); University of Bamberg (班贝格大学)
类目: Computation and Language (cs.CL)
备注: Accepted to NLP4DH 2025 @ NAACL 2025

点击查看摘要

[NLP-30] DeFine: A Decomposed and Fine-Grained Annotated Dataset for Long-form Article Generation

链接: https://arxiv.org/abs/2503.07170
作者: Ming Wang,Fang Wang,Minghao Hu,Li He,Haiyang Wang,Jun Zhang,Tianwei Yan,Li Li,Zhunchen Luo,Wei Luo,Xiaoying Bai,Guotong Geng
机构: North China University of Technology (华北理工大学); Peking University (北京大学); National University of Defense Technology (国防科技大学); Center of Information Research, AMS (AMS信息研究中心)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-31] MRCEval: A Comprehensive Challenging and Accessible Machine Reading Comprehension Benchmark

链接: https://arxiv.org/abs/2503.07144
作者: Shengkun Ma,Hao Peng,Lei Hou,Juanzi Li
机构: Department of Computer Science and Technology, Tsinghua University (计算机科学与技术系, 清华大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Under review

点击查看摘要

[NLP-32] A Systematic Comparison of Syntactic Representations of Dependency Parsing

链接: https://arxiv.org/abs/2503.07142
作者: Guillaume Wisniewski(LLF - UMR7110, UPCité),Ophélie Lacroix(UCPH)
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-33] Application of Multiple Chain-of-Thought in Contrastive Reasoning for Implicit Sentiment Analysis

链接: https://arxiv.org/abs/2503.07140
作者: Liwei Yang,Xinying Wang,Xiaotang Zhou,Zhengchao Wu,Ningning Tan
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-34] ASTRA: A Negotiation Agent with Adaptive and Strategic Reasoning through Action in Dynamic Offer Optimization

链接: https://arxiv.org/abs/2503.07129
作者: Deuksin Kwon,Jiwon Hae,Emma Clift,Daniel Shamsoddini,Jonathan Gratch,Gale M. Lucas
机构: University of Southern California (南加州大学); St. Olaf College (圣欧拉夫学院); Northwestern University (西北大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-35] PoseLess: Depth-Free Vision-to-Joint Control via Direct Image Mapping with VLM

链接: https://arxiv.org/abs/2503.07111
作者: Alan Dao(Gia Tuan Dao),Dinh Bach Vu,Tuan Le Duc Anh,Bui Quang Huy
机构: Menlo Research (Menlo Research)
类目: Robotics (cs.RO); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-36] A Novel Ophthalmic Benchmark for Evaluating Multimodal Large Language Models with Fundus Photographs and OCT Images

链接: https://arxiv.org/abs/2503.07094
作者: Xiaoyi Liang,Mouxiao Bian,Moxin Chen,Lihao Liu,Junjun He,Jie Xu,Lin Li
机构: Ninth People’s Hospital, Shanghai Jiao Tong University School of Medicine (上海交通大学医学院第九人民医院); Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology (上海市眼眶病眼肿瘤重点实验室); Shanghai Artificial Intelligence Laboratory (上海人工智能实验室)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-37] Linguistic Knowledge Transfer Learning for Speech Enhancement

链接: https://arxiv.org/abs/2503.07078
作者: Kuo-Hsuan Hung,Xugang Lu,Szu-Wei Fu,Huan-Hsin Tseng,Hsin-Yi Lin,Chii-Wann Lin,Yu Tsao
机构: Department of Biomedical Engineering, National Taiwan University (国立台湾大学生物医学工程学系), Taipei, Taiwan; National Institute of Information and Communications Technology (信息通信技术国立研究所), Japan; NVIDIA (英伟达), Taipei, Taiwan; AI & ML Department, Brookhaven National Laboratory (布鲁克海文国家实验室人工智能与机器学习部门), Upton NY, USA; Department of Mathematics and Computer Science, Seton Hall University (塞顿霍尔大学数学与计算机科学系), South Orange, NJ 07079, USA; Research Center for Information Technology Innovation, Academia Sinica (中央研究院资讯技术创新研究中心), Taipei, Taiwan
类目: Computation and Language (cs.CL); Audio and Speech Processing (eess.AS)
备注: 11 pages, 6 figures

点击查看摘要

[NLP-38] DistiLLM -2: A Contrastive Approach Boosts the Distillation of LLM s

链接: https://arxiv.org/abs/2503.07067
作者: Jongwoo Ko,Tianyi Chen,Sungnyun Kim,Tianyu Ding,Luming Liang,Ilya Zharkov,Se-Young Yun
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: The code will be available soon at this https URL

点击查看摘要

[NLP-39] DatawiseAgent : A Notebook-Centric LLM Agent Framework for Automated Data Science

链接: https://arxiv.org/abs/2503.07044
作者: Ziming You,Yumiao Zhang,Dexuan Xu,Yiwei Lou,Yandong Yan,Wei Wang,Huaming Zhang,Yu Huang
机构: National Engineering Research Center for Software Engineering, Peking University (北京大学软件工程国家工程研究中心); School of Software & Microelectronics, Peking University (北京大学软件与微电子学院); School of Computer Science, Peking University (北京大学计算机科学学院); Xi’an Jiaotong University (西安交通大学); Institute of Basic Theory of Chinese Medicine, China Academy of Chinese Medical Sciences (中国中医科学院中药基础理论研究所)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-40] CM-3CEval: A Triaxial Benchmark for Assessing Responses from Large Language Models in Traditional Chinese Medicine

链接: https://arxiv.org/abs/2503.07041
作者: Tianai Huang,Lu Lu,Jiayuan Chen,Lihao Liu,Junjun He,Yuping Zhao,Wenchao Tang,Jie Xu
机构: School of Acupuncture-Moxibustion and Tuina, Shanghai University of Traditional Chinese Medicine (上海中医药大学针灸推拿学院), Shanghai, China; Shanghai Artificial Intelligence Laboratory (上海人工智能实验室), Shanghai, China; China Academy of Chinese Medical Sciences (中国中医科学院), Beijing, China
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-41] Bot Wars Evolved: Orchestrating Competing LLM s in a Counterstrike Against Phone Scams

链接: https://arxiv.org/abs/2503.07036
作者: Nardine Basta,Conor Atkins,Dali Kaafar
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-42] Multimodal Human-AI Synergy for Medical Imaging Quality Control: A Hybrid Intelligence Framework with Adaptive Dataset Curation and Closed-Loop Evaluation

链接: https://arxiv.org/abs/2503.07032
作者: Zhi Qin,Qianhui Gui,Mouxiao Bian,Rui Wang,Hong Ge,Dandan Yao,Ziying Sun,Yuan Zhao,Yu Zhang,Hui Shi,Dongdong Wang,Chenxin Song,Shenghong Ju,Lihao Liu,Junjun He,Jie Xu,Yuan-Cheng Wang
机构: Department of Radiology, Zhongda Hospital (放射科，中大医院); Nurturing Center of Jiangsu Province for State Laboratory of AI Imaging & Interventional Radiology (江苏省人工智能影像与介入放射重点实验室培育中心); School of Medicine, Southeast University (东南大学医学院); Shanghai Artificial Intelligence Laboratory (上海人工智能实验室); The Fifth Clinical Medical College of Henan University of Chinese Medicine (河南中医药大学第五临床医学院); (Zhengzhou People’s Hospital) (郑州市人民医院)
类目: Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[NLP-43] oward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning

链接: https://arxiv.org/abs/2503.07018
作者: Xintong Li,Jalend Bantupalli,Ria Dharmani,Yuwei Zhang,Jingbo Shang
机构: University of California, San Diego (加州大学圣地亚哥分校)
类目: Computation and Language (cs.CL)
备注: Preprint

点击查看摘要

[NLP-44] ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation

链接: https://arxiv.org/abs/2503.07010
作者: Kaiyuan Liu,Youcheng Pan,Jing Li,Daojing He,Yang Xiang,Yexing Du,Tianrun Gao
机构: Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学（深圳）); Pengcheng Laboratory (鹏城实验室); Harbin Institute of Technology (哈尔滨工业大学)
类目: oftware Engineering (cs.SE); Computation and Language (cs.CL)
备注: 17 pages (9 Appendix pages), 4 figures, 7 tables

点击查看摘要

[NLP-45] Large Language Models Often Say One Thing and Do Another ICLR2025

链接: https://arxiv.org/abs/2503.07003
作者: Ruoxi Xu,Hongyu Lin,Xianpei Han,Jia Zheng,Weixiang Zhou,Le Sun,Yingfei Sun
机构: University of Chinese Academy of Sciences (中国科学院大学); Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences (中国科学院软件研究所中文信息处理实验室); State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences (中国科学院软件研究所计算机科学国家重点实验室)
类目: Computation and Language (cs.CL)
备注: Published on ICLR 2025

点击查看摘要

[NLP-46] Social Bias Benchmark for Generation: A Comparison of Generation and QA-Based Evaluations

链接: https://arxiv.org/abs/2503.06987
作者: Jiho Jin,Woosung Kang,Junho Myung,Alice Oh
机构: KAIST (高丽科技大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-47] Exploring Multimodal Perception in Large Language Models Through Perceptual Strength Ratings

链接: https://arxiv.org/abs/2503.06980
作者: Jonghyun Lee,Dojun Park,Jiwoo Lee,Hoekeon Choi,Sung-Eun Lee
机构: 未知
类目: Computation and Language (cs.CL)
备注: under review, 15 pages

点击查看摘要

[NLP-48] CtrlRAG : Black-box Adversarial Attacks Based on Masked Language Models in Retrieval-Augmented Language Generation

链接: https://arxiv.org/abs/2503.06950
作者: Runqi Sui
机构: Beijing University of Posts and Telecommunications (北京邮电大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-49] Lshan-1.0 Technical Report

链接: https://arxiv.org/abs/2503.06949
作者: Haotian Chen,Yanyu Xu,Boyan Wang,Chaoyue Zhao,Xiaoyu Han,Fang Wang,Lizhen Cui,Yonghui Xu
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-50] Effect of Selection Format on LLM Performance

链接: https://arxiv.org/abs/2503.06926
作者: Yuchen Han,Yucheng Wu,Jeffrey Willard
机构: Washington University in St. Louis (圣路易斯华盛顿大学); Nanjing University of Posts and Telecommunications (南京邮电大学); Boston University (波士顿大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Emerging Technologies (cs.ET); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-51] Automatic Speech Recognition for Non-Native English: Accuracy and Disfluency Handling

链接: https://arxiv.org/abs/2503.06924
作者: Michael McGuire
机构: 未知
类目: Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)
备注: 33 pages, 10 figures

点击查看摘要

[NLP-52] KwaiChat: A Large-Scale Video-Driven Multilingual Mixed-Type Dialogue Corpus

链接: https://arxiv.org/abs/2503.06899
作者: Xiaoming Shi,Zeming Liu,Yiming Lei,Chenkai Zhang,Haitao Leng,Chuan Wang,Qingjie Liu,Wanxiang Che,Shaoguo Liu,Size Li,Yunhong Wang
机构: East China Normal University (华东师范大学), Shanghai, China; Beihang University (北京航空航天大学), Beijing, China; KuaiShou Inc. (快手公司), Hangzhou, China; Beijing JiaoTong University (北京交通大学), Beijing, China; Research Center for Social Computing and Information Retrieval, HIT (哈尔滨工业大学社会计算与信息检索研究中心), Harbin, China
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-53] A LongFormer-Based Framework for Accurate and Efficient Medical Text Summarization

链接: https://arxiv.org/abs/2503.06888
作者: Dan Sun,Jacky He,Hanlu Zhang,Zhen Qi,Hongye Zheng,Xiaokai Wang
机构: 未知
类目: Computation and Language (cs.CL)
备注: Paper accepted by 2025 8th International Conference on Advanced Algorithms and Control Engineering (ICAACE 2025)

点击查看摘要

[NLP-54] Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset Evaluation Framework and Mitigation

链接: https://arxiv.org/abs/2503.06868
作者: Junhao Zhang,Richong Zhang,Fanshuang Kong,Ziyang Miao,Yanhan Ye,Yaowei Zheng
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-55] Enhanced Multi-Tuple Extraction for Alloys: Integrating Pointer Networks and Augmented Attention

链接: https://arxiv.org/abs/2503.06861
作者: Mengzhe Hei,Zhouran Zhang,Qingbao Liu,Yan Pan,Xiang Zhao,Yongqian Peng,Yicong Ye,Xin Zhang,Shuxin Bai
机构: Nudt(国防科技大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 17 pages, 5 figures

点击查看摘要

[NLP-56] Silent Hazards of Token Reduction in Vision-Language Models: The Hidden Impact on Consistency

链接: https://arxiv.org/abs/2503.06794
作者: Yizheng Sun,Hao Li,Chang Xu,Chenghua Lin,Riza Batista-Navarro,Jingyuan Sun
机构: University of Manchester (曼彻斯特大学); Microsoft Research (微软研究)
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-57] On the Mutual Influence of Gender and Occupation in LLM Representations

链接: https://arxiv.org/abs/2503.06792
作者: Haozhe An,Connor Baumler,Abhilasha Sancheti,Rachel Rudinger
机构: University of Maryland, College Park (马里兰大学帕克分校)
类目: Computation and Language (cs.CL)
备注: In submission

点击查看摘要

[NLP-58] Dr Genre: Reinforcement Learning from Decoupled LLM Feedback for Generic Text Rewriting

链接: https://arxiv.org/abs/2503.06781
作者: Yufei Li,John Nham,Ganesh Jawahar,Lei Shu,David Uthus,Yun-Hsuan Sung,Chengrun Yang,Itai Rolnick,Yi Qiao,Cong Liu
机构: UC Riverside (UC Riverside); Google DeepMind (Google DeepMind); Google Cloud (Google Cloud)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 29 pages, 4 figures, 25 tables

点击查看摘要

[NLP-59] Large Language Models Are Effective Human Annotation Assistants But Not Good Independent Annotators

链接: https://arxiv.org/abs/2503.06778
作者: Feng Gu,Zongxia Li,Carlos Rafael Colon,Benjamin Evans,Ishani Mondal,Jordan Lee Boyd-Graber
机构: University of Maryland, College Park (马里兰大学帕克分校)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 9 pages, 4 figures

点击查看摘要

[NLP-60] Effectiveness of Zero-shot-CoT in Japanese Prompts

链接: https://arxiv.org/abs/2503.06765
作者: Shusuke Takayama,Ian Frank
机构: Future University Hakodate (未来大学函馆)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: NLP2025 Workshop on Japanese Language Resources (JLR2025)

点击查看摘要

[NLP-61] Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

链接: https://arxiv.org/abs/2503.06749
作者: Wenxuan Huang,Bohan Jia,Zijie Zhai,Shaosheng Cao,Zheyu Ye,Fei Zhao,Yao Hu,Shaohui Lin
机构: East China Normal University (华东师范大学); Xiaohongshu Inc. (小红书科技)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-62] Gender Encoding Patterns in Pretrained Language Model Representations

链接: https://arxiv.org/abs/2503.06734
作者: Mahdi Zakizadeh,Mohammad Taher Pilehvar
机构: TeIAS (泰伊阿斯); Khatam University (卡汗姆大学), Iran; Cardiff University (卡迪夫大学), UK
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Proceedings of the 5th Workshop on Trustworthy Natural Language Processing (TrustNLP 2025)

点击查看摘要

[NLP-63] opology of Syntax Networks across Languages

链接: https://arxiv.org/abs/2503.06724
作者: Juan Soria-Postigo,Luis F Seoane
机构: 未知
类目: Computation and Language (cs.CL)
备注: Final Thesis for MSc in Computational and Applied Mathematics at UC3M

点击查看摘要

[NLP-64] Delusions of Large Language Models

链接: https://arxiv.org/abs/2503.06709
作者: Hongshen Xu,Zixv yang,Zichen Zhu,Kunyao Lan,Zihan Wang,Mengyue Wu,Ziwei Ji,Lu Chen,Pascale Fung,Kai Yu
机构: X-LANCE Lab, Department of Computer Science and Engineering (计算机科学与工程系 X-LANCE 实验室), MoE Key Lab of Artificial Intelligence (教育部人工智能重点实验室), AI Institute (人工智能研究院), Shanghai Jiao Tong University (上海交通大学, 上海, 中国); Center for Artificial Intelligence Research (CAiRE) (人工智能研究中心), Hong Kong University of Science and Technology
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-65] Alignment for Efficient Tool Calling of Large Language Models

链接: https://arxiv.org/abs/2503.06708
作者: Hongshen Xu,Zihan Wang,Zichen Zhu,Lei Pan,Xingyu Chen,Lu Chen,Kai Yu
机构: X-LANCE Lab, Department of Computer Science and Engineering (计算机科学与工程系), MoE Key Lab of Artificial Intelligence (教育部人工智能重点实验室), AI Institute (人工智能研究院), Shanghai Jiao Tong University (上海交通大学); AISpeech Co., Ltd. (思必驰科技股份有限公司)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-66] PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts

链接: https://arxiv.org/abs/2503.06706
作者: Ming Zhang,Yuhui Wang,Yujiong Shen,Tingyi Yang,Changhao Jiang,Yilong Wu,Shihan Dou,Qinhao Chen,Zhiheng Xi,Zhihao Zhang,Yi Dong,Zhen Wang,Zhihui Fei,Mingyang Wan,Tao Liang,Guojun Ma,Qi Zhang,Tao Gui,Xuanjing Huang
机构: School of Computer Science, Fudan University (复旦大学计算机学院); Douyin Co., Ltd. (抖音有限公司); Institute of Modern Languages and Linguistics, Fudan University (复旦大学现代语言与语言学研究所); Graduate School of Arts and Sciences, Columbia University (哥伦比亚大学艺术与科学研究生院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-67] InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models

链接: https://arxiv.org/abs/2503.06692
作者: Yuchen Yan,Yongliang Shen,Yang Liu,Jin Jiang,Mengdi Zhang,Jian Shao,Yueting Zhuang
机构: Zhejiang University (浙江大学); Meituan Group (美团集团); Peking University (北京大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-68] DependEval: Benchmarking LLM s for Repository Dependency Understanding

链接: https://arxiv.org/abs/2503.06689
作者: Junjia Du,Yadi Liu,Hongcheng Guo,Jiawei Wang,Haojian Huang,Yunyi Ni,Zhoujun Li
机构: 未知
类目: oftware Engineering (cs.SE); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-69] Attention Please! PixelSHAP Reveals What Vision-Language Models Actually Focus On

链接: https://arxiv.org/abs/2503.06670
作者: Roni Goldshmidt
机构: Nexar (内克斯尔)
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-70] Enhancing NLP Robustness and Generalization through LLM -Generated Contrast Sets: A Scalable Framework for Systematic Evaluation and Adversarial Training

链接: https://arxiv.org/abs/2503.06648
作者: Hender Lin
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-71] Is Your Benchmark (Still) Useful? Dynamic Benchmarking for Code Language Models

链接: https://arxiv.org/abs/2503.06643
作者: Batu Guan,Xiao Wu,Yuanyuan Yuan,Shaohua Li
机构: 未知
类目: oftware Engineering (cs.SE); Computation and Language (cs.CL)
备注: 14 pages, 7 figures

点击查看摘要

[NLP-72] Revisiting Early Detection of Sexual Predators via Turn-level Optimization NAACL2025

链接: https://arxiv.org/abs/2503.06627
作者: Jinmyeong An,Sangwon Ryu,Heejin Do,Yunsu Kim,Jungseul Ok,Gary Geunbae Lee
机构: Graduate School of Artificial Intelligence, POSTECH (POSTECH 人工智能研究生院); Department of Computer Science and Engineering, POSTECH (POSTECH 计算机科学与工程系); aiXplain Inc. (aiXplain Inc.)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Accepted as a main conference paper at NAACL 2025

点击查看摘要

[NLP-73] Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation

链接: https://arxiv.org/abs/2503.06594
作者: Yingfeng Luo,Tong Zheng,Yongyu Mu,Bei Li,Qinghong Zhang,Yongqi Gao,Ziqiang Xu,Peinan Feng,Xiaoqian Liu,Tong Xiao,Jingbo Zhu
机构: NLP Lab, Northeastern University (东北大学), Shenyang, China; NiuTrans Research (纽昂思研究), Shenyang, China
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-74] WildIFEval: Instruction Following in the Wild

链接: https://arxiv.org/abs/2503.06573
作者: Gili Lior,Asaf Yehudai,Ariel Gera,Liat Ein-Dor
机构: The Hebrew University of Jerusalem (希伯来大学耶路撒冷); IBM Research (IBM研究院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-75] Multimodal Programming in Computer Science with Interactive Assistance Powered by Large Language Model

链接: https://arxiv.org/abs/2503.06552
作者: Rajan Das Gupta,Md. Tanzib Hosain,M. F. Mridha,Salah Uddin Ahmed
机构: 未知
类目: Human-Computer Interaction (cs.HC); Computation and Language (cs.CL)
备注: Accepted in Proceedings of the 27th International Conference on. Human-Computer Interaction, 2025

点击查看摘要

[NLP-76] BingoGuard: LLM Content Moderation Tools with Risk Levels ICLR2025

链接: https://arxiv.org/abs/2503.06550
作者: Fan Yin,Philippe Laban,Xiangyu Peng,Yilun Zhou,Yixin Mao,Vaibhav Vats,Linnea Ross,Divyansh Agarwal,Caiming Xiong,Chien-Sheng Wu
机构: 未知
类目: Computation and Language (cs.CL)
备注: 10 pages, 4 figures, 4 tables. ICLR 2025 poster

点击查看摘要

[NLP-77] KréyoLID From Language Identification Towards Language Mining

链接: https://arxiv.org/abs/2503.06547
作者: Rasul Dent,Pedro Ortiz Suarez,Thibault Clérice,Benoît Sagot
机构: Inria(法国国家信息与自动化研究所); Common Crawl Foundation(公共爬虫基金会)
类目: Computation and Language (cs.CL)
备注: 8 main pages

点击查看摘要

[NLP-78] SafeSpeech: A Comprehensive and Interactive Tool for Analysing Sexist and Abusive Language in Conversations NAACL2025

链接: https://arxiv.org/abs/2503.06534
作者: Xingwei Tan,Chen Lyu,Hafiz Muhammad Umer,Sahrish Khan,Mahathi Parvatham,Lois Arthurs,Simon Cullen,Shelley Wilson,Arshad Jhumka,Gabriele Pergola
机构: Department of Computer Science, University of Warwick (华威大学), UK; School of Computer Science, University of Sheffield (谢菲尔德大学), UK; School of Computer Science, University of Leeds (利兹大学), UK; Forensic Capability Network (法医能力网络), UK
类目: Computation and Language (cs.CL)
备注: NAACL 2025 system demonstration camera-ready

点击查看摘要

[NLP-79] MetaXCR: Reinforcement-Based Meta-Transfer Learning for Cross-Lingual Commonsense Reasoning

链接: https://arxiv.org/abs/2503.06531
作者: Jie He,Yu Fu
机构: School of Informatics (信息学院), University of Edinburgh (爱丁堡大学); College of Intelligence and Computing (智能与计算学院), Tianjin University (天津大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-80] GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks

链接: https://arxiv.org/abs/2503.06514
作者: Haoqiang Kang,Enna Sachdeva,Piyush Gupta,Sangjae Bae,Kwonjoon Lee
机构: Honda Research Institute (本田研究院), USA; University of California, San Diego (加州大学圣地亚哥分校)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-81] Less is More: Adaptive Program Repair with Bug Localization and Preference Learning AAAI2025

链接: https://arxiv.org/abs/2503.06510
作者: Zhenlong Dai,Bingrui Chen,Zhuoluo Zhao,Xiu Tang,Sai Wu,Chang Yao,Zhipeng Gao,Jingyuan Chen
机构: Zhejiang University (浙江大学); Hohai University (河海大学); Guizhou University (贵州大学)
类目: oftware Engineering (cs.SE); Computation and Language (cs.CL)
备注: accepted by AAAI2025 Oral

点击查看摘要

[NLP-82] VisualSimpleQA: A Benchmark for Decoupled Evaluation of Large Vision-Language Models in Fact-Seeking Question Answering

链接: https://arxiv.org/abs/2503.06492
作者: Yanling Wang,Yihan Zhao,Xiaodong Chen,Shasha Guo,Lixin Liu,Haoyang Li,Yong Xiao,Jing Zhang,Qi Li,Ke Xu
机构: Zhongguancun Laboratory (中关村实验室); Renmin University of China (中国人民大学); Tencent (腾讯); Tsinghua University (清华大学)
类目: Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[NLP-83] MoFE: Mixture of Frozen Experts Architecture NAACL2025

链接: https://arxiv.org/abs/2503.06491
作者: Jean Seo,Jaeyoon Kim,Hyopil Shin
机构: Seoul National University (首尔国立大学)
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: NAACL 2025 Industry

点击查看摘要

[NLP-84] SKG-LLM : Developing a Mathematical Model for Stroke Knowledge Graph Construction Using Large Language Models

链接: https://arxiv.org/abs/2503.06475
作者: Ali Sarabadani,Kheirolah Rahsepar Fard,Hamid Dalvand
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-85] HuixiangDou2: A Robustly Optimized GraphRAG Approach

链接: https://arxiv.org/abs/2503.06474
作者: Huanjun Kong,Zhefan Wang,Chenyang Wang,Zhe Ma,Nanqing Dong
机构: Shanghai Artificial Intelligence Laboratory (上海人工智能实验室)
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 11 pages

点击查看摘要

[NLP-86] hink Twice Click Once: Enhancing GUI Grounding via Fast and Slow Systems

链接: https://arxiv.org/abs/2503.06470
作者: Fei Tang,Yongliang Shen,Hang Zhang,Siqi Chen,Guiyang Hou,Wenqi Zhang,Wenqiao Zhang,Kaitao Song,Weiming Lu,Yueting Zhuang
机构: Zhejiang University (浙江大学); Microsoft Research Asia (微软亚洲研究院)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[NLP-87] Graph Retrieval-Augmented LLM for Conversational Recommendation Systems PAKDD2025

链接: https://arxiv.org/abs/2503.06430
作者: Zhangchi Qiu,Linhao Luo,Zicheng Zhao,Shirui Pan,Alan Wee-Chung Liew
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
备注: Accepted by PAKDD 2025

点击查看摘要

[NLP-88] raining LLM -based Tutors to Improve Student Learning Outcomes in Dialogues

链接: https://arxiv.org/abs/2503.06424
作者: Alexander Scarlatos,Naiming Liu,Jaewook Lee,Richard Baraniuk,Andrew Lan
机构: University of Massachusetts Amherst (马萨诸塞大学阿默斯特分校); Rice University (莱斯大学)
类目: Computation and Language (cs.CL); Computers and Society (cs.CY)
备注:

点击查看摘要

[NLP-89] How LLM s Learn: Tracing Internal Representations with Sparse Autoencoders

链接: https://arxiv.org/abs/2503.06394
作者: Tatsuro Inaba,Kentaro Inui,Yusuke Miyao,Yohei Oseki,Benjamin Heinzerling,Yu Takagi
机构: National Institute of Informatics (国立情报学研究所); Kyoto University (京都大学); MBZUAI (Mohammed bin Zayed University of Artificial Intelligence); Tohoku University (东北大学); RIKEN (理化学研究所); University of Tokyo (东京大学)
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: Our code, demo, SAE weights are available at: this https URL

点击查看摘要

[NLP-90] I-JEPA: An Innovative Energy-based Joint Embedding Strategy for Text-Image Multimodal Systems

链接: https://arxiv.org/abs/2503.06380
作者: Khang H. N. Vo,Duc P. T. Nguyen,Thong Nguyen,Tho T. Quan
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-91] General Scales Unlock AI Evaluation with Explanatory and Predictive Power

链接: https://arxiv.org/abs/2503.06378
作者: Lexin Zhou,Lorenzo Pacchiardi,Fernando Martínez-Plumed,Katherine M. Collins,Yael Moros-Daval,Seraphina Zhang,Qinlin Zhao,Yitian Huang,Luning Sun,Jonathan E. Prunty,Zongqian Li,Pablo Sánchez-García,Kexin Jiang Chen,Pablo A. M. Casares,Jiyun Zu,John Burden,Behzad Mehrbakhsh,David Stillwell,Manuel Cebrian,Jindong Wang,Peter Henderson,Sherry Tongshuang Wu,Patrick C. Kyllonen,Lucy Cheke,Xing Xie,José Hernández-Orallo
机构: University of Cambridge(剑桥大学); Imperial College London(帝国理工学院); Universidad Politécnica de Madrid(马德里理工大学); Boston University(波士顿大学); Peking University(北京大学); Shanghai Jiao Tong University(上海交通大学); University of New South Wales(新南威尔士大学); Universitat Politècnica de València(瓦伦西亚理工大学); Tsinghua University(清华大学); National University of Defense Technology(国防科技大学); Harvard University(哈佛大学); University of Oxford(牛津大学)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computers and Society (cs.CY)
备注:

点击查看摘要

[NLP-92] Phraselette: A Poets Procedural Palette

链接: https://arxiv.org/abs/2503.06335
作者: Alex Calderwood,John Joon Young Chung,Yuqian Sun,Melissa Roemmele,Max Kreminski
机构: University of California, Santa Cruz (加州大学圣克鲁兹分校); Midjourney; Midjourney; Midjourney; Midjourney
类目: Human-Computer Interaction (cs.HC); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-93] States of LLM -generated Texts and Phase Transitions between them

链接: https://arxiv.org/abs/2503.06330
作者: Nikolay Mikhaylovskiy
机构: NTR Labs (NTR 实验室), Moscow, Russia; Higher IT School (高等信息技术学院), Tomsk State University (托木斯克国立大学), Tomsk, Russia
类目: Computation and Language (cs.CL); Statistical Mechanics (cond-mat.stat-mech); Artificial Intelligence (cs.AI)
备注: Published as a conference paper at MathAI 2025

点击查看摘要

[NLP-94] Advancing Autonomous Vehicle Intelligence: Deep Learning and Multimodal LLM for Traffic Sign Recognition and Robust Lane Detection

链接: https://arxiv.org/abs/2503.06313
作者: Chandan Kumar Sah,Ankit Kumar Shaw,Xiaoli Lian,Arsalan Shahid Baig,Tuopu Wen,Kun Jiang,Mengmeng Yang,Diange Yang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Robotics (cs.RO)
备注: 11 pages, 9 figures

点击查看摘要

[NLP-95] MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal Answering NAACL

链接: https://arxiv.org/abs/2503.06296
作者: Vinay Kumar Verma,Shreyas Sunil Kulkarni,Happy Mittal,Deepak Gupta
机构: Private Brands - Discovery, Amazon (亚马逊); International Machine Learning, Amazon (亚马逊); CMT Systems, Amazon (亚马逊)
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: To appear at NAACL Industry Track

点击查看摘要

[NLP-96] IteRABRe: Iterative Recovery-Aided Block Reduction

链接: https://arxiv.org/abs/2503.06291
作者: Haryo Akbarianto Wibowo,Haiyue Song,Hideki Tanaka,Masao Utiyama,Alham Fikri Aji,Raj Dabre
机构: NICT; MBZUAI
类目: Computation and Language (cs.CL)
备注: 8 pages

点击查看摘要

[NLP-97] Critical Foreign Policy Decisions (CFPD)-Benchmark: Measuring Diplomatic Preferences in Large Language Models

链接: https://arxiv.org/abs/2503.06263
作者: Benjamin Jensen,Ian Reynolds,Yasir Atalan,Michael Garcia,Austin Woo,Anthony Chen,Trevor Howarth
机构: Center for Strategic and International Studies; Scale AI
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-98] A Noise-Robust Turn-Taking System for Real-World Dialogue Robots: A Field Experiment

链接: https://arxiv.org/abs/2503.06241
作者: Koji Inoue,Yuki Okafuji,Jun Baba,Yoshiki Ohira,Katsuya Hyodo,Tatsuya Kawahara
机构: Graduate School of Informatics, Kyoto University (京都大学信息学研究科); CyberAgent (赛博代理); Osaka University (大阪大学)
类目: Robotics (cs.RO); Computation and Language (cs.CL); Sound (cs.SD)
备注:

点击查看摘要

[NLP-99] Integrating Chain-of-Thought for Multimodal Alignment: A Study on 3D Vision-Language Learning

链接: https://arxiv.org/abs/2503.06232
作者: Yanjun Chen,Yirong Sun,Xinghao Chen,Jian Wang,Xiaoyu Shen,Wenjie Li,Wei Zhang
机构: Department of Computing, The Hong Kong Polytechnic University (香港理工大学计算机系), Hong Kong, China; Digital Twin Institute, Eastern Institute of Technology (东方理工数字孪生研究所), Ningbo, China
类目: Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[NLP-100] KnowLogic: A Benchmark for Commonsense Reasoning via Knowledge-Driven Data Synthesis

链接: https://arxiv.org/abs/2503.06218
作者: Weidong Zhan,Yue Wang,Nan Hu,Liming Xiao,Jingyuan Ma,Yuhang Qin,Zheng Li,Yixin Yang,Sirui Deng,Jinkun Ding,Wenhan Ma,Rui Li,Weilin Luo,Qun Liu,Zhifang Sui
机构: Center for Chinese Linguistics, Department of Chinese Language and Literature, Peking University (北京大学中国语言文学系中国语言学研究中心); School of Computer Science, State Key Laboratory of Multimedia Information Processing, Peking University (北京大学计算机科学学院多媒体信息处理国家重点实验室); Huawei Noah’s Ark Lab (华为诺亚方舟实验室), China
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-101] xt-Speech Language Models with Improved Cross-Modal Transfer by Aligning Abstraction Levels

链接: https://arxiv.org/abs/2503.06211
作者: Santiago Cuervo,Adel Moumen,Yanis Labrak,Sameer Khurana,Antoine Laurent,Mickael Rouvier,Ricard Marxer
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS)
备注:

点击查看摘要

[NLP-102] CUPCase: Clinically Uncommon Patient Cases and Diagnoses Dataset AAAI2025

链接: https://arxiv.org/abs/2503.06204
作者: Oriel Perets,Ofir Ben Shoham,Nir Grinberg,Nadav Rappoport
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Accepted to AAAI 2025

点击查看摘要

[NLP-103] Explainable Synthetic Image Detection through Diffusion Timestep Ensembling

链接: https://arxiv.org/abs/2503.06201
作者: Yixin Wu,Feiran Zhang,Tianyuan Shi,Ruicheng Yin,Zhenghua Wang,Zhenliang Gan,Xiaohua Wang,Changze Lv,Xiaoqing Zheng,Xuanjing Huang
机构: School of Computer Science, Fudan University (复旦大学计算机科学学院), Shanghai, China; Shanghai Key Laboratory of Intelligent Information Processing (上海市智能信息处理重点实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 13 pages, 5 figures

点击查看摘要

[NLP-104] Sample-aware Adaptive Structured Pruning for Large Language Models

链接: https://arxiv.org/abs/2503.06184
作者: Jun Kong,Xinge Ma,Jin Wang,Xuejie Zhang
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-105] GRP: Goal-Reversed Prompting for Zero-Shot Evaluation with LLM s

链接: https://arxiv.org/abs/2503.06139
作者: Mingyang Song,Mao Zheng,Xuan Luo
机构: Machine Learning Platform Department, Tencent (腾讯机器学习平台部)
类目: Computation and Language (cs.CL)
备注: Ongoing Work

点击查看摘要

[NLP-106] Evaluating Discourse Cohesion in Pre-trained Language Models

链接: https://arxiv.org/abs/2503.06137
作者: Jie He,Wanqiu Long,Deyi Xiong
机构: University of Edinburgh (爱丁堡大学), UK; College of Intelligence and Computing, Tianjin University (天津大学智能与计算学部), China
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-107] AF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learning

链接: https://arxiv.org/abs/2503.06112
作者: Hoang-Thang Ta,Anh Tran
机构: Dalat University (Dalat大学); FPT University (FPT大学)
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注: 25 pages

点击查看摘要

[NLP-108] heta Theory: operads and coloring

链接: https://arxiv.org/abs/2503.06091
作者: Matilde Marcolli,Richard K. Larson
机构: 未知
类目: Computation and Language (cs.CL)
备注: 26 pages LaTeX

点击查看摘要

[NLP-109] Multi-Attribute Multi-Grained Adaptation of Pre-Trained Language Models for Text Understanding from Bayesian Perspective AAAI2025

链接: https://arxiv.org/abs/2503.06085
作者: You Zhang,Jin Wang,Liang-Chih Yu,Dan Xu,Xuejie Zhang
机构: 未知
类目: Computation and Language (cs.CL)
备注: Extended version accepted by AAAI 2025

点击查看摘要

[NLP-110] An Empirical Study of Causal Relation Extraction Transfer: Design and Data

链接: https://arxiv.org/abs/2503.06076
作者: Sydney Anuyah,Jack Vanschaik,Palak Jain,Sawyer Lehman,Sunandan Chakraborty
机构: Indiana University (印第安纳大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-111] owards Conversational AI for Disease Management

链接: https://arxiv.org/abs/2503.06074
作者: Anil Palepu,Valentin Liévin,Wei-Hung Weng,Khaled Saab,David Stutz,Yong Cheng,Kavita Kulkarni,S. Sara Mahdavi,Joëlle Barral,Dale R. Webster,Katherine Chou,Avinatan Hassidim,Yossi Matias,James Manyika,Ryutaro Tanno,Vivek Natarajan,Adam Rodman,Tao Tu,Alan Karthikesalingam,Mike Schaekermann
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 62 pages, 7 figures in main text, 36 figures in appendix

点击查看摘要

[NLP-112] GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images

链接: https://arxiv.org/abs/2503.06073
作者: Xiang Lan,Feng Wu,Kai He,Qinghao Zhao,Shenda Hong,Mengling Feng
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[NLP-113] A Survey on Post-training of Large Language Models

链接: https://arxiv.org/abs/2503.06072
作者: Guiyao Tie,Zeli Zhao,Dingjie Song,Fuyang Wei,Rong Zhou,Yurou Dai,Wen Yin,Zhejian Yang,Jiangyue Yan,Yao Su,Zhenhan Dai,Yifeng Xie,Yihan Cao,Lichao Sun,Pan Zhou,Lifang He,Hechang Chen,Yu Zhang,Qingsong Wen,Tianming Liu,Neil Zhenqiang Gong,Jiliang Tang,Caiming Xiong,Heng Ji,Philip S. Yu,Jianfeng Gao
机构: Huazhong University of Science and Technology (华中科技大学); Lehigh University (里海大学); The University of Hong Kong (香港大学); Jilin University (吉林大学); Southern University of Science and Technology (南方科技大学); Worcester Polytechnic Institute (伍斯特理工学院); LinkedIn Corporation (领英公司); Squirrel Ai Learning (松鼠Ai学习); University of Georgia (佐治亚大学); Duke University (杜克大学); Michigan State University (密歇根州立大学); Salesforce Research (Salesforce研究); University of Illinois Urbana-Champaign (伊利诺伊大学厄巴纳-香槟分校); University of Illinois at Chicago (芝加哥大学伊利诺伊分校); Microsoft Research (微软研究)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 87 pages, 21 figures, 9 tables

点击查看摘要

[NLP-114] A Novel Trustworthy Video Summarization Algorithm Through a Mixture of LoRA Experts

链接: https://arxiv.org/abs/2503.06064
作者: Wenzhuo Du,Gerun Wang,Guancheng Chen,Hang Zhao,Xin Li,Jian Gao
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-115] Fine-Grained Bias Detection in LLM : Enhancing detection mechanisms for nuanced biases

链接: https://arxiv.org/abs/2503.06054
作者: Suvendu Mohanty
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Bias detection, Large Language Models, nuanced biases, fine-grained mechanisms, model transparency, ethical AI

点击查看摘要

[NLP-116] Constructions are Revealed in Word Distributions

链接: https://arxiv.org/abs/2503.06048
作者: Joshua Rozner,Leonie Weissweiler,Kyle Mahowald,Cory Shain
机构: Stanford University (斯坦福大学); The University of Texas at Austin (德克萨斯大学奥斯汀分校); Stanford University (斯坦福大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-117] DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM -based Agents in Complex Decision-Making Environments

链接: https://arxiv.org/abs/2503.06047
作者: Wenjie Tang,Yuan Zhou,Erqiang Xu,Keyan Cheng,Minne Li,Liquan Xiao
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 43 pages, 5 figures, conference

点击查看摘要

[NLP-118] Mitigating Memorization in LLM s using Activation Steering

链接: https://arxiv.org/abs/2503.06040
作者: Manan Suri,Nishit Anand,Amisha Bhaskar
机构: University of Maryland, College Park (马里兰大学帕克分校)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-119] Rank-R1: Enhancing Reasoning in LLM -based Document Rerankers via Reinforcement Learning

链接: https://arxiv.org/abs/2503.06034
作者: Shengyao Zhuang,Xueguang Ma,Bevan Koopman,Jimmy Lin,Guido Zuccon
机构: CSIRO; University of Waterloo; The University of Queensland
类目: Information Retrieval (cs.IR); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-120] SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?

链接: https://arxiv.org/abs/2503.06029
作者: Xudong Lu,Haohao Gao,Renshou Wu,Shuai Ren,Xiaoxin Chen,Hongsheng Li,Fangyuan Li
机构: vivo AI Lab (vivo AI 实验室); CUHK MMLab (香港中文大学多媒体实验室)
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: 23 pages

点击查看摘要

[NLP-121] GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices

链接: https://arxiv.org/abs/2503.06019
作者: Xudong Lu,Yinghao Chen,Renshou Wu,Haohao Gao,Xi Chen,Xue Yang,Xiangyu Zhao,Aojun Zhou,Fangyuan Li,Yafei Wen,Xiaoxin Chen,Shuai Ren,Hongsheng Li
机构: vivo AI Lab (维沃移动通信(东莞)有限公司人工智能实验室); CUHK MMLab (香港中文大学多媒体实验室); Shanghai Jiao Tong University (上海交通大学)
类目: Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
备注: 14 pages

点击查看摘要

[NLP-122] Intent-Aware Self-Correction for Mitigating Social Biases in Large Language Models

链接: https://arxiv.org/abs/2503.06011
作者: Panatchakorn Anantaprayoon,Masahiro Kaneko,Naoaki Okazaki
机构: Institute of Science Tokyo(科学研究所东京); MBZUAI(穆罕默德·本·扎耶德人工智能大学); AIST(国家高级工业科学技术研究院); NII LLMC(国立信息学研究所大型语言模型中心)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 18 pages. Under review

点击查看摘要

[NLP-123] Psycholinguistic Analyses in Software Engineering Text: A Systematic Literature Review

链接: https://arxiv.org/abs/2503.05992
作者: Amirali Sajadi,Kostadin Damevski,Preetha Chatterjee
机构: Drexel University (德雷塞尔大学); Virginia Commonwealth University (弗吉尼亚联邦大学)
类目: oftware Engineering (cs.SE); Computation and Language (cs.CL); Computers and Society (cs.CY)
备注:

点击查看摘要

[NLP-124] SINdex: Semantic INconsistency Index for Hallucination Detection in LLM s

链接: https://arxiv.org/abs/2503.05980
作者: Samir Abdaljalil,Hasan Kurban,Parichit Sharma,Erchin Serpedin,Rachad Atat
机构: Electrical and Computer Engineering, Texas A&M University (德州农工大学), College Station, TX USA;
College of Science and Engineering, Hamad Bin Khalifa University (哈马德本哈利法大学), Doha, Qatar;
Department of Computer Science, Luddy School of Informatics, Bloomington, Indiana, USA;
Department of Computer Science and Mathematics, Lebanese American University, Beirut, Lebanon
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-125] SANDWiCH: Semantical Analysis of Neighbours for Disambiguating Words in Context ad Hoc NAACL2025

链接: https://arxiv.org/abs/2503.05958
作者: Daniel Guzman-Olivares,Lara Quijano-Sanchez,Federico Liberatore
机构: Bulil Technologies; Autonomous University of Madrid (马德里自治大学); Cardiff University (卡迪夫大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 15 pages, 2 figures, 7 tables, NAACL 2025

点击查看摘要

[NLP-126] DETQUS: Decomposition-Enhanced Transformers for QUery-focused Summarization NAACL2025

链接: https://arxiv.org/abs/2503.05935
作者: Yasir Khan,Xinlei Wu,Sangpil Youm,Justin Ho,Aryaan Shaikh,Jairo Garciga,Rohan Sharma,Bonnie J. Dorr
机构: University of Florida, Gainesville, Florida (佛罗里达大学, 盎格尔伍德, 佛罗里达)
类目: Computation and Language (cs.CL)
备注: 12 pages, 2 figures, Accepted to NAACL 2025 main conference

点击查看摘要

[NLP-127] raining and Inference Efficiency of Encoder-Decoder Speech Models

链接: https://arxiv.org/abs/2503.05931
作者: Piotr Żelasko,Kunal Dhawan,Daniel Galvez,Krishna C. Puvvada,Ankita Pasad,Nithin Rao Koluguri,Ke Hu,Vitaly Lavrukhin,Jagadeesh Balam,Boris Ginsburg
机构: NVIDIA (英伟达), USA
类目: Computation and Language (cs.CL); Audio and Speech Processing (eess.AS)
备注:

点击查看摘要

[NLP-128] IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining

链接: https://arxiv.org/abs/2503.05920
作者: Yixiao Li,Xianzhi Du,Ajay Jaiswal,Tao Lei,Tuo Zhao,Chong Wang,Jianyu Wang
机构: Apple (苹果)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-129] From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning

链接: https://arxiv.org/abs/2503.05919
作者: Eric Zhao,Pranjal Awasthi,Nika Haghtalab
机构: 未知
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-130] MastermindEval: A Simple But Scalable Reasoning Benchmark

链接: https://arxiv.org/abs/2503.05891
作者: Jonas Golde,Patrick Haller,Fabio Barth,Alan Akbik
机构: Humboldt-Universität zu Berlin (柏林洪堡大学); DFKI Berlin (德国人工智能研究中心)
类目: Computation and Language (cs.CL)
备注: 9 pages, 2 figures, 4 tables

点击查看摘要

[NLP-131] QG-SMS: Enhancing Test Item Analysis via Student Modeling and Simulation

链接: https://arxiv.org/abs/2503.05888
作者: Bang Nguyen,Tingting Du,Mengxia Yu,Lawrence Angrave,Meng Jiang
机构: University of Notre Dame (圣母大学); University of Wisconsin-Madison (威斯康星大学麦迪逊分校); University of Illinois at Urbana-Champaign (伊利诺伊大学香槟分校)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG)
备注: Under Review

点击查看摘要

[NLP-132] Bimodal Connection Attention Fusion for Speech Emotion Recognition

链接: https://arxiv.org/abs/2503.05858
作者: Jiachen Luo,Huy Phan,Lin Wang,Joshua D. Reiss
机构: Centre for Digital Music, Queen Mary University of London (中心数字音乐, 伦敦玛丽女王大学)
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multimedia (cs.MM); Audio and Speech Processing (eess.AS)
备注:

点击查看摘要

[NLP-133] his Is Your Doge If It Please You: Exploring Deception and Robustness in Mixture of LLM s

链接: https://arxiv.org/abs/2503.05856
作者: Lorenz Wolf,Sangwoong Yoon,Ilija Bogunovic
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 35 pages, 9 figures, 16 tables

点击查看摘要

[NLP-134] Extracting and Emulsifying Cultural Explanation to Improve Multilingual Capability of LLM s

链接: https://arxiv.org/abs/2503.05846
作者: Hamin Koo,Jaehyung Kim
机构: Yonsei University (延世大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: under review, 18pages

点击查看摘要

[NLP-135] MedSimAI: Simulation and Formative Feedback Generation to Enhance Deliberate Practice in Medical Education

链接: https://arxiv.org/abs/2503.05793
作者: Yann Hicke,Jadon Geathers,Niroop Rajashekar,Colleen Chan,Anyanate Gwendolyne Jack,Justin Sewell,Mackenzi Preston,Susannah Cornes,Dennis Shung,Rene Kizilcec
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-136] Emergent Abilities in Large Language Models : A Survey

链接: https://arxiv.org/abs/2503.05788
作者: Leonardo Berti,Flavio Giorgi,Gjergji Kasneci
机构: Technical University of Munich (慕尼黑工业大学); Sapienza University of Rome (罗马一大)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-137] FedMentalCare: Towards Privacy-Preserving Fine-Tuned LLM s to Analyze Mental Health Status Using Federated Learning Framework

链接: https://arxiv.org/abs/2503.05786
作者: S M Sarwar
机构: University of Maryland Baltimore County (马里兰大学巴尔的摩郡分校)
类目: Computation and Language (cs.CL); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
备注: 9 pages, 3 figures, 2 tables and 2 algorithms

点击查看摘要

[NLP-138] Where is my Glass Slipper? AI Poetry and Art DATE

链接: https://arxiv.org/abs/2503.05781
作者: Anastasios P. Pagiaslis
机构: 未知
类目: Computers and Society (cs.CY); Computation and Language (cs.CL)
备注: 36 pages, 0 figures, I have updated the submission to the correct submission standards apologies. The paper is a Literature Review so there are no formulas or results tables and images

点击查看摘要

[NLP-139] DreamNet: A Multimodal Framework for Semantic and Emotional Analysis of Sleep Narratives

链接: https://arxiv.org/abs/2503.05778
作者: Tapasvi Panchagnula
机构: Sreenidhi Institute of Science and Technology (斯里尼德拉科学与技术学院)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 10 pages, 5 figures, new research contribution

点击查看摘要

[NLP-140] Medical Hallucinations in Foundation Models and Their Impact on Healthcare

链接: https://arxiv.org/abs/2503.05777
作者: Yubin Kim,Hyewon Jeong,Shan Chen,Shuyue Stella Li,Mingyu Lu,Kumail Alhamoud,Jimin Mun,Cristina Grau,Minseok Jung,Rodrigo Gameiro,Lizhou Fan,Eugene Park,Tristan Lin,Joonsik Yoon,Wonjin Yoon,Maarten Sap,Yulia Tsvetkov,Paul Liang,Xuhai Xu,Xin Liu,Daniel McDuff,Hyeonhoon Lee,Hae Won Park,Samir Tulebaev,Cynthia Breazeal
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注:

点击查看摘要

[NLP-141] Effect of Gender Fair Job Description on Generative AI Images ISCA

链接: https://arxiv.org/abs/2503.05769
作者: Finn Böckling,Jan Marquenie,Ingo Siegert
机构: Otto von Guericke University Magdeburg (奥托·冯·格里克马格德堡大学)
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: ISCA/ITG Workshop on Diversity in Large Speech and Language Models

点击查看摘要

[NLP-142] Graph Masked Language Models

链接: https://arxiv.org/abs/2503.05763
作者: Aarush Sinha,OM Kumar CU
机构: Vellore Institute of Technology (维洛尔理工学院); OM Kumar CU (OM Kumar CU)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-143] Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models WWW25

链接: https://arxiv.org/abs/2503.05757
作者: Prasenjit Dey,Srujana Merugu,Sivaramakrishnan Kaveri
机构: Amazon
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Proceedings of the ACM Web Conference 2025, WWW 25

点击查看摘要

[NLP-144] CSTRL: Context-Driven Sequential Transfer Learning for Abstractive Radiology Report Summarization

链接: https://arxiv.org/abs/2503.05750
作者: Mst. Fahmida Sultana Naznin,Adnan Ibney Faruq,Mostafa Rifat Tazwar,Md Jobayer,Md. Mehedi Hasan Shawon,Md Rakibul Hasan
机构: Bangladesh University of Engineering and Technology (孟加拉国工程技术大学); BRAC University (孟加拉国工程技术大学); Curtin University (科廷大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 11-pages main paper with 2-pages appendices

点击查看摘要

[NLP-145] ChatWise: AI-Powered Engaging Conversations for Enhancing Senior Cognitive Wellbeing

链接: https://arxiv.org/abs/2503.05740
作者: Zhengbang Yang,Zhuangdi Zhu
机构: George Mason University (乔治·梅森大学)
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-146] What Are They Filtering Out? A Survey of Filtering Strategies for Harm Reduction in Pretraining Datasets

链接: https://arxiv.org/abs/2503.05721
作者: Marco Antonio Stranisci,Christian Hardmeier
机构: Università degli Studi di Torino (都灵大学); IT University of Copenhagen (哥本哈根信息技术大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-147] hat is Unacceptable: the Moral Foundations of Canceling

链接: https://arxiv.org/abs/2503.05720
作者: Soda Marem Lo,Oscar Araque,Rajesh Sharma,Marco Antonio Stranisci
机构: 未知
类目: Computers and Society (cs.CY); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-148] Beyond English: Unveiling Multilingual Bias in LLM Copyright Compliance

链接: https://arxiv.org/abs/2503.05713
作者: Yupeng Chen,Xiaoyu Zhang,Yixian Huang,Qian Xie
机构: The Chinese University of Hong Kong, Shenzhen (香港中文大学（深圳）); University of Leeds (利兹大学)
类目: Computers and Society (cs.CY); Computation and Language (cs.CL)
备注: Work in progress

点击查看摘要

[NLP-149] Russo-Ukrainian war disinformation detection in suspicious Telegram channels

链接: https://arxiv.org/abs/2503.05707
作者: Anton Bazdyrev
机构: 未知
类目: Computers and Society (cs.CY); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: CEUR-WS, Vol-3777 ProfIT AI 2024 4th International Workshop of IT-professionals on Artificial Intelligence 2024

点击查看摘要

[NLP-150] OPTIC: Optimizing Patient-Provider Triaging Improving Communications in Clinical Operations using GPT -4 Data Labeling and Model Distillation

链接: https://arxiv.org/abs/2503.05701
作者: Alberto Santamaria-Pang,Frank Tuan,Ross Campbell,Cindy Zhang,Ankush Jindal,Roopa Surapur,Brad Holloman,Deanna Hanisch,Rae Buckley,Carisa Cooney,Ivan Tarapov,Kimberly S. Peairs,Brian Hasselfeld,Peter Greene
机构: 未知
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注: 15 pages, 8 figures. submitted to Journal of the American Medical Informatics Association

点击查看摘要

[NLP-151] ORANSight-2.0: Foundational LLM s for O-RAN

链接: https://arxiv.org/abs/2503.05200
作者: Pranshav Gajjar,Vijay K. Shah
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI)
备注:

点击查看摘要

[NLP-152] Building English ASR model with regional language support

链接: https://arxiv.org/abs/2503.07522
作者: Purvi Agrawal,Vikas Joshi,Bharati Patidar,Ankur Gupta,Rupesh Kumar Mehta
机构: 未知
类目: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL)
备注: 5 pages, 3 figures

点击查看摘要

[NLP-153] Evaluating and Aligning Human Economic Risk Preferences in LLM s

链接: https://arxiv.org/abs/2503.06646
作者: Jiaxin Liu,Yi Yang,Kar Yan Tam
机构: 未知
类目: General Economics (econ.GN); Computation and Language (cs.CL)
备注:

点击查看摘要

计算机视觉

[CV-0] AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning

链接: https://arxiv.org/abs/2503.07608
作者: Bo Jiang,Shaoyu Chen,Qian Zhang,Wenyu Liu,Xinggang Wang
机构: Huazhong University of Science and Technology (华中科技大学); Horizon Robotics (地平线)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: Project Page: this https URL

点击查看摘要

[CV-1] VoD: Learning Volume of Differences for Video-Based Deepfake Detection

链接: https://arxiv.org/abs/2503.07607
作者: Ying Xu,Marius Pedersen,Kiran Raja
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-2] Should VLMs be Pre-trained with Image Data? ICLR2025

【速读】：该论文试图解决的问题是：相比于在预训练初期即整合图像数据的视觉-语言模型（Vision-Language Models, VLMs），分两步进行训练（先文本预训练，后加入图像数据再训练）的多模态预训练语言模型（Multimodal Pre-trained Language Models）在视觉-语言任务和纯文本任务上的性能差异及其原因。论文旨在量化这种两步训练方法相对于早期集成图像数据的方法所带来的增益或损失。

解决方案的关键在于系统性地对比不同预训练策略的效果。具体而言，作者训练了一系列模型，这些模型在数据集、模型规模、图像-文本比例以及预训练阶段引入视觉标记的时间点等方面存在差异。通过分析这些模型在下游视觉-语言任务和纯文本任务上的表现，研究发现，在预训练过程中混合图像和文本数据可以提升视觉-语言任务的表现，同时保持纯文本任务的竞争力。此外，对于10亿参数量级的模型，在预训练的80%阶段引入视觉标记相较于在完全预训练后引入，平均能在6项多样化任务上带来2%的性能提升。这一结果揭示了在预训练后期引入视觉信息的有效性及其对整体模型性能的影响。

链接: https://arxiv.org/abs/2503.07603
作者: Sedrick Keh,Jean Mercat,Samir Yitzhak Gadre,Kushal Arora,Igor Vasiljevic,Benjamin Burchfiel,Shuran Song,Russ Tedrake,Thomas Kollar,Ludwig Schmidt,Achal Dave
机构: Toyota Research Institute (丰田研究所); Columbia University (哥伦比亚大学); Stanford (斯坦福大学); MIT (麻省理工学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: ICLR 2025

点击查看摘要

Abstract:Pre-trained LLMs that are further trained with image data perform well on vision-language tasks. While adding images during a second training phase effectively unlocks this capability, it is unclear how much of a gain or loss this two-step pipeline gives over VLMs which integrate images earlier into the training process. To investigate this, we train models spanning various datasets, scales, image-text ratios, and amount of pre-training done before introducing vision tokens. We then fine-tune these models and evaluate their downstream performance on a suite of vision-language and text-only tasks. We find that pre-training with a mixture of image and text data allows models to perform better on vision-language tasks while maintaining strong performance on text-only evaluations. On an average of 6 diverse tasks, we find that for a 1B model, introducing visual tokens 80% of the way through pre-training results in a 2% average improvement over introducing visual tokens to a fully pre-trained model.
zh

[CV-3] DreamRelation: Relation-Centric Video Customization

链接: https://arxiv.org/abs/2503.07602
作者: Yujie Wei,Shiwei Zhang,Hangjie Yuan,Biao Gong,Longxiang Tang,Xiang Wang,Haonan Qiu,Hengjia Li,Shuai Tan,Yingya Zhang,Hongming Shan
机构: Fudan University (复旦大学); Alibaba Group (阿里巴巴集团); Ant Group (蚂蚁集团); Nanyang Technological University (南洋理工大学); Zhejiang University (浙江大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project Page: this https URL

点击查看摘要

[CV-4] Balanced Image Stylization with Style Matching Score

链接: https://arxiv.org/abs/2503.07601
作者: Yuxin Jiang,Liming Jiang,Shuai Yang,Jia-Wei Liu,Ivor Tsang,Mike Zheng Shou
机构: Show Lab, National University of Singapore (新加坡国立大学); Nanyang Technological University (南洋理工大学); Wangxuan Institute of Computer Technology, Peking University (北京大学王选计算机技术研究所); Agency for Science, Technology and Research (A*STAR) (新加坡科技研究局)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Project page: this https URL

点击查看摘要

[CV-5] VACE: All-in-One Video Creation and Editing

链接: https://arxiv.org/abs/2503.07598
作者: Zeyinzi Jiang,Zhen Han,Chaojie Mao,Jingfeng Zhang,Yulin Pan,Yu Liu
机构: Tongyi Lab, Alibaba Group (阿里云实验室，阿里巴巴集团)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-6] HumanMM: Global Human Motion Recovery from Multi-shot Videos CVPR2025

链接: https://arxiv.org/abs/2503.07597
作者: Yuhong Zhang,Guanlin Wu,Ling-Hao Chen,Zhuokai Zhao,Jing Lin,Xiaoke Jiang,Jiamin Wu,Zhuoheng Li,Hao Frank Yang,Haoqian Wang,Lei Zhang
机构: Tsinghua University (清华大学); IDEA Research (IDEA 研究院); Johns Hopkins University (约翰斯·霍普金斯大学); University of Chicago (芝加哥大学); HKUST (香港科技大学); HKU (香港大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: CVPR 2025; Project page: this https URL

点击查看摘要

[CV-7] Hierarchical Cross-Modal Alignment for Open-Vocabulary 3D Object Detection AAAI2025

链接: https://arxiv.org/abs/2503.07593
作者: Youjun Zhao,Jiaying Lin,Rynson W.H. Lau
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: AAAI 2025 (Extented Version). Project Page: this https URL

点击查看摘要

[CV-8] Filter Images First Generate Instructions Later: Pre-Instruction Data Selection for Visual Instruction Tuning CVPR

链接: https://arxiv.org/abs/2503.07591
作者: Bardia Safaei,Faizan Siddiqui,Jiacong Xu,Vishal M. Patel,Shao-Yuan Lo
机构: Johns Hopkins University (约翰霍普金斯大学); Honda Research Institute USA (本田研究院美国)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Accepted at Computer Vision and Pattern Recognition Conference (CVPR) 2025

点击查看摘要

[CV-9] When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning

链接: https://arxiv.org/abs/2503.07588
作者: Junwei Luo,Yingying Zhang,Xue Yang,Kang Wu,Qi Zhu,Lei Liang,Jingdong Chen,Yansheng Li
机构: Wuhan Universtiy (武汉大学); Ant Group (蚂蚁集团); Shanghai Jiao Tong University (上海交通大学); University of Science and Technology of China (中国科学技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 12 pages, 6 figures, 7 tables

点击查看摘要

[CV-10] Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru

链接: https://arxiv.org/abs/2503.07587
作者: Dunant Cusipuma,David Ortega,Victor Flores-Benites,Arturo Deza
机构: Artificio (Artificio); Universidad de Ingeneria y Tecnologia (UTEC) (秘鲁利马工程技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Robotics (cs.RO)
备注: A pre-print. 26 pages. Link to Code + Data: this https URL

点击查看摘要

[CV-11] Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation

链接: https://arxiv.org/abs/2503.07578
作者: Tianyu Chen,Yasi Zhang,Zhendong Wang,Ying Nian Wu,Oscar Leong,Mingyuan Zhou
机构: University of Texas at Austin (德克萨斯大学奥斯汀分校); University of California, Los Angeles (加州大学洛杉矶分校); Microsoft (微软)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: First Author and Second Author contributed equally to this work. The last two authors equally advised this work

点击查看摘要

[CV-12] Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regression

链接: https://arxiv.org/abs/2503.07561
作者: Thibaut Loiseau,Guillaume Bourmaud,Vincent Lepetit
机构: LIGM, Ecole des Ponts, Univ Gustave Eiffel, CNRS (法国国家科学研究中心), France; Laboratoire IMS, Université de Bordeaux (波尔多大学), France
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-13] LBM: Latent Bridge Matching for Fast Image-to-Image Translation

链接: https://arxiv.org/abs/2503.07535
作者: Clément Chadebec,Onur Tasar,Sanjeev Sreetharan,Benjamin Aubin
机构: Jasper Research (贾斯珀研究)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-14] VisRL: Intention-Driven Visual Perception via Reinforced Reasoning

【速读】：该论文试图解决在视觉理解任务中，由于意图驱动的焦点选择导致的标注开销问题。现有方法依赖于带注释的中间边界框进行监督训练，但这种方式因意图-区域对组合爆炸而难以扩展。论文的关键解决方案是提出VisRL框架，它首次将强化学习（Reinforcement Learning, RL）应用于意图驱动的视觉感知任务。VisRL通过仅使用奖励信号优化整个视觉推理过程，将中间焦点选择视为通过试错优化的内部决策，从而消除了昂贵的区域标注需求，同时更紧密地模拟人类的学习方式。实验结果表明，VisRL在多个基准数据集上超越了强大的基线模型，并展现出对不同大型多模态模型的良好泛化能力。

链接: https://arxiv.org/abs/2503.07523
作者: Zhangquan Chen,Xufang Luo,Dongsheng Li
机构: Tsinghua University (清华大学); Microsoft Research Asia (微软研究院亚洲)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 18pages,11 figures

点击查看摘要

Abstract:Visual understanding is inherently intention-driven - humans selectively focus on different regions of a scene based on their goals. Recent advances in large multimodal models (LMMs) enable flexible expression of such intentions through natural language, allowing queries to guide visual reasoning processes. Frameworks like Visual Chain-of-Thought have demonstrated the benefit of incorporating explicit reasoning steps, where the model predicts a focus region before answering a query. However, existing approaches rely heavily on supervised training with annotated intermediate bounding boxes, which severely limits scalability due to the combinatorial explosion of intention-region pairs. To overcome this limitation, we propose VisRL, the first framework that applies reinforcement learning (RL) to the problem of intention-driven visual perception. VisRL optimizes the entire visual reasoning process using only reward signals. By treating intermediate focus selection as a internal decision optimized through trial-and-error, our method eliminates the need for costly region annotations while aligning more closely with how humans learn to perceive the world. Extensive experiments across multiple benchmarks show that VisRL consistently outperforms strong baselines, demonstrating both its effectiveness and its strong generalization across different LMMs. Our code is available at this [URL](this https URL).
zh

[CV-15] From Limited Labels to Open Domains: An Efficient Learning Paradigm for UAV-view Geo-Localization

链接: https://arxiv.org/abs/2503.07520
作者: Zhongwei Chen,Zhao-Xu Yang,Hai-Jun Rong,Jiawei Lang
机构: State Key Laboratory for Strength and Vibration of Mechanical Structures (机械结构强度与振动国家重点实验室); School of Aerospace Engineering, Xi’an Jiaotong University (西安交通大学航空航天学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Information Retrieval (cs.IR)
备注:

点击查看摘要

[CV-16] FastInstShadow: A Simple Query-Based Model for Instance Shadow Detection

链接: https://arxiv.org/abs/2503.07517
作者: Takeru Inoue,Ryusuke Miyamoto
机构: Meiji University (明治大学); Meiji University (明治大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-17] CPAny: Couple With Any Encoder to Refer Multi-Object Tracking

链接: https://arxiv.org/abs/2503.07516
作者: Weize Li,Yunhao Du,Qixiang Yin,Zhicheng Zhao,Fei Su,Daqi Liu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-18] PointVLA: Injecting the 3D World into Vision-Language-Action Models

链接: https://arxiv.org/abs/2503.07511
作者: Chengmeng Li,Junjie Wen,Yan Peng,Yaxin Peng,Feifei Feng,Yichen Zhu
机构: Midea Group (美的集团); Shanghai University (上海大学); East China Normal University (华东师范大学)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-19] PE3R: Perception-Efficient 3D Reconstruction

链接: https://arxiv.org/abs/2503.07507
作者: Jie Hu,Shizun Wang,Xinchao Wang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-20] ADROIT: A Self-Supervised Framework for Learning Robust Representations for Active Learning

链接: https://arxiv.org/abs/2503.07506
作者: Soumya Banerjee,Vinay Kumar Verma
机构: IIT Kanpur (印度理工学院坎普尔校区); Amazon, India (亚马逊印度)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-21] hink Before You Segment: High-Quality Reasoning Segmentation with GPT Chain of Thoughts

链接: https://arxiv.org/abs/2503.07503
作者: Shiu-hong Kao,Yu-Wing Tai,Chi-Keung Tang
机构: HKUST (香港科技大学); Dartmouth College (达特茅斯学院); HKUST (香港科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-22] AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements

链接: https://arxiv.org/abs/2503.07499
作者: Calvin Yeung,Tomohiro Suzuki,Ryota Tanaka,Zhuoer Yin,Keisuke Fujii
机构: Graduate School of Informatics, Nagoya University (名古屋大学信息研究院), Japan; Center for Advanced Intelligence Project, RIKEN (理化学研究所先进智能研究中心), Japan
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-23] V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation

链接: https://arxiv.org/abs/2503.07493
作者: Guiwei Zhang,Tianyu Zhang,Mohan Zhou,Yalong Bai,Biye Li
机构: Du Xiaoman Financial (度小满金融)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 11 pages, 6 figures

点击查看摘要

[CV-24] LLaVA-RadZ: Can Multimodal Large Language Models Effectively Tackle Zero-shot Radiology Recognition?

链接: https://arxiv.org/abs/2503.07487
作者: Bangyan Li,Wenxuan Huang,Yunhang Shen,Yeqiang Wang,Shaohui Lin,Jingzhong Lin,Ling You,Yinqi Zhang,Ke Li,Xing Sun,Yuling Sun
机构: East China Normal University; Tencent Youtu Lab. (腾讯优图实验室); Northwest A&F University
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-25] Chameleon: Fast-slow Neuro-symbolic Lane Topology Extraction ICRA2025

链接: https://arxiv.org/abs/2503.07485
作者: Zongzheng Zhang,Xinrun Li,Sizhe Zou,Guoxuan Chi,Siqi Li,Xuchong Qiu,Guoliang Wang,Guantian Zheng,Leichen Wang,Hang Zhao,Hao Zhao
机构: Institute for AI Industry Research (AIR), Tsinghua University (清华大学智能产业研究院); Bosch Corporate Research (博世中央研究部); Institute for Interdisciplinary Information Sciences(IIIS), Tsinghua University (清华大学交叉信息研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: ICRA 2025, Project Page: this https URL

点击查看摘要

[CV-26] VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models

链接: https://arxiv.org/abs/2503.07478
作者: Jiacheng Ruan,Wenzhen Yuan,Xian Gao,Ye Guo,Daoxin Zhang,Zhe Xu,Yao Hu,Ting Liu,Yuzhuo Fu
机构: Shanghai Jiao Tong University (上海交通大学); Xiaohongshu Inc. (小红书科技)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 12 pages, 4 figures. This work is in progress

点击查看摘要

[CV-27] SOGS: Second-Order Anchor for Advanced 3D Gaussian Splatting CVPR2025

链接: https://arxiv.org/abs/2503.07476
作者: Jiahui Zhang,Fangneng Zhan,Ling Shao,Shijian Lu
机构: Nanyang Technological University (南洋理工大学); Harvard University (哈佛大学); MIT (麻省理工学院); UCAS-Terminus AI Lab, University of Chinese Academy of Sciences (中国科学院大学 UCAS-Terminus AI 实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025

点击查看摘要

[CV-28] A Review on Geometry and Surface Inspection in 3D Concrete Printing

链接: https://arxiv.org/abs/2503.07472
作者: K. Mawas,M. Maboudi,M. Gerke
机构: Technische Universität Braunschweig (布伦瑞克工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-29] YOLOE: Real-Time Seeing Anything

链接: https://arxiv.org/abs/2503.07465
作者: Ao Wang,Lihao Liu,Hui Chen,Zijia Lin,Jungong Han,Guiguang Ding
机构: Tsinghua University (清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 15 pages, 9 figures;

点击查看摘要

[CV-30] Anatomy-Aware Conditional Image-Text Retrieval

链接: https://arxiv.org/abs/2503.07456
作者: Meng Zheng,Jiajin Zhang,Benjamin Planche,Zhongpai Gao,Terrence Chen,Ziyan Wu
机构: United Imaging Intelligence (联影智能); Rensselaer Polytechnic Institute (伦斯勒理工学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 16 pages, 10 figures

点击查看摘要

[CV-31] EigenGS Representation: From Eigenspace to Gaussian Image Space

链接: https://arxiv.org/abs/2503.07446
作者: Lo-Wei Tai,Ching-En Li,Cheng-Lin Chen,Chih-Jung Tsai,Hwann-Tzong Chen,Tyng-Luh Liu
机构: National Tsing Hua University (清华大学); Aeolus Robotics (未知); Academia Sinica, Taiwan (台湾中央研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-32] Divide and Conquer Self-Supervised Learning for High-Content Imaging

链接: https://arxiv.org/abs/2503.07444
作者: Lucas Farndale,Paul Henderson,Edward W Roberts,Ke Yuan
机构: Cancer Research UK Scotland Institute (英国癌症研究中心苏格兰研究所), Glasgow, Scotland; University of Glasgow (格拉斯哥大学), Glasgow, Scotland
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
备注:

点击查看摘要

[CV-33] Open-Set Gait Recognition from Sparse mmWave Radar Point Clouds

链接: https://arxiv.org/abs/2503.07435
作者: Riccardo Mazzieri,Jacopo Pegoraro,Michele Rossi
机构: Department of Information Engineering, University of Padova (信息工程系, 帕多瓦大学); Department of Mathematics “Tullio Levi-Civita”, University of Padova (“图里奥·利维–齐瓦塔”数学系, 帕多瓦大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Signal Processing (eess.SP)
备注:

点击查看摘要

[CV-34] CATPlan: Loss-based Collision Prediction in End-to-End Autonomous Driving

链接: https://arxiv.org/abs/2503.07425
作者: Ziliang Xiong,Shipeng Liu,Nathaniel Helgesen,Joakim Johnander,Per-Erik Forssen
机构: Computer Vision Laboratory, Department of Electrical Engineering, Linköping University (林雪平大学); Zenseact (智驾科技), Sweden (瑞典)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-35] Analysis of 3D Urticaceae Pollen Classification Using Deep Learning Models

链接: https://arxiv.org/abs/2503.07419
作者: Tijs Konijn,Imaan Bijl,Lu Cao,Fons Verbeek
机构: Leiden Institute of Advanced Computer Science, Leiden University (莱顿大学先进计算机科学研究所)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-36] AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion CVPR2025

链接: https://arxiv.org/abs/2503.07418
作者: Mingzhen Sun,Weining Wang,Gen Li,Jiawei Liu,Jiahui Sun,Wanquan Feng,Shanshan Lao,SiYu Zhou,Qian He,Jing Liu
机构: IA, CAS (中科院自动化研究所); UCAS (中国科学院大学); Bytedance Inc. (字节跳动)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025

点击查看摘要

[CV-37] GM-MoE: Low-Light Enhancement with Gated-Mechanism Mixture-of-Experts

链接: https://arxiv.org/abs/2503.07417
作者: Minwen Liao,Hao Bo Dong,Xinyi Wang,Ziyang Yan,Yihua Shao
机构: XJU (新疆大学); HUC (哈尔滨大学); CUST (长春理工大学); UniTn (University of Trento); USTB (北京科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-38] meStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision

链接: https://arxiv.org/abs/2503.07416
作者: Shaobin Zhuang,Yiwei Guo,Yanbo Ding,Kunchang Li,Xinyuan Chen,Yaohui Wang,Fangyikang Wang,Ying Zhang,Chen Li,Yali Wang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 17 pages, 5 figures, 13 tables

点击查看摘要

[CV-39] REF-VLM: Triplet-Based Referring Paradigm for Unified Visual Decoding

链接: https://arxiv.org/abs/2503.07413
作者: Yan Tai,Luhao Zhu,Zhiqiang Chen,Ynan Ding,Yiying Dong,Xiaohong Liu,Guodong Guo
机构: Shanghai Jiao Tong University (上海交通大学); Zhejiang University (浙江大学); Hong Kong Polytechnic University (香港理工大学); Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China (宁波数字孪生研究院, 浙东理工学院, 宁波, 中国)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-40] Keeping Representation Similarity in Finetuning for Medical Image Analysis

链接: https://arxiv.org/abs/2503.07399
作者: Wenqiang Zu,Shenghao Xie,Hao Chen,Yiming Liang,Lei Ma
机构: Institute of Automation, Chinese Academy of Sciences (自动化研究所，中国科学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 12 pages, 6 figures

点击查看摘要

[CV-41] Brain Inspired Adaptive Memory Dual-Net for Few-Shot Image Classification

链接: https://arxiv.org/abs/2503.07396
作者: Kexin Di,Xiuxing Li,Yuyang Han,Ziyu Li,Qing Li,Xia Wu
机构: Beijing Normal University (北京师范大学); Beijing Institute of Technology (北京理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-42] SPEED: Scalable Precise and Efficient Concept Erasure for Diffusion Models

链接: https://arxiv.org/abs/2503.07392
作者: Ouxiang Li,Yuan Wang,Xinting Hu,Houcheng Jiang,Tao Liang,Yanbin Hao,Guojun Ma,Fuli Feng
机构: University of Science and Technology of China (中国科学技术大学); Nanyang Technological University (南洋理工大学); Douyin Co., Ltd. (抖音有限公司); Hefei University of Technology (合肥工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-43] PersonaBooth: Personalized Text-to-Motion Generation

链接: https://arxiv.org/abs/2503.07390
作者: Boeun Kim,Hea In Jeong,JungHoon Sung,Yihua Cheng,Jeongmin Lee,Ju Yong Chang,Sang-Il Choi,Younggeun Choi,Saim Shin,Jungho Kim,Hyung Jin Chang
机构: University of Birmingham (伯明翰大学); Korea Electronics Technology Institute (韩国电子技术研究院); Dankook University (檀国大学); Kwangwoon University (光云大学); Saim Shin (未知); Jungho Kim (未知); Hyung Jin Chang (未知)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-44] RCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models

链接: https://arxiv.org/abs/2503.07389
作者: Ruidong Chen,Honglin Guo,Lanjun Wang,Chenyu Zhang,Weizhi Nie,An-An Liu
机构: The School of Electrical and Information Engineering, Tianjin University (天津大学电气与信息工程学院); The School of New Media and Communication, Tianjin University (天津大学新媒体与传播学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-45] Probabilistic Segmentation for Robust Field of View Estimation

链接: https://arxiv.org/abs/2503.07375
作者: R. Spencer Hallyburton,David Hunt,Yiwei He,Judy He,Miroslav Pajic
机构: Department of Electrical and Computer Engineering, Duke University (杜克大学), Durham, NC 27708, USA
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-46] HGO-YOLO: Advancing Anomaly Behavior Detection with Hierarchical Features and Lightweight Optimized Detection

链接: https://arxiv.org/abs/2503.07371
作者: Qizhi Zheng,Zhongze Luo,Meiyan Guo,Xinzhu Wang,Renqimuge Wu,Qiu Meng,Guanghui Dong
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages

点击查看摘要

[CV-47] LEGO-Motion: Learning-Enhanced Grids with Occupancy Instance Modeling for Class-Agnostic Motion Prediction

链接: https://arxiv.org/abs/2503.07367
作者: Kangan Qian,Jinyu Miao,Ziang Luo,Zheng Fu,and Jinchen Li,Yining Shi,Yunlong Wang,Kun Jiang,Mengmeng Yang,Diange Yang
机构: School of Vehicle and Mobility, Tsinghua University (清华大学车辆与运载学院); AI2Robotics (AI2Robotics); AD Division of NIO Inc. (蔚来汽车自动驾驶部门)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 4 figures

点击查看摘要

[CV-48] MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning

链接: https://arxiv.org/abs/2503.07365
作者: Fanqing Meng,Lingxiao Du,Zongkai Liu,Zhixiang Zhou,Quanfeng Lu,Daocheng Fu,Botian Shi,Wenhai Wang,Junjun He,Kaipeng Zhang,Ping Luo,Yu Qiao,Qiaosheng Zhang,Wenqi Shao
机构: Shanghai AI Laboratory (上海人工智能实验室); Shanghai Innovation Institute (上海创新研究院); Shanghai Jiao Tong University (上海交通大学); The University of Hong Kong (香港大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-49] Inversion-Free Video Style Transfer with Trajectory Reset Attention Control and Content-Style Bridging

链接: https://arxiv.org/abs/2503.07363
作者: Jiang Lin,Zili Yi
机构: Nanjing University (南京大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-50] Certifiably Optimal Anisotropic Rotation Averag ing

链接: https://arxiv.org/abs/2503.07353
作者: Carl Olsson,Yaroslava Lochman,Johan Malmport,Christopher Zach
机构: Lund University (隆德大学); Chalmers University of Technology (查尔姆斯理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-51] Fully Unsupervised Annotation of C. Elegans

链接: https://arxiv.org/abs/2503.07348
作者: Christoph Karg,Sebastian Stricker,Lisa Hutschenreiter,Bogdan Savchynskyy,Dagmar Kainmueller
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-52] DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection

链接: https://arxiv.org/abs/2503.07347
作者: Johan Edstedt,Georg Bökman,Mårten Wadenbäck,Michael Felsberg
机构: Linköping University (林雪平大学); Chalmers University of Technology (查尔姆斯理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-53] Now you see me! A framework for obtaining class-relevant saliency maps

链接: https://arxiv.org/abs/2503.07346
作者: Nils Philipp Walter,Jilles Vreeken,Jonas Fischer
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-54] Unleashing the Potential of Large Language Models for Text-to-Image Generation through Autoregressive Representation Alignment

链接: https://arxiv.org/abs/2503.07334
作者: Xing Xie,Jiawei Liu,Ziyue Lin,Huijie Fan,Zhi Han,Yandong Tang,Liangqiong Qu
机构: Shenyang Institute of Automation, Chinese Academy of Sciences (沈阳自动化研究所，中国科学院); University of Chinese Academy of Sciences (中国科学院大学); The University of Hong Kong (香港大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-55] Mitigating Hallucinations in YOLO-based Object Detection Models: A Revisit to Out-of-Distribution Detection

链接: https://arxiv.org/abs/2503.07330
作者: Weicheng He,Changshun Wu,Chih-Hong Cheng,Xiaowei Huang,Saddek Bensalem
机构: Université Grenoble Alpes (格勒诺布尔阿尔卑斯大学); Chalmers University of Technology (查尔姆斯理工大学); University of Gothenburg (哥德堡大学); University of Liverpool (利物浦大学); CSX-AI (格勒诺布尔)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Software Engineering (cs.SE)
备注:

点击查看摘要

[CV-56] Dynamic Path Navigation for Motion Agents with LLM Reasoning

链接: https://arxiv.org/abs/2503.07323
作者: Yubo Zhao,Qi Wu,Yifan Wang,Yu-Wing Tai,Chi-Keung Tang
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-57] Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions ICLR2025

链接: https://arxiv.org/abs/2503.07315
作者: Rui Qiao,Zhaoxuan Wu,Jingtan Wang,Pang Wei Koh,Bryan Kian Hsiang Low
机构: National University of Singapore (新加坡国立大学); Singapore-MIT Alliance for Research and Technology (新加坡-麻省理工学院研究与技术联盟); Agency for Science, Technology and Research (A*STAR) (科学技术研究局); University of Washington (华盛顿大学)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to the 13th International Conference on Learning Representations (ICLR 2025). Code is available at this https URL

点击查看摘要

[CV-58] Automated Movie Generation via Multi-Agent CoT Planning

链接: https://arxiv.org/abs/2503.07314
作者: Weijia Wu,Zeyu Zhu,Mike Zheng Shou
机构: Show Lab, National University of Singapore (新加坡国立大学 Show 实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: The code and project website are available at: this https URL and this https URL

点击查看摘要

[CV-59] AttenST: A Training-Free Attention-Driven Style Transfer Framework with Pre-Trained Diffusion Models

链接: https://arxiv.org/abs/2503.07307
作者: Bo Huang,Wenlun Xu,Qizhuo Han,Haodong Jing,Ying Li
机构: Northwestern Polytechnical University (西北工业大学); Northwest A&F University (西北农林科技大学); Xi’an Jiaotong University (西安交通大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-60] Goal Conditioned Reinforcement Learning for Photo Finishing Tuning NEURIPS2024

链接: https://arxiv.org/abs/2503.07300
作者: Jiarui Wu,Yujin Wang,Lingen Li,Zhang Fan,Tianfan Xue
机构: Shanghai AI Laboratory (上海人工智能实验室); The Chinese University of Hong Kong (香港中文大学); PJLab (鹏城实验室)
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV)
备注: 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

点击查看摘要

[CV-61] ALLVB: All-in-One Long Video Understanding Benchmark AAAI2025

链接: https://arxiv.org/abs/2503.07298
作者: Xichen Tan,Yuanjing Luo,Yunfan Ye,Fang Liu,Zhiping Cai
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: AAAI 2025

点击查看摘要

[CV-62] Distilling Knowledge into Quantum Vision Transformers for Biomedical Image Classification MICCAI2025

链接: https://arxiv.org/abs/2503.07294
作者: Thomas Boucher,Evangelos B. Mazomenos
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Submitted for MICCAI 2025

点击查看摘要

[CV-63] A Systematic Review of ECG Arrhythmia Classification: Adherence to Standards Fair Evaluation and Embedded Feasibility

链接: https://arxiv.org/abs/2503.07276
作者: Guilherme Silva,Pedro Silva,Gladston Moreira,Vander Freitas,Jadson Gertrudes,Eduardo Luz
机构: Computing Department, Federal University of Ouro Preto (计算机系, 米纳斯吉拉斯联邦大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-64] Efficient Distillation of Classifier-Free Guidance using Adapters

链接: https://arxiv.org/abs/2503.07274
作者: Cristian Perez Jensen,Seyedmorteza Sadat
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-65] Customized SAM 2 for Referring Remote Sensing Image Segmentation

链接: https://arxiv.org/abs/2503.07266
作者: Fu Rong,Meng Lan,Qian Zhang,Lefei Zhang
机构: Wuhan University (武汉大学); Hong Kong University of Science and Technology (香港科技大学); Horizon Robotics (地平线 robotics)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-66] COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition

链接: https://arxiv.org/abs/2503.07259
作者: Baiyu Chen,Wilson Wongso,Zechen Li,Yonchanok Khaokaew,Hao Xue,Flora Salim
机构: The University of New South Wales (新南威尔士大学), Sydney, NSW, Australia
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-67] AnomalyPainter: Vision-Language-Diffusion Synergy for Zero-Shot Realistic and Diverse Industrial Anomaly Synthesis

链接: https://arxiv.org/abs/2503.07253
作者: Zhangyu Lai,Yilin Lu,Xinyang Li,Jianghang Lin,Yansong Qu,Liujuan Cao,Ming Li,Rongrong Ji
机构: Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University (厦门大学); INSPUR DIGI ENT. (浪潮电子信息产业有限公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: anomaly synthesis,anomaly detection

点击查看摘要

[CV-68] Semantic Communications with Computer Vision Sensing for Edge Video Transmission

链接: https://arxiv.org/abs/2503.07252
作者: Yubo Peng,Luping Xiang,Kun Yang,Kezhi Wang,Merouane Debbah
机构: State Key Laboratory of Novel Software Technology, Nanjing University (南京大学), Nanjing, China; School of Intelligent Software and Engineering, Nanjing University (南京大学)(Suzhou Campus), Suzhou, China; Department of Computer Science, Brunel University London (布鲁内尔大学伦敦学院), UK; Department of Electrical Engineering and Computer Science and the KU 6G Center, Khalifa University (哈利法大学), Abu Dhabi 127788, UAE
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV); Signal Processing (eess.SP)
备注:

点击查看摘要

[CV-69] xt-IRSTD: Leverag ing Semantic Text to Promote Infrared Small Target Detection in Complex Scenes

链接: https://arxiv.org/abs/2503.07249
作者: Feng Huang,Shuyuan Zheng,Zhaobing Qiu,Huanxian Liu,Huanxin Bai,Liqiong Chen
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-70] Retinex-MEF: Retinex-based Glare Effects Aware Unsupervised Multi-Exposure Image Fusion

链接: https://arxiv.org/abs/2503.07235
作者: Haowen Bai,Jiangshe Zhang,Zixiang Zhao,Lilun Deng,Yukun Cui,Shuang Xu
机构: Xi’an Jiaotong University (西安交通大学); ETH Zürich (瑞士苏黎世联邦理工学院); Northwestern Polytechnical University (西北工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-71] CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLM s and Chain-of-Thought Prompting

链接: https://arxiv.org/abs/2503.07234
作者: Haicheng Liao,Hanlin Kong,Bonan Wang,Chengyue Wang,Wang Ye,Zhengbing He,Chengzhong Xu,Zhenning Li
机构: State Key Laboratory of Internet of Things for Smart City, University of Macau (澳门大学物联网智慧城市国家重点实验室); Department of Computer and Information Science, University of Macau (澳门大学计算机与信息科学系); Senseable City Lab, Massachusetts Institute of Technology (麻省理工学院感城实验室); State Key Lab of Intelligent Transportation System (智能交通系统国家重点实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Robotics (cs.RO)
备注:

点击查看摘要

[CV-72] Boosting Diffusion-Based Text Image Super-Resolution Model Towards Generalized Real-World Scenarios

链接: https://arxiv.org/abs/2503.07232
作者: Chenglu Pan,Xiaogang Xu,Ganggui Ding,Yunke Zhang,Wenbo Li,Jiarong Xu,Qingbiao Wu
机构: Zhejiang University (浙江大学); Huawei Technologies Ltd. (华为技术有限公司); Fudan University (复旦大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-73] A Deep Learning Architecture for Land Cover Mapping Using Spatio-Temporal Sentinel-1 Features

链接: https://arxiv.org/abs/2503.07230
作者: Luigi Russo,Antonietta Sorriso,Silvia Liberata Ullo,Paolo Gamba
机构: Department of Electrical, Computer and Biomedical Engineering, University of Pavia (意大利帕维亚大学); Department of Engineering, University of Sannio (意大利萨尼奥大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注: Submitted to IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

点击查看摘要

[CV-74] ReelWave: A Multi-Agent Framework Toward Professional Movie Sound Generation

链接: https://arxiv.org/abs/2503.07217
作者: Zixuan Wang,Chi-Keung Tang,Yu-Wing Tai
机构: HKUST (香港科技大学); Dartmouth College (达特茅斯学院)
类目: ound (cs.SD); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-75] Synthetic Lung X-ray Generation through Cross-Attention and Affinity Transformation

链接: https://arxiv.org/abs/2503.07209
作者: Ruochen Pi,Lianlei Shan
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-76] Endo-FASt3r: Endoscopic Foundation model Adaptation for Structure from motion

链接: https://arxiv.org/abs/2503.07204
作者: Mona Sheikh Zeinoddin,Mobarakol Islam,Zafer Tandogdu,Greg Shaw,Mathew J. Clarkson,Evangelos Mazomenos,Danail Stoyanov
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-77] Effective and Efficient Masked Image Generation Models

链接: https://arxiv.org/abs/2503.07197
作者: Zebin You,Jingyang Ou,Xiaolu Zhang,Jun Hu,Jun Zhou,Chongxuan Li
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-78] All That Glitters Is Not Gold: Key-Secured 3D Secrets within 3D Gaussian Splatting

链接: https://arxiv.org/abs/2503.07191
作者: Yan Ren,Shilin Lu,Adams Wai-Kin Kong
机构: Nanyang Technological University (南洋理工大学), Singapore
类目: Graphics (cs.GR); Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-79] Evaluation of Alignment-Regularity Characteristics in Deformable Image Registration

链接: https://arxiv.org/abs/2503.07185
作者: Vasiliki Sideri-Lampretsa,Daniel Rueckert,Huaqi Qiu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-80] owards Spatial Transcriptomics-guided Pathological Image Recognition with Batch-Agnostic Encoder

链接: https://arxiv.org/abs/2503.07173
作者: Kazuya Nishimura,Ryoma Bise,Yasuhiro Kojima
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to ISBI 2025

点击查看摘要

[CV-81] HisTrackMap: Global Vectorized High-Definition Map Construction via History Map Tracking

链接: https://arxiv.org/abs/2503.07168
作者: Jing Yang,Sen Yang,Xiao Tan,Hanli Wang
机构: Tongji University (同济大学); Baidu Inc. (百度公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-82] mporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation

链接: https://arxiv.org/abs/2503.07167
作者: Ziliang Miao,Runjian Chen,Yixi Cai,Buwei He,Wenquan Zhao,Wenqi Shao,Bo Zhang,Fu Zhang
机构: The University of Hong Kong (香港大学); KTH Royal Institute of Technology (瑞典皇家理工学院); Southern University of Science and Technology (南方科技大学); 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:

点击查看摘要

[CV-83] MIRAM: Masked Image Reconstruction Across Multiple Scales for Breast Lesion Risk Prediction

链接: https://arxiv.org/abs/2503.07157
作者: Hung Q. Vo,Pengyu Yuan,Zheng Yin,Kelvin K. Wong,Chika F. Ezeana,Son T. Ly,Stephen T.C. Wong,Hien V. Nguyen
机构: Department of Electrical and Computer Engineering, University of Houston (休斯敦大学电气与计算机工程系); Systems Medicine and Biomedical Engineering, Houston Methodist (休斯敦卫理公会医院系统医学与生物医学工程)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-84] Controllable 3D Outdoor Scene Generation via Scene Graphs

链接: https://arxiv.org/abs/2503.07152
作者: Yuheng Liu,Xinke Li,Yuning Zhang,Lu Qi,Xin Li,Wenping Wang,Chongshou Li,Xueting Li,Ming-Hsuan Yang
机构: Texas A&M University; UC Merced; City University of Hong Kong; Southwest Jiaotong University; Insta360 Research; NVIDIA
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project Page: this https URL

点击查看摘要

[CV-85] VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation CVPR2025

链接: https://arxiv.org/abs/2503.07135
作者: Hanzhi Chen,Boyang Sun,Anran Zhang,Marc Pollefeys,Stefan Leutenegger
机构: Technical University of Munich (慕尼黑工业大学); ETH Zürich (苏黎世联邦理工学院); Microsoft (微软)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to CVPR 2025

点击查看摘要

[CV-86] A Light Perspective for 3D Object Detection

链接: https://arxiv.org/abs/2503.07133
作者: Marcelo Eduardo Pederiva,José Mario De Martino,Alessandro Zimmer
机构: School of Electrical and Computer Engineering, State University of Campinas (巴西坎皮纳斯州立大学电气与计算机工程学院); AImotion Bayern, Technische Hochschule Ingolstadt (德国英戈尔施塔特技术大学AImotion Bayern)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-87] Learning A Zero-shot Occupancy Network from Vision Foundation Models via Self-supervised Adaptation

链接: https://arxiv.org/abs/2503.07125
作者: Sihao Lin,Daqi Liu,Ruochong Fu,Dongrui Liu,Andy Song,Hongwei Xie,Zhihui Li,Bing Wang,Xiaojun Chang
机构: RMIT University (皇家墨尔本理工大学); Xiaomi Auto (小米汽车); Shanghai Jiao Tong University (SJTU) (上海交通大学); University of Science and Technology of China (USTC) (中国科学技术大学); University of Technology Sydney (UTS) (悉尼科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: preprint

点击查看摘要

[CV-88] Exposure Bias Reduction for Enhancing Diffusion Transformer Feature Caching

链接: https://arxiv.org/abs/2503.07120
作者: Zhen Zou,Hu Yu,Jie Xiao,Feng Zhao
机构: University of Science and Technology of China (中国科学技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-89] YOLOMG: Vision-based Drone-to-Drone Detection with Appearance and Pixel-Level Motion Fusion

链接: https://arxiv.org/abs/2503.07115
作者: Hanqing Guo,Xiuxiu Lin,Shiyu Zhao
机构: Department of Artificial Intelligence, Westlake University (西湖大学), Hangzhou, China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages, 8 figures

点击查看摘要

[CV-90] owards Experience Replay for Class-Incremental Learning in Fully-Binary Networks

链接: https://arxiv.org/abs/2503.07107
作者: Yanis Basso-Bert,Anca Molnos,Romain Lemaire,William Guicquero,Antoine Dupret
机构: Univ. Grenoble Alpes (格勒诺布尔阿尔卑斯大学); CEA (法国原子能委员会); List (CEA下属研究机构); Leti (CEA下属研究机构)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-91] SimROD: A Simple Baseline for Raw Object Detection with Global and Local Enhancements

链接: https://arxiv.org/abs/2503.07101
作者: Haiyang Xie,Xi Shen,Shihua Huang,Zheng Wang
机构: National Engineering Research Center for Multimedia Software (多媒体软件国家工程研究中心), School of Computer Science (计算机科学学院), Wuhan University (武汉大学); Intellindust AI Lab (智谱人工智能实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-92] OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation

链接: https://arxiv.org/abs/2503.07098
作者: Ding Zhong,Xu Zheng,Chenfei Liao,Yuanhuiyi Lyu,Jialei Chen,Shengyang Wu,Linfeng Zhang,Xuming Hu
机构: AI Thrust, HKUST(GZ) (香港科技大学（广州）); CSE, HKUST (香港科技大学); UMich (密歇根大学); INSAIT (未知); Nagoya University (名古屋大学); SJTU (上海交通大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-93] FaceID-6M: A Large-Scale Open-Source FaceID Customization Dataset

链接: https://arxiv.org/abs/2503.07091
作者: Shuhe Wang,Xiaoya Li,Jiwei Li,Guoyin Wang,Xiaofei Sun,Bob Zhu,Han Qiu,Mo Yu,Shengjie Shen,Eduard Hovy
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-94] RS2V-L: Vehicle-Mounted LiDAR Data Generation from Roadside Sensor Observations

链接: https://arxiv.org/abs/2503.07085
作者: Ruidan Xing,Runyi Huang,Qing Xu,Lei He
机构: School of Vehicle and Mobility, Tsinghua University (清华大学车辆与运载学院); State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University (清华大学智能绿色车辆与交通重点实验室); School of Instrumentation and Optoelectronic Engineering, BeiHang University (北京航空航天大学仪器光电工程学院); Department of Automation, Tsinghua University (清华大学自动化系); National Key R&D Program of China (中国国家关键研发计划)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注: 7 pages, 4 figures

点击查看摘要

[CV-95] On the Generalization of Representation Uncertainty in Earth Observation

链接: https://arxiv.org/abs/2503.07082
作者: Spyros Kondylatos,Nikolaos Ioannis Bountos,Dimitrios Michail,Xiao Xiang Zhu,Gustau Camps-Valls,Ioannis Papoutsis
机构: Orion Lab, National Observatory of Athens & National Technical University of Athens (奥赖昂实验室, 雅典国家天文台 & 雅典国立技术大学); Image Processing Laboratory (IPL), Universitat de València (图像处理实验室, 瓦伦西亚大学); Harokopio University of Athens (哈罗科皮奥斯大学); Data Science in Earth Observation, Technical University of Munich (地球观测数据科学, 慕尼黑工业大学); Munich Center for Machine Learning (慕尼黑机器学习中心)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 18 pages

点击查看摘要

[CV-96] NFIG: Autoregressive Image Generation with Next-Frequency Prediction

链接: https://arxiv.org/abs/2503.07076
作者: Zhihao Huang,Xi Qiu,Yukuo Ma,Yifu Zhou,Chi Zhang,Xuelong Li
机构: Northwestern Polytechnical University (西北工业大学); TeleAI; Beihang University (北京航空航天大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 10 pages, 7 figures, 2 tables

点击查看摘要

[CV-97] XR-VLM: Cross-Relationship Modeling with Multi-part Prompts and Visual Features for Fine-Grained Recognition

链接: https://arxiv.org/abs/2503.07075
作者: Chuanming Wang,Henming Mao,Huanhuan Zhang,Huiyuan Fu,Huadong Ma
机构: The State Key Laboratory of Networking and Switching Technology (网络与交换技术国家重点实验室), Beijing University of Posts and Telecommunications (北京邮电大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-98] Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning

链接: https://arxiv.org/abs/2503.07065
作者: Huilin Deng,Ding Zou,Rui Ma,Hongchen Luo,Yang Cao,Yu Kang
机构: School of Information Science and Technology, University of Science and Technology of China (中国科学技术大学); Intelligent System Department, Zhongxing Telecom Equipment(ZTE) (中兴通讯股份有限公司); Northeastern University (东北大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-99] Breaking the Limits of Quantization-Aware Defenses: QADT-R for Robustness Against Patch-Based Adversarial Attacks in QNNs

链接: https://arxiv.org/abs/2503.07058
作者: Amira Guesmi,Bassem Ouni,Muhammad Shafique
机构: NYU Abu Dhabi (纽约大学阿布扎比分校); Technology Innovation Institute (技术创新研究所); NYU Abu Dhabi (纽约大学阿布扎比分校)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-100] IDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation

链接: https://arxiv.org/abs/2503.07050
作者: Victor Shea-Jay Huang,Le Zhuo,Yi Xin,Zhaokai Wang,Peng Gao,Hongsheng Li
机构: CUHK (香港中文大学); Shanghai AI Laboratory (上海人工智能实验室); NJU (南京大学); SJTU (上海交通大学)
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-101] Recovering Partially Corrupted Major Objects through Tri-modality Based Image Completion

链接: https://arxiv.org/abs/2503.07047
作者: Yongle Zhang,Yimin Liu,Qiang Wu
机构: University of Technology Sydney (悉尼科技大学), Australia; Hefei University of Technology (合肥工业大学), China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 17 pages, 6 page supplementary

点击查看摘要

[CV-102] MambaFlow: A Mamba-Centric Architecture for End-to-End Optical Flow Estimation

链接: https://arxiv.org/abs/2503.07046
作者: Juntian Du,Yuan Sun,Zhihu Zhou,Pinyi Chen,Runzhe Zhang,Keji Mao
机构: College of Computer Science and Technology College of Software, Zhejiang University of Technology (浙江工业大学), China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-103] Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimization

链接: https://arxiv.org/abs/2503.07038
作者: Mihcael Green,Matan Levy,Issar Tzachor,Dvir Samuel,Nir Darshan,Rami Ben-Ari
机构: OriginAI (OriginAI); The Hebrew University of Jerusalem (希伯来大学); Bar-Ilan University (巴伊兰大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-104] Zero-Shot Hashing Based on Reconstruction With Part Alignment

链接: https://arxiv.org/abs/2503.07037
作者: Yan Jiang,Zhongmiao Qi,Jianhao Li,Jiangbo Qian,Chong Wang,Yu Xin
机构: Faculty of Electrical Engineering and Computer Science, and Merchants’ Guild Economics and Cultural Intelligent Computing Laboratory, Ningbo University (宁波大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Information Retrieval (cs.IR)
备注:

点击查看摘要

[CV-105] Universal Incremental Learning: Mitigating Confusion from Inter- and Intra-task Distribution Randomness

链接: https://arxiv.org/abs/2503.07035
作者: Sheng Luo,Yi Zhou,Tao Zhou
机构: School of Computer Science and Engineering, Southeast University (东南大学); Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education (教育部), China; Nanjing University of Science and Technology (南京理工大学), Nanjing (南京), China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 4 figures, 4 tables

点击查看摘要

[CV-106] Learning a Unified Degradation-aware Representation Model for Multi-modal Image Fusion

链接: https://arxiv.org/abs/2503.07033
作者: Haolong Ma,Hui Li,Chunyang Cheng,Zeyang Zhang,Xiaoning Song,Xiao-Jun Wu
机构: Jiangnan University (江南大学); Jiangsu University of Science and Technology (江苏科技大学); Jiangnan University (江南大学); Jiangnan University (江南大学); Jiangnan University (江南大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-107] Availability-aware Sensor Fusion via Unified Canonical Space for 4D Radar LiDAR and Camera

链接: https://arxiv.org/abs/2503.07029
作者: Dong-Hee Paek,Seung-Hyun Kong
机构: CCS Graduate School of Mobility (CCS 移动研究生院); KAIST (韩国科学技术院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Arxiv preprint

点击查看摘要

[CV-108] EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer

链接: https://arxiv.org/abs/2503.07027
作者: Yuxuan Zhang,Yirui Yuan,Yiren Song,Haofan Wang,Jiaming Liu
机构: Tiamat AI; ShanghaiTech University (上海科技大学); National University of Singapore (新加坡国立大学); Liblib AI
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-109] Erase Diffusion: Empowering Object Removal Through Calibrating Diffusion Pathways CVPR2025

链接: https://arxiv.org/abs/2503.07026
作者: Yi Liu,Hao Zhou,Wenxiang Shang,Ran Lin,Benlei Cui
机构: Alibaba Group (阿里巴巴集团)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: accepted by CVPR 2025

点击查看摘要

[CV-110] HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions

链接: https://arxiv.org/abs/2503.07019
作者: Keyu Du,Hao Xu,Haipeng Li,Hong Qu,Chi-Wing Fu,Shuaicheng Liu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 2025, Association for the Advancement of Artificial Intelligence

点击查看摘要

[CV-111] SDFA: Structure Aware Discriminative Feature Aggregation for Efficient Human Fall Detection in Video

链接: https://arxiv.org/abs/2503.07008
作者: Sania Zahan,Ghulam Mubashar Hassan,Ajmal Mian
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Published IEEE Transactions on Industrial Informatics

点击查看摘要

[CV-112] NukesFormers: Unpaired Hyperspectral Image Generation with Non-Uniform Domain Alignment

链接: https://arxiv.org/abs/2503.07004
作者: Jiaojiao Li,Shiyao Duan,Haitao XU,Rui Song
机构: Xidian University (西安电子科技大学); National Space Science Center, Chinese Academy of Sciences (中国科学院国家空间科学中心)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-113] aking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue Learning

链接: https://arxiv.org/abs/2503.07002
作者: Jiazheng Liu,Sipeng Zheng,Börje F. Karlsson,Zongqing Lu
机构: School of Computer Science, Peking University (北京大学); Beijing Academy of Artificial Intelligence (北京人工智能研究院); BAAI (北京人工智能研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-114] Frequency-Aware Density Control via Reparameterization for High-Quality Rendering of 3D Gaussian Splatting AAAI2025

链接: https://arxiv.org/abs/2503.07000
作者: Zhaojie Zeng,Yuesong Wang,Lili Ju,Tao Guan
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to AAAI2025

点击查看摘要

[CV-115] SOYO: A Tuning-Free Approach for Video Style Morphing via Style-Adaptive Interpolation in Diffusion Models

链接: https://arxiv.org/abs/2503.06998
作者: Haoyu Zheng,Qifan Yu,Binghe Yu,Yang Dai,Wenqiao Zhang,Juncheng Li,Siliang Tang,Yueting Zhuang
机构: Zhejiang University (浙江大学); University of Electronic Science and Technology of China (电子科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-116] Public space security management using digital twin technologies

链接: https://arxiv.org/abs/2503.06996
作者: Stylianos Zindros,Christos Chronis,Panagiotis Radoglou-Grammatikis,Vasileios Argyriou,Panagiotis Sarigiannidis,Iraklis Varlamis,Georgios Th. Papadopoulos
机构: Department of Informatics and Telematics, Harokopio University of Athens (哈罗科皮奥雅典大学), Greece; Department of Electrical and Computer Engineering, University of Western Macedonia (西方马其顿大学), Greece; Department of Networks and Digital Media, Kingston University (金斯顿大学), United Kingdom
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-117] CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language Model

链接: https://arxiv.org/abs/2503.06993
作者: Shihao Hou,Xinyi Shang,Shreyank N Gowda,Yang Lu,Chao Wu,Yan Yan,Hanzi Wang
机构: Xiamen University (厦门大学); University College London (伦敦大学学院); University of Nottingham (诺丁汉大学); Zhejiang University (浙江大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-118] Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow

链接: https://arxiv.org/abs/2503.06992
作者: Hanyu Zhou,Haonan Wang,Haoyue Liu,Yuxing Duan,Yi Chang,Luxin Yan
机构: National Key Lab of Multispectral Information Intelligent Processing Technology (多光谱信息智能处理技术国家重点实验室), School of Artificial Intelligence and Automation (人工智能与自动化学院), Huazhong University of Science and Technology (华中科技大学); School of Computing (计算学院), National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-119] Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols

链接: https://arxiv.org/abs/2503.06991
作者: Yongwoo Kim,Sungmin Cha,Donghyun Kim
机构: Korea University (韩国大学); New York University (纽约大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-120] Utilizing Jailbreak Probability to Attack and Safeguard Multimodal LLM s

链接: https://arxiv.org/abs/2503.06989
作者: Wenzhuo Xu,Zhipeng Wei,Xiongtao Sun,Deyue Zhang,Dongdong Yang,Quanchen Zou,Xiangzheng Zhang
机构: 360 AI Security Lab; International Computer Science Institute (国际计算机科学研究所); Xidian University (西安电子科技大学)
类目: Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-121] ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud Restoration

链接: https://arxiv.org/abs/2503.06986
作者: Youngseok Kim,Sunwook Hwang,Hyung-Sin Kim,Saewoong Bahk
机构: Department of Electrical and Computer Engineering, Seoul National University (首尔国立大学); System LSI, Samsung Electronics (三星电子); Graduate School of Data Science, Seoul National University (首尔国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-122] Synchronized Video-to-Audio Generation via Mel Quantization-Continuum Decomposition CVPR-25

链接: https://arxiv.org/abs/2503.06984
作者: Juncheng Wang,Chao Xu,Cheng Yu,Lei Shang,Zhe Hu,Shujun Wang,Liefeng Bo
机构: The Hong Kong Polytechnic University (香港理工大学); Tongyi Lab, Alibaba Group (通义实验室, 阿里巴巴集团)
类目: ound (cs.SD); Computer Vision and Pattern Recognition (cs.CV); Audio and Speech Processing (eess.AS)
备注: Accepted to CVPR-25

点击查看摘要

[CV-123] Griffin: Aerial-Ground Cooperative Detection and Tracking Dataset and Benchmark IROS2025

链接: https://arxiv.org/abs/2503.06983
作者: Jiahao Wang,Xiangyu Cao,Jiaru Zhong,Yuner Zhang,Haibao Yu,Lei He,Shaobing Xu
机构: School of Vehicle and Mobility, Tsinghua University (清华大学车辆与运载学院); Xingjian College, Tsinghua University (清华大学行健书院); School of Mechanical Engineering, Beijing Institute of Technology (北京理工大学机械工程学院); Faculty of Electrical and Systems Engineering, University of Pennsylvania (宾夕法尼亚大学电气与系统工程学院); Department of Computer Science, The University of Hong Kong (香港大学计算机科学系)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: 8 pages, 7 figures. This work has been submitted to IROS 2025 for possible publication

点击查看摘要

[CV-124] Lightweight Multimodal Artificial Intelligence Framework for Maritime Multi-Scene Recognition

链接: https://arxiv.org/abs/2503.06978
作者: Xinyu Xi,Hua Yang,Shentai Zhang,Yijie Liu,Sijin Sun,Xiuju Fu
机构: Shanghai Maritime University (上海海事大学); National University of Singapore (新加坡国立大学); Institute of High Performance Computing, ASTAR (高性能计算研究所，ASTAR)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Robotics (cs.RO)
备注: 19 pages, 4 figures, submitted to Engineering Applications of Artificial Intelligence

点击查看摘要

[CV-125] ask-Specific Knowledge Distillation from the Vision Foundation Model for Enhanced Medical Image Segmentation

链接: https://arxiv.org/abs/2503.06976
作者: Pengchen Liang,Haishan Huang,Bin Pu,Jianguo Chen,Xiang Hua,Jing Zhang,Weibo Ma,Zhuangzhuang Chen,Yiwei Li,Qing Chang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 29 pages, 10 figures, 16 tables

点击查看摘要

[CV-126] Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment AAAI

链接: https://arxiv.org/abs/2503.06974
作者: Yang Liu,Mengyuan Liu,Shudong Huang,Jiancheng Lv
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages, 5 figures, The 39th Annual AAAI Conference on Artificial Intelligence

点击查看摘要

[CV-127] A Multimodal Benchmark Dataset and Model for Crop Disease Diagnosis ECCV2024

链接: https://arxiv.org/abs/2503.06973
作者: Xiang Liu,Zhaoxiang Liu,Huan Hu,Zezhou Chen,Kohou Wang,Kai Wang,Shiguo Lian
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Accepted by ECCV 2024 (14 pages, 8 figures)

点击查看摘要

[CV-128] MIGA: Mutual Information-Guided Attack on Denoising Models for Semantic Manipulation

链接: https://arxiv.org/abs/2503.06966
作者: Guanghao Li,Mingzhi Chen,Hao Yu,Shuting Dong,Wenhao Jiang,Ming Tang,Chun Yuan
机构: SIGS, Tsinghua University (清华大学交叉信息研究院); Southern University of Science and Technology (南方科技大学); Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) (深圳人工智能与数字经济广东省实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-129] SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks

链接: https://arxiv.org/abs/2503.06965
作者: Shining Wang,Yunlong Wang,Ruiqi Wu,Bingliang Jiao,Wenxuan Wang,Peng Wang
机构: School of Computer Science, Northwestern Polytechnical University (西北工业大学计算机学院), Ningbo Institute, Northwestern Polytechnical University (宁波研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-130] A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning CVPR2025

链接: https://arxiv.org/abs/2503.06960
作者: Xin Wen,Bingchen Zhao,Yilun Chen,Jiangmiao Pang,Xiaojuan Qi
机构: The University of Hong Kong (香港大学); University of Edinburgh (爱丁堡大学); 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: Accepted by CVPR 2025

点击查看摘要

[CV-131] LatexBlend: Scaling Multi-concept Customized Generation with Latent Textual Blending CVPR2025

链接: https://arxiv.org/abs/2503.06956
作者: Jian Jin,Zhenbo Yu,Yang Shen,Zhenyong Fu,Jian Yang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: cvpr2025

点击查看摘要

[CV-132] Motion Anything: Any to Motion Generation

链接: https://arxiv.org/abs/2503.06955
作者: Zeyu Zhang,Yiran Wang,Wei Mao,Danning Li,Rui Zhao,Biao Wu,Zirui Song,Bohan Zhuang,Ian Reid,Richard Hartley
机构: ANU (澳大利亚国立大学); USYD (悉尼大学); Tencent (腾讯); McGill (麦吉尔大学); JD.com (京东); UTS (悉尼科技大学); MBZUAI (穆罕默德·本·扎耶德人工智能大学); ZJU (浙江大学); Google (谷歌)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-133] Approximate Size Targets Are Sufficient for Accurate Semantic Segmentation

链接: https://arxiv.org/abs/2503.06954
作者: Xingye Fan,Zhongwen(Rex)Zhang,Yuri Boykov
机构: University of Waterloo (滑铁卢大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-134] Large Language Model Guided Progressive Feature Alignment for Multimodal UAV Object Detection

链接: https://arxiv.org/abs/2503.06948
作者: Wentao Wu,Chenglong Li,Xiao Wang,Bin Luo,Qi Liu
机构: School of Artificial Intelligence, Anhui University, Hefei, China (安徽大学人工智能学院，合肥，中国); School of Computer Science and Technology, Anhui University, Hefei, China (安徽大学计算机科学与技术学院，合肥，中国); University of Science and Technology of China, Hefei, China (中国科学技术大学，合肥，中国)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-135] Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitives

链接: https://arxiv.org/abs/2503.06947
作者: Jiaxin Li,Hongxing Wang,Jiawei Tan,Zhilong Ou,Junsong Yuan
机构: School of Big Data and Software Engineering, Chongqing University (重庆大学), China; Department of Computer Science and Engineering, State University of New York at Buffalo (纽约州立大学布法罗分校), USA
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 15 pages, 15 figures, 8 tables

点击查看摘要

[CV-136] CineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processing

链接: https://arxiv.org/abs/2503.06940
作者: Jianxiong Gao,Yichang Liu,Baofeng Yang,Jianfeng Feng,Yanwei Fu
机构: Fudan University (复旦大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 14 pages, 13 figures

点击查看摘要

[CV-137] Modeling Human Skeleton Joint Dynamics for Fall Detection

链接: https://arxiv.org/abs/2503.06938
作者: Sania Zahan,Ghulam Mubashar Hassan,Ajmal Mian
机构: The University of Western Australia (西澳大利亚大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Published in 2021 Digital Image Computing: Techniques and Applications (DICTA)

点击查看摘要

[CV-138] LLaFEA: Frame-Event Complementary Fusion for Fine-Grained Spatiotemporal Understanding in LMMs

链接: https://arxiv.org/abs/2503.06934
作者: Hanyu Zhou,Gim Hee Lee
机构: 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)
备注:

点击查看摘要

[CV-139] Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping

链接: https://arxiv.org/abs/2503.06930
作者: Ning Ding,Jing Han,Yuchuan Tian,Chao Xu,Kai Han,Yehui Tang
机构: State Key Lab of General AI, School of Intelligence Science and Technology, Peking University (北京大学); School of Artificial Intelligence, Beijing University of Posts and Telecommunications (北京邮电大学); Huawei Noah’s Ark Lab. (华为诺亚方舟实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-140] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers

链接: https://arxiv.org/abs/2503.06923
作者: Jiacheng Liu,Chang Zou,Yuanhuiyi Lyu,Junjie Chen,Linfeng Zhang
机构: Shanghai Jiao Tong University (上海交通大学); Shandong University (山东大学); University of Electronic Science and Technology of China (电子科技大学); The Hong Kong University of Science and Technology (香港科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 13 pages, 14 figures

点击查看摘要

[CV-141] When Lighting Deceives: Exposing Vision-Language Models Illumination Vulnerability Through Illumination Transformation Attack

链接: https://arxiv.org/abs/2503.06903
作者: Hanqing Liu,Shouwei Ruan,Yao Huang,Shiji Zhao,Xingxing Wei
机构: Institute of Artificial Intelligence, Beihang University (北航人工智能学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-142] Iterative Prompt Relocation for Distribution-Adaptive Visual Prompt Tuning

链接: https://arxiv.org/abs/2503.06901
作者: Chikai Shang,Mengke Li,Yiqun Zhang,Zhen Chen,Jinlin Wu,Fangqing Gu,Yang Lu,Yiu-ming Cheung
机构: Guangdong University of Technology; Shenzhen University; Yale University; Chinese Academy of Sciences; Xiamen University; Hong Kong Baptist University
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-143] DirectTriGS: Triplane-based Gaussian Splatting Field Representation for 3D Generation CVPR2025

链接: https://arxiv.org/abs/2503.06900
作者: Xiaoliang Ju,Hongsheng Li
机构: CUHK MMLab (香港中文大学多媒体实验室); CPII under InnoHK (InnoHK 创新香港研发平台)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025

点击查看摘要

[CV-144] Illuminating Darkness: Enhancing Real-world Low-light Scenes with Smartphone Images

链接: https://arxiv.org/abs/2503.06898
作者: S M A Sharif,Abdur Rehman,Zain Ul Abidin,Rizwan Ali Naqvi,Fayaz Ali Dharejo,Radu Timofte
机构: Opt-AI Inc. (Opt-AI Inc.); Sejong University (世宗大学); University of Wurzburg (维尔茨堡大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-145] HiSTF Mamba: Hierarchical Spatiotemporal Fusion with Multi-Granular Body-Spatial Modeling for High-Fidelity Text-to-Motion Generation

链接: https://arxiv.org/abs/2503.06897
作者: Xingzu Zhan,Chen Xie,Haoran Sun,Xiaochun Mai
机构: Shenzhen University (深圳大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 11pages,3figures,

点击查看摘要

[CV-146] CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution CVPR2025

链接: https://arxiv.org/abs/2503.06896
作者: Xin Liu,Jie Liu,Jie Tang,Gangshan Wu
机构: State Key Laboratory for Novel Software Technology, Nanjing University (南京大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR2025

点击查看摘要

[CV-147] Improving cognitive diagnostics in pathology: a deep learning approach for augmenting perceptional understanding of histopathology images

链接: https://arxiv.org/abs/2503.06894
作者: Xiaoqian Hu
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-148] Accessing the Effect of Phyllotaxy and Planting Density on Light Use Efficiency in Field-Grown Maize using 3D Reconstructions

链接: https://arxiv.org/abs/2503.06887
作者: Nasla Saleem,Talukder Zaki Jubery,Aditya Balu,Yan Zhou,Yawei Li,Patrick S. Schnable,Adarsh Krishnamurthy,Baskar Ganapathysubramanian
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 17 pages, 8 figures

点击查看摘要

[CV-149] ProBench: Judging Multimodal Foundation Models on Open-ended Multi-domain Expert Tasks

链接: https://arxiv.org/abs/2503.06885
作者: Yan Yang,Dongxu Li,Haoning Wu,Bei Chen,Liu Liu,Liyuan Pan,Junnan Li
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-150] xt-to-Image Diffusion Models Cannot Count and Prompt Refinement Cannot Help

链接: https://arxiv.org/abs/2503.06884
作者: Yuefan Cao,Xuyang Guo,Jiayan Huo,Yingyu Liang,Zhenmei Shi,Zhao Song,Jiahao Zhang,Zhen Zhuang
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-151] Interactive Medical Image Analysis with Concept-based Similarity Reasoning CVPR2025

链接: https://arxiv.org/abs/2503.06873
作者: Ta Duc Huy,Sen Kim Tran,Phan Nguyen,Nguyen Hoang Tran,Tran Bao Sam,Anton van den Hengel,Zhibin Liao,Johan W. Verjans,Minh-Son To,Vu Minh Hieu Phan
机构: Australian Institute for Machine Learning (澳大利亚机器学习研究所), The University of Adelaide (阿德莱德大学); Flinders University (弗林德斯大学); NVIDIA
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Accepted CVPR2025

点击查看摘要

[CV-152] HIF: Height Interval Filtering for Efficient Dynamic Points Removal

链接: https://arxiv.org/abs/2503.06863
作者: Shufang Zhang,Tao Jiang,Jiazheng Wu,Ziyu Meng,Ziyang Zhang,Shan An
机构: School of Electrical and Information Engineering, Tianjin University (天津大学), China; School of Control Science and Engineering, Shandong University (山东大学), China
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-153] owards Generalization of Tactile Image Generation: Reference-Free Evaluation in a Leakage-Free Setting

链接: https://arxiv.org/abs/2503.06860
作者: Cagri Gungor,Derek Eppinger,Adriana Kovashka
机构: University of Pittsburgh (匹兹堡大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-154] ActiveInitSplat: How Active Image Selection Helps Gaussian Splatting

链接: https://arxiv.org/abs/2503.06859
作者: Konstantinos D. Polyzos,Athanasios Bacharis,Saketh Madhuvarasu,Nikos Papanikolopoulos,Tara Javidi
机构: University of California San Diego (加州大学圣地亚哥分校); University of Minnesota (明尼苏达大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-155] From Image- to Pixel-level: Label-efficient Hyperspectral Image Reconstruction

链接: https://arxiv.org/abs/2503.06852
作者: Yihong Leng,Jiaojiao Li,Haitao Xu,Rui Song
机构: Xidian University (西安电子科技大学); National Satellite Meteorological Center (国家卫星气象中心)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-156] MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification

链接: https://arxiv.org/abs/2503.06847
作者: Xiangyan Qu,Jing Yu,Jiamin Zhuang,Gaopeng Gou,Gang Xiong,Qi Wu
机构: Institute of Information Engineering, Chinese Academy of Sciences, China (中国科学院信息工程研究所); School of Cyber Security, University of Chinese Academy of Sciences, China (中国科学院大学网络空间安全学院); School of Information Engineering, Minzu University of China, Beijing, China (中央民族大学信息工程学院); Australia Centre for Robotic Vision (ACRV), the University of Adelaide (澳大利亚机器人视觉中心)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-157] Improving Visual Place Recognition with Sequence-Matching Receptiveness Prediction

链接: https://arxiv.org/abs/2503.06840
作者: Somayeh Hussaini,Tobias Fischer,Michael Milford
机构: The authors are with the QUT Centre for Robotics, School of Electrical Engineering and Robotics, Queensland University of Technology (昆士兰科技大学), Brisbane, QLD 4000, Australia.
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 5 figures, under review

点击查看摘要

[CV-158] AttFC: Attention Fully-Connected Layer for Large-Scale Face Recognition with One GPU

链接: https://arxiv.org/abs/2503.06839
作者: Zhuowen Zheng,Yain-Whar Si,Xiaochen Yuan,Junwei Duan,Ke Wang,Xiaofan Li,Xinyuan Zhang,Xueyuan Gong
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-159] GUIDE-CoT: Goal-driven and User-Informed Dynamic Estimation for Pedestrian Trajectory using Chain-of-Thought AAMAS2025

链接: https://arxiv.org/abs/2503.06832
作者: Sungsik Kim,Janghyun Baek,Jinkyu Kim,Jaekoo Lee
机构: Korea University (高丽大学); Kookmin University (国民大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 5 figures, will be published on The 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025)

点击查看摘要

[CV-160] One-Shot Dual-Arm Imitation Learning WWW ICRA2025

链接: https://arxiv.org/abs/2503.06831
作者: Yilong Wang,Edward Johns
机构: The Robot Learning Lab at Imperial College London (帝国理工学院机器人学习实验室)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at ICRA 2025. Project Webpage: this https URL

点击查看摘要

[CV-161] HierDAMap: Towards Universal Domain Adaptive BEV Mapping via Hierarchical Perspective Priors

链接: https://arxiv.org/abs/2503.06821
作者: Siyu Li,Yihong Cao,Hao Shi,Yongsheng Zang,Xuan He,Kailun Yang,Zhiyong Li
机构: School of Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University (湖南大学), Changsha 410082, China (邮件: zhiyong.li@hnu.edu.cn; kailun.yang@hnu.edu.cn); State Key Laboratory of Extreme Photonics and Instrumentation, Zhejiang University (浙江大学), Hangzhou 310027, China; College of Computer Science and Electronic Engineering, Hunan University (湖南大学), Changsha 410082, China; Hunan Vanguard Group Corporation Limited (湖南先锋集团有限公司), Changsha 410100, China
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO); Image and Video Processing (eess.IV)
备注: The source code will be made publicly available at this https URL

点击查看摘要

[CV-162] owards Fine-Grained Video Question Answering

链接: https://arxiv.org/abs/2503.06820
作者: Wei Dai,Alan Luo,Zane Durante,Debadutta Dash,Arnold Milstein,Kevin Schulman,Ehsan Adeli,Li Fei-Fei
机构: Stanford University (斯坦福大学)
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-163] Sub-Image Recapture for Multi-View 3D Reconstruction

链接: https://arxiv.org/abs/2503.06818
作者: Yanwei Wang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 5 pages, 4 figures

点击查看摘要

[CV-164] Unlocking Generalization for Robotics via Modularity and Scale

链接: https://arxiv.org/abs/2503.06814
作者: Murtaza Dalal
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: CMU Robotics PhD Thesis, 185 pages

点击查看摘要

[CV-165] Multimodal Emotion Recognition and Sentiment Analysis in Multi-Party Conversation Contexts

链接: https://arxiv.org/abs/2503.06805
作者: Aref Farhadipour,Hossein Ranjbar,Masoumeh Chapariniya,Teodora Vukovic,Sarah Ebling,Volker Dellwo
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Sound (cs.SD); Audio and Speech Processing (eess.AS)
备注: 5 pages

点击查看摘要

[CV-166] VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation

链接: https://arxiv.org/abs/2503.06800
作者: Hritik Bansal,Clark Peng,Yonatan Bitton,Roman Goldenberg,Aditya Grover,Kai-Wei Chang
机构: University of California Los Angeles (加州大学洛杉矶分校); Google Research (谷歌研究)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 41 pages, 33 Figures

点击查看摘要

[CV-167] Robotic Ultrasound-Guided Femoral Artery Reconstruction of Anatomically-Representative Phantoms

链接: https://arxiv.org/abs/2503.06795
作者: Lidia Al-Zogbi,Deepak Raina,Vinciya Pandian,Thorsten Fleiter,Axel Krieger
机构: Department of Mechanical Engineering and the Laboratory of Computational Sensing and Robotics, Johns Hopkins University (约翰斯·霍普金斯大学); Malone Center for Engineering in Healthcare, Whiting School of Engineering, Johns Hopkins University (约翰斯·霍普金斯大学); Ross and Carol Nese College of Nursing, Pennsylvania State University (宾夕法尼亚州立大学); R. Cowley Shock Trauma Center, Department of Diagnostic Radiology, School of Medicine, University of Maryland (马里兰大学)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-168] GenDR: Lightning Generative Detail Restorator

链接: https://arxiv.org/abs/2503.06790
作者: Yan Wang,Shijie Zhao,Kai Chen,Kexin Zhang,Junlin Li,Li Zhang
机构: Bytedance Inc. (字节跳动)
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-169] Infinite Leagues Under the Sea: Photorealistic 3D Underwater Terrain Generation by Latent Fractal Diffusion Models

链接: https://arxiv.org/abs/2503.06784
作者: Tianyi Zhang,Weiming Zhi,Joshua Mangelson,Matthew Johnson-Roberson
机构: Carnegie Mellon University (卡内基梅隆大学); Brigham Young University (杨百翰大学)
类目: Graphics (cs.GR); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Robotics (cs.RO)
备注: 10 pages

点击查看摘要

[CV-170] Investigating Image Manifolds of 3D Objects: Learning Shape Analysis and Comparisons

链接: https://arxiv.org/abs/2503.06773
作者: Benjamin Beaudett,Shenyuan Liang,Anuj Srivastava
机构: Florida State University (佛罗里达州立大学); Florida State University (佛罗里达州立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-171] SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and Generation

链接: https://arxiv.org/abs/2503.06764
作者: Zisheng Chen,Chunwei Wang,Xiuwei Chen,Hang Xu,Jianhua Han,Xiandan Liang
机构: Sun Yat-sen University (中山大学); Huawei Noah’s Ark Lab (华为诺亚方舟实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Under Review

点击查看摘要

[CV-172] Gaussian RBFNet: Gaussian Radial Basis Functions for Fast and Accurate Representation and Reconstruction of Neural Fields

链接: https://arxiv.org/abs/2503.06762
作者: Abdelaziz Bouzidi,Hamid Laga,Hazem Wannous
机构: School of Information Technology, Murdoch University (澳大利亚默多克大学); IMT Nord Europe (法国); School of Information Technology, Murdoch University (澳大利亚默多克大学); IMT Nord Europe (法国)
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-173] Revisiting Invariant Learning for Out-of-Domain Generalization on Multi-Site Mammogram Datasets

链接: https://arxiv.org/abs/2503.06759
作者: Hung Q. Vo,Samira Zare,Son T. Ly,Lin Wang,Chika F. Ezeana,Xiaohui Yu,Kelvin K. Wong,Stephen T.C. Wong,Hien V. Nguyen
机构: Department of Electrical and Computer Engineering, University of Houston (电气与计算机工程系, 休斯敦大学); Department of Systems Medicine and Biomedical Engineering, Houston Methodist Cancer Center (系统医学与生物医学工程系, 休斯敦卫理公会癌症中心)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-174] DiffAtlas: GenAI-fying Atlas Segmentation via Image-Mask Diffusion

链接: https://arxiv.org/abs/2503.06748
作者: Hantao Zhang,Yuhe Liu,Jiancheng Yang,Weidong Guo,Xinyuan Wang,Pascal Fua
机构: EPFL (瑞士联邦理工学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 11 pages

点击查看摘要

[CV-175] Color Alignment in Diffusion CVPR2025

链接: https://arxiv.org/abs/2503.06746
作者: Ka Chun Shum,Binh-Son Hua,Duc Thanh Nguyen,Sai-Kit Yeung
机构: Hong Kong University of Science and Technology (香港科技大学); Trinity College Dublin (都柏林圣三一大学); Deakin University (迪肯大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: CVPR 2025

点击查看摘要

[CV-176] CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving

链接: https://arxiv.org/abs/2503.06744
作者: Rui Song,Chenwei Liang,Yan Xia,Walter Zimmer,Hu Cao,Holger Caesar,Andreas Festag,Alois Knoll
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-177] D3DR: Lighting-Aware Object Insertion in Gaussian Splatting

链接: https://arxiv.org/abs/2503.06740
作者: Vsevolod Skorokhodov,Nikita Durasov,Pascal Fua
机构: EPFL (洛桑联邦理工学院), Lausanne, Switzerland (瑞士)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-178] Continuous Online Adaptation Driven by User Interaction for Medical Image Segmentation

链接: https://arxiv.org/abs/2503.06717
作者: Wentian Xu,Ziyun Liang,Harry Anthony,Yasin Ibrahim,Felix Cohen,Guang Yang,Daniel Whitehouse,David Menon,Virginia Newcombe,Konstantinos Kamnitsas
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-179] MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation

链接: https://arxiv.org/abs/2503.06700
作者: Chenfei Liao,Xu Zheng,Yuanhuiyi Lyu,Haiwei Xue,Yihong Cao,Jiawen Wang,Kailun Yang,Xuming Hu
机构: AI Thrust, HKUST(GZ)(香港科技大学(广州)); CSE, HKUST (香港科技大学); INSAIT (未知); Tsinghua (清华大学); HNU (未知); CUMTB (中国矿业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-180] Unsupervised Multi-Clustering and Decision-Making Strategies for 4D-STEM Orientation Mapping

链接: https://arxiv.org/abs/2503.06699
作者: Junhao Cao,Nicolas Folastre,Gozde Oney,Edgar Rauch,Stavros Nicolopoulos,Partha Pratim Das,Arnaud Demortière
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注: 32 pages, 5 figures, 5 figures in SI

点击查看摘要

[CV-181] Whats in a Latent? Leverag ing Diffusion Latent Space for Domain Generalization

链接: https://arxiv.org/abs/2503.06698
作者: Xavier Thomas,Deepti Ghadiyaram
机构: Boston University (波士顿大学); Runway (Runway)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-182] Asymmetric Decision-Making in Online Knowledge Distillation:Unifying Consensus and Divergence

链接: https://arxiv.org/abs/2503.06685
作者: Zhaowei Chen,Borui Zhao,Yuchen Ge,Yuhao Chen,Renjie Song,Jiajun Liang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-183] PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation

链接: https://arxiv.org/abs/2503.06684
作者: Yanjie Pan,Qingdong He,Zhengkai Jiang,Pengcheng Xu,Chaoyi Wang,Jinlong Peng,Haoxuan Wang,Yun Cao,Zhenye Gan,Mingmin Chi,Bo Peng,Yabiao Wang
机构: Fudan University (复旦大学); Youtu Lab, Tencent (腾讯互娱AILab); Hong Kong University of Science and Technology (香港科技大学); Western University (西方大学); University of Chinese Academy of Sciences (中国科学院大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-184] Dynamic Dictionary Learning for Remote Sensing Image Segmentation

链接: https://arxiv.org/abs/2503.06683
作者: Xuechao Zou,Yue Li,Shun Zhang,Kai Li,Shiying Wang,Pin Tao,Junliang Xing,Congyan Lang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-185] Gamma: Toward Generic Image Assessment with Mixture of Assessment Experts

链接: https://arxiv.org/abs/2503.06678
作者: Hantao Zhou,Rui Yang,Longxiang Tang,Guanyi Qin,Yan Zhang,Runze Hu,Xiu Li
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-186] REArtGS: Reconstructing and Generating Articulated Objects via 3D Gaussian Splatting with Geometric and Motion Constraints

链接: https://arxiv.org/abs/2503.06677
作者: Di Wu,Liu Liu,Zhou Linli,Anran Huang,Liangtu Song,Qiaojun Yu,Qi Wu,Cewu Lu
机构: Hefei Institutes of Physical Science Chinese Academy of Sciences (合肥物理科学研究院中国科学院); University of Science and Technology of China (中国科学技术大学); Hefei University of Technology (合肥工业大学); Shanghai Jiao Tong University (上海交通大学); ByteDance (字节跳动)
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注: 11pages, 6 figures

点击查看摘要

[CV-187] Seeing Delta Parameters as JPEG Images: Data-Free Delta Compression with Discrete Cosine Transform

链接: https://arxiv.org/abs/2503.06676
作者: Chenyu Huang,Peng Ye,Xiaohui Wang,Shenghe Zheng,Biqing Qi,Lei Bai,Wanli Ouyang,Tao Chen
机构: Fudan University (复旦大学); Shanghai Artificial Intelligence Laboratory (上海人工智能实验室); The Chinese University of Hong Kong (香港中文大学); Harbin Institute of Technology (哈尔滨工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Image and Video Processing (eess.IV)
备注: 15 pages, 7 figures

点击查看摘要

[CV-188] Learning Few-Step Diffusion Models by Trajectory Distribution Matching

链接: https://arxiv.org/abs/2503.06674
作者: Yihong Luo,Tianyang Hu,Jiacheng Sun,Yujun Cai,Jing Tang
机构: HKUST (香港科技大学); NUS (新加坡国立大学); Huawei Noah’s Ark Lab (华为诺亚方舟实验室); HKUST (GZ) (香港科技大学广州校区)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-189] Emulating Self-attention with Convolution for Efficient Image Super-Resolution

链接: https://arxiv.org/abs/2503.06671
作者: Dongheon Lee,Seokju Yun,Youngmin Ro
机构: Machine Intelligence Laboratory, University of Seoul (首尔大学)(韩国)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-190] AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

链接: https://arxiv.org/abs/2503.06669
作者: AgiBot-World-Contributors,Qingwen Bu,Jisong Cai,Li Chen,Xiuqi Cui,Yan Ding,Siyuan Feng,Shenyuan Gao,Xindong He,Xu Huang,Shu Jiang,Yuxin Jiang,Cheng Jing,Hongyang Li,Jialu Li,Chiming Liu,Yi Liu,Yuxiang Lu,Jianlan Luo,Ping Luo,Yao Mu,Yuehan Niu,Yixuan Pan,Jiangmiao Pang,Yu Qiao,Guanghui Ren,Cheng Ruan,Jiaqi Shan,Yongjian Shen,Chengshi Shi,Mingkang Shi,Modi Shi,Chonghao Sima,Jianheng Song,Huijie Wang,Wenhao Wang,Dafeng Wei,Chengen Xie,Guo Xu,Junchi Yan,Cunbiao Yang,Lei Yang,Shukai Yang,Maoqing Yao,Jia Zeng,Chi Zhang,Qinglin Zhang,Bin Zhao,Chengyue Zhao,Jiaqi Zhao,Jianchao Zhu
机构: OpenAI (OpenAI)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Project website: this https URL , Code: this https URL

点击查看摘要

[CV-191] AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP

链接: https://arxiv.org/abs/2503.06661
作者: Wenxin Ma,Xu Zhang,Qingsong Yao,Fenghe Tang,Chenxu Wu,Yingtai Li,Rui Yan,Zihang Jiang,S.Kevin Zhou
机构: School of Biomedical Engineering, Division of Life Sciences and Medicine, USTC (中国科学技术大学生物医学工程学院，生命科学与医学部); MIRACLE Center, Suzhou Institute for Advance Research, USTC (中国科学技术大学苏州高等研究院奇迹中心); Key Laboratory of Intelligent Information Processing of CAS, ICT, CAS (中国科学院计算技术研究所智能信息处理重点实验室); State Key Laboratory of Precision and Intelligent Chemistry, USTC (中国科学技术大学精准智能化学国家重点实验室); Stanford University (斯坦福大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 8 pages, 7 figures

点击查看摘要

[CV-192] AxisPose: Model-Free Matching-Free Single-Shot 6D Object Pose Estimation via Axis Generation

链接: https://arxiv.org/abs/2503.06660
作者: Yang Zou,Zhaoshuai Qi,Yating Liu,Zihao Xu,Weipeng Sun,Weiyi Liu,Xingyuan Li,Jiaqi Yang,Yanning Zhang
机构: Northwestern Polytechnical University (西北工业大学); Dalian University of Technology (大连理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-193] Adding Additional Control to One-Step Diffusion with Joint Distribution Matching

链接: https://arxiv.org/abs/2503.06652
作者: Yihong Luo,Tianyang Hu,Yifan Song,Jiacheng Sun,Zhenguo Li,Jing Tang
机构: HKUST (香港科技大学); NUS (新加坡国立大学); HKUST (GZ) (香港科技大学（广州）); Huawei Noah’s Ark Lab (华为诺亚方舟实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-194] Personalized Class Incremental Context-Aware Food Classification for Food Intake Monitoring Systems

链接: https://arxiv.org/abs/2503.06647
作者: Hassan Kazemi Tehrani,Jun Cai,Abbas Yekanlou,Sylvia Santosa
机构: Network Intelligence and Innovation Lab (N⁢I2⁢L𝑁superscript𝐼2𝐿NI^{2}Litalic_N italic_I start_POSTSUPERSCRIPT 2 end_POSTSUPERSCRIPT italic_L), Department of Electrical and Computer Engineering, Concordia University (康考迪亚大学); Department of Health, Kinesiology, and Applied Physiology, Concordia University (康考迪亚大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-195] CLICv2: Image Complexity Representation via Content Invariance Contrastive Learning

链接: https://arxiv.org/abs/2503.06641
作者: Shipeng Liu,Liang Zhao,Dengfeng Chen
机构: XAUAT
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-196] CLAD: Constrained Latent Action Diffusion for Vision-Language Procedure Planning

链接: https://arxiv.org/abs/2503.06637
作者: Lei Shi,Andreas Bulling
机构: University of Stuttgart (斯图加特大学); Örebro University (厄勒布鲁大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-197] owards More Accurate Personalized Image Generation: Addressing Overfitting and Evaluation Bias

链接: https://arxiv.org/abs/2503.06632
作者: Mingxiao Li,Tingyu Qu,Tinne Tuytelaars,Marie-Francine Moens
机构: Department of Computer Science, KU Leuven (鲁汶大学计算机科学系); Department of Electrical Engineering, KU Leuven (鲁汶大学电气工程系)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 18

点击查看摘要

[CV-198] DiffCLIP: Differential Attention Meets CLIP

链接: https://arxiv.org/abs/2503.06626
作者: Hasan Abed Al Kader Hammoud,Bernard Ghanem
机构: KAUST (国王科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Under review

点击查看摘要

[CV-199] Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking

链接: https://arxiv.org/abs/2503.06625
作者: Chaocan Xue,Bineng Zhong,Qihua Liang,Yaozong Zheng,Ning Li,Yuanliang Xue,Shuxiang Song
机构: Key Laboratory of Education Blockchain and Intelligent Technology (教育部重点实验室), Ministry of Education (中华人民共和国教育部), Guangxi Normal University (广西师范大学), Guilin 541004, China (中国); Xi’an Research Institute of High Technology (西安高技术研究所), Xi’an 710025, China (中国)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-200] Chameleon: On the Scene Diversity and Domain Variety of AI-Generated Videos Detection

链接: https://arxiv.org/abs/2503.06624
作者: Meiyu Zeng,Xingming Liao,Canyu Chen,Nankai Lin,Zhuowei Wang,Chong Chen,Aimin Yang
机构: Guangdong University of Technology (广东工业大学); Guangdong University of Foreign Studies (广东外语外贸大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 17 pages

点击查看摘要

[CV-201] ransforming Weather Data from Pixel to Latent Space

链接: https://arxiv.org/abs/2503.06623
作者: Sijie Zhao,Feng Liu,Xueliang Zhang,Hao Chen,Tao Han,Junchao Gong,Ran Tao,Pengfeng Xiao,Lei Bai,Wanli Ouyang
机构: Nanjing University (南京大学); Shanghai Artificial Intelligence Laboratory (上海人工智能实验室); Shanghai Jiao Tong University (上海交通大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 6 figures

点击查看摘要

[CV-202] Dynamic Updates for Language Adaptation in Visual-Language Tracking

链接: https://arxiv.org/abs/2503.06621
作者: Xiaohai Li,Bineng Zhong,Qihua Liang,Zhiyi Mo,Jian Nong,Shuxiang Song
机构: Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University (广西师范大学); Guangxi Colleges and Universities Key Laboratory of Intelligent Software, Wuzhou University (梧州学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-203] Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling

链接: https://arxiv.org/abs/2503.06617
作者: Long Peng,Anran Wu,Wenbo Li,Peizhe Xia,Xueyuan Dai,Xinjie Zhang,Xin Di,Haoze Sun,Renjing Pei,Yang Wang,Yang Cao,Zheng-Jun Zha
机构: USTC(中国科学技术大学); AHU(安徽大学); Huawei Noah’s Ark Lab(华为诺亚方舟实验室); Chang’an University(长安大学); HKUST(香港科技大学); THU(清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Tech Report

点击查看摘要

[CV-204] GroMo: Plant Growth Modeling with Multiview Images

链接: https://arxiv.org/abs/2503.06608
作者: Ruchi Bhatt,Shreya Bansal,Amanpreet Chander,Rupinder Kaur,Malya Singh,Mohan Kankanhalli,Abdulmotaleb El Saddik,Mukesh Kumar Saini
机构: Indian Institute of Technology Ropar(印度理工学院罗帕尔); National University of Singapore(新加坡国立大学); Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)(穆罕默德·本·扎耶德人工智能大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Multimedia (cs.MM)
备注: 7 pages, 5 Figures, 3 Tables

点击查看摘要

[CV-205] Steerable Pyramid Weighted Loss: Multi-Scale Adaptive Weighting for Semantic Segmentation

链接: https://arxiv.org/abs/2503.06604
作者: Renhao Lu
机构: Renhao Lu; Meinig School of Biomedical Engineering (梅尼格生物医学工程学院); Cornell University (康奈尔大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages, 4 figures

点击查看摘要

[CV-206] StructVPR: Distill Structural and Semantic Knowledge with Weighting Samples for Visual Place Recognition

链接: https://arxiv.org/abs/2503.06601
作者: Yanqing Shen,Sanping Zhou,Jingwen Fu,Ruotong Wang,Shitao Chen,Nanning Zheng
机构: National Key Laboratory of Human-Machine Hybrid Augmented Intelligence (人机混合增强智能国家重点实验室), National Engineering Research Center for Visual Information and Applications (视觉信息处理与应用国家工程研究中心), Institute of Artificial Intelligence and Robotics (人工智能与机器人研究所), Xi’an Jiaotong University (西安交通大学), Xi’an, Shaanxi 710049, China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-207] MultiCo3D: Multi-Label Voxel Contrast for One-Shot Incremental Segmentation of 3D Neuroimages

链接: https://arxiv.org/abs/2503.06598
作者: Hao Xu,Tengfei Xue,Dongnan Liu,Yuqian Chen,Fan Zhang,Carl-Fredrik Westin,Ron Kikinis,Lauren J. O’Donnell,Weidong Cai
机构: The University of Sydney (悉尼大学); Harvard Medical School (哈佛医学院); University of Electronic Science and Technology of China (电子科技大学); Brigham and Women’s Hospital (布里格姆妇女医院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 13 pages, 6 figures, 6 tables

点击查看摘要

[CV-208] Speech Audio Generation from dynamic MRI via a Knowledge Enhanced Conditional Variational Autoencoder

链接: https://arxiv.org/abs/2503.06588
作者: Yaxuan Li,Han Jiang,Yifei Ma,Shihua Qin,Fangxu Xing
机构: Harvard Medical School (哈佛医学院)
类目: ound (cs.SD); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-209] Introducing Unbiased Depth into 2D Gaussian Splatting for High-accuracy Surface Reconstruction

链接: https://arxiv.org/abs/2503.06587
作者: Xiaoming Peng,Yixin Yang,Yang Zhou,Hui Huang
机构: Visual Computing Research Center, CCSE, Shenzhen University (深圳大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-210] Global-Aware Monocular Semantic Scene Completion with State Space Models

链接: https://arxiv.org/abs/2503.06569
作者: Shijie Li,Zhongyao Cheng,Rong Li,Shuai Li,Juergen Gall,Xun Xu,Xulei Yang
机构: I2R, A*STAR (I2R, 新加坡科技研究局); AI Thrust, HKUST(GZ) (人工智能推进中心, 香港科技大学广州校区); Bonn University (波恩大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-211] Conceptrol: Concept Control of Zero-shot Personalized Image Generation

链接: https://arxiv.org/abs/2503.06568
作者: Qiyuan He,Angela Yao
机构: National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-212] Future-Aware Interaction Network For Motion Forecasting

链接: https://arxiv.org/abs/2503.06565
作者: Shijie Li,Xun Xu,Si Yong Yeo,Xulei Yang
机构: I2R, A*STAR (I2R, 新加坡科技研究局); Nanyang Technological University (南洋理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-213] R-DQ: Time-Rotation Diffusion Quantization

链接: https://arxiv.org/abs/2503.06564
作者: Yihua Shao,Deyang Lin,Fanhu Zeng,Minxi Yan,Muyang Zhang,Siyu Chen,Yuxuan Fan,Ziyang Yan,Haozhe Wang,Jingcai Guo,Yan Wang,Haotong Qin,Hao Tang
机构: Institution1; Institution2
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-214] MMARD: Improving the Min-Max Optimization Process in Adversarial Robustness Distillation

链接: https://arxiv.org/abs/2503.06559
作者: Yuzheng Wang,Zhaoyu Chen,Dingkang Yang,Yuanhang Wang,Lizhe Qi
机构: Shanghai Engineering Research Center of AI & Robotics, Academy for Engineering & Technology, Fudan University (复旦大学工程与技术学院上海人工智能与机器人工程研究中心); Engineering Research Center of AI & Robotics, Ministry of Education, Academy for Engineering & Technology, Fudan University (复旦大学工程与技术学院教育部人工智能与机器人工程研究中心)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-215] ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM -based Process Judges

链接: https://arxiv.org/abs/2503.06553
作者: Jiaxin Ai,Pengfei Zhou,Zhaopan Xu,Ming Li,Fanrui Zhang,Zizhen Li,Jianwen Sun,Yukang Feng,Baojin Huang,Zhongyuan Wang,Kaipeng Zhang
机构: WHU (武汉大学); Shanghai AI Laboratory (上海人工智能实验室); USTC (中国科学技术大学); NKU (南开大学); HZAU (华中农业大学); Shanghai Innovation Institude (上海创新研究院)
类目: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-216] QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation

链接: https://arxiv.org/abs/2503.06545
作者: Junyi Wu,Zhiteng Li,Zheng Hui,Yulun Zhang,Linghe Kong,Xiaokang Yang
机构: Shanghai Jiao Tong University (上海交通大学); MGTV, Shanhai Academy (魔都广电集团上海研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: The code and models will be available at this https URL

点击查看摘要

[CV-217] ARMOR v0.1: Empowering Autoregressive Multimodal Understanding Model with Interleaved Multimodal Generation via Asymmetric Synergy

链接: https://arxiv.org/abs/2503.06542
作者: Jianwen Sun,Yukang Feng,Chuanhao Li,Fanrui Zhang,Zizhen Li,Jiaxin Ai,Sizhuo Zhou,Yu Dai,Shenglin Zhang,Kaipeng Zhang
机构: Nankai University (南开大学); Shanghai Innovation Institute (上海创新研究院); University of Science and Technology of China (中国科学技术大学); Wuhan University (武汉大学); Shanghai AI Laboratory (上海人工智能实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-218] One-Step Diffusion Model for Image Motion-Deblurring

链接: https://arxiv.org/abs/2503.06537
作者: Xiaoyang Liu,Yuquan Wang,Zheng Chen,Jiezhang Cao,He Zhang,Yulun Zhang,Xiaokang Yang
机构: Shanghai Jiao Tong University (上海交通大学); Harvard University (哈佛大学); Adobe Research (Adobe 研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-219] AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection

链接: https://arxiv.org/abs/2503.06529
作者: Jialin Lu,Junjie Shan,Ziqi Zhao,Ka-Ho Chow
机构: School of Computing and Data Science (计算机与数据科学学院), The University of Hong Kong (香港大学)
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-220] meLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videos

链接: https://arxiv.org/abs/2503.06526
作者: Chen-Lin Zhang,Lin Sui,Shuming Liu,Fangzhou Mu,Zhangcheng Wang,Bernard Ghanem
机构: Moonshot AI (月球shot AI); KAUST (国王 Abdullah科技大学); NVIDIA (英伟达); 4Paradigm Inc (第四范式)
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注: Code models will be released at this https URL . The first 4 authors contributes equally

点击查看摘要

[CV-221] SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic

链接: https://arxiv.org/abs/2503.06522
作者: Yuchen Yang,Wei Wang,Yifei Liu,Linfeng Dong,Hao Wu,Mingxin Zhang,Zhihang Zhong,Xiao Sun
机构: Fudan University (复旦大学); Shanghai Artificial Intelligence Laboratory (上海人工智能实验室); Beihang University (北京航空航天大学); Zhejiang University (浙江大学); University of Science and Technology of China (中国科学技术大学); Shanghai University of Sport (上海体育学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: None

点击查看摘要

[CV-222] Seg-Zero: Reasoning -Chain Guided Segmentation via Cognitive Reinforcement

链接: https://arxiv.org/abs/2503.06520
作者: Yuqi Liu,Bohao Peng,Zhisheng Zhong,Zihao Yue,Fanbin Lu,Bei Yu,Jiaya Jia
机构: CUHK (香港中文大学); HKUST (香港科技大学); RUC (中国人民大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注:

点击查看摘要

[CV-223] Instance-wise Supervision-level Optimization in Active Learning CVPR2025

链接: https://arxiv.org/abs/2503.06517
作者: Shinnosuke Matsuo,Riku Togashi,Ryoma Bise,Seiichi Uchida,Masahiro Nomura
机构: Kyushu University (九州大学); CyberAgent, Inc. (赛博代理公司)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Accepted at CVPR2025

点击查看摘要

[CV-224] SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model

链接: https://arxiv.org/abs/2503.06515
作者: Jing Zhang,Zhikai Li,Qingyi Gu
机构: Institute of Automation, Chinese Academy of Sciences (自动化研究所，中国科学院); School of Artificial Intelligence, University of Chinese Academy of Sciences (人工智能学院，中国科学院大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-225] A Light and Tuning-free Method for Simulating Camera Motion in Video Generation

链接: https://arxiv.org/abs/2503.06508
作者: Quanjian Song,Zhihang Lin,Zhanpeng Zeng,Ziyue Zhang,Liujuan Cao,Rongrong Ji
机构: Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University (厦门大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 18 pages in total

点击查看摘要

[CV-226] Fine-Grained Alignment and Noise Refinement for Compositional Text-to-Image Generation

链接: https://arxiv.org/abs/2503.06506
作者: Amir Mohammad Izadi,Seyed Mohammad Hadi Hosseini,Soroush Vafaie Tabar,Ali Abdollahi,Armin Saghafian,Mahdieh Soleymani Baghshah
机构: Sharif University of Technology (Sharif 大学技术)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-227] DynamicID: Zero-Shot Multi-ID Image Personalization with Flexible Facial Editability

链接: https://arxiv.org/abs/2503.06505
作者: Xirui Hu,Jiahao Wang,Hao Chen,Weizhan Zhang,Benqi Wang,Yikun Li,Haishun Nan
机构: School of Computer Science and Technology, Xi’an Jiaotong University (西安交通大学计算机科学与技术学院); AI Lab, Western Movie Group (西部电影集团人工智能实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 17 pages, 16 figures

点击查看摘要

[CV-228] xtInPlace: Indoor Visual Place Recognition in Repetitive Structures with Scene Text Spotting and Verification

链接: https://arxiv.org/abs/2503.06501
作者: Huaqi Tao,Bingxi Liu,Calvin Chen,Tingjun Huang,He Li,Jinqiang Cui,Hong Zhang
机构: Department of Electronic and Electrical Engineering, Southern University of Science and Technology (南方科技大学电子与电气工程系), Shenzhen, China; Peng Cheng Laboratory (鹏城实验室), Shenzhen, China; University of Cambridge (剑桥大学), Cambridge, United Kingdom
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: 8 pages,5 figures

点击查看摘要

[CV-229] ExGes: Expressive Human Motion Retrieval and Modulation for Audio-Driven Gesture Synthesis

链接: https://arxiv.org/abs/2503.06499
作者: Xukun Zhou,Fengxin Li,Ming Chen,Yan Zhou,Pengfei Wan,Di Zhang,Hongyan Liu,Jun He,Zhaoxin Fan
机构: Renmin University (中国人民大学); Kuaishou Technology (快手科技); Tsinghua University (清华大学); BUAA (北京航空航天大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-230] Evaluation of Safety Cognition Capability in Vision-Language Models for Autonomous Driving

链接: https://arxiv.org/abs/2503.06497
作者: Enming Zhang,Peizhe Gong,Xingyuan Dai,Yisheng Lv,Qinghai Miao
机构: School of Artificial Intelligence, University of Chinese Academy of Sciences (人工智能学院，中国科学院大学); State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences (多模态人工智能系统国家重点实验室，中国科学院自动化研究所)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-231] PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training

链接: https://arxiv.org/abs/2503.06486
作者: Cong Chen,Mingyu Liu,Chenchen Jing,Yizhou Zhou,Fengyun Rao,Hao Chen,Bo Zhang,Chunhua Shen
机构: Zhejiang University (浙江大学); WeChat Group (微信团队); Zhejiang University of Technology (浙江工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-232] A Mesh Is Worth 512 Numbers: Spectral-domain Diffusion Modeling for High-dimension Shape Generation

链接: https://arxiv.org/abs/2503.06485
作者: Jiajie Fan,Amal Trigui,Andrea Bonfanti,Felix Dietrich,Thomas Bäck,Hao Wang
机构: Leiden University (莱顿大学); BMW Group (宝马集团); Technical University of Munich (慕尼黑工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-233] Sign Language Translation using Frame and Event Stream: Benchmark Dataset and Algorithms

链接: https://arxiv.org/abs/2503.06484
作者: Xiao Wang,Yuehang Li,Fuling Wang,Bo Jiang,Yaowei Wang,Yonghong Tian,Jin Tang,Bin Luo
机构: School of Computer Science and Technology, Anhui University, Hefei, China (安徽大学计算机科学与技术学院，合肥，中国); Harbin Institute of Technology, Shenzhen, China (哈尔滨工业大学（深圳）); Peng Cheng Laboratory, Shenzhen, China (鹏城实验室，深圳，中国); National Key Laboratory for Multimedia Information Processing, Peking University, China (北京大学多媒体信息处理国家重点实验室，中国); School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, China (北京大学深圳研究生院电子与计算机工程学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE)
备注: In Peer Review

点击查看摘要

[CV-234] PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization

链接: https://arxiv.org/abs/2503.06482
作者: Honglin Li,Zhongyi Shui,Yunlong Zhang,Chenglu Zhu,Lin Yang
机构: Zhejiang University (浙江大学); Research Center for Industries of the Future (未来产业研究中心); School of Engineering, Westlake University (西湖大学工学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-235] PDB: Not All Drivers Are the Same – A Personalized Dataset for Understanding Driving Behavior

链接: https://arxiv.org/abs/2503.06477
作者: Chuheng Wei,Ziye Qin,Siyan Li,Ziyan Zhang,Xuanpeng Zhao,Amr Abdelraouf,Rohit Gupta,Kyungtae Han,Matthew J. Barth,Guoyuan Wu
机构: University of California, Riverside (加州大学河滨分校); Southwest Jiaotong University (西南交通大学); InfoTech Labs, Toyota Motor North America (丰田汽车北美信息技术实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-236] Enhancing Layer Attention Efficiency through Pruning Redundant Retrievals

链接: https://arxiv.org/abs/2503.06473
作者: Hanze Li,Xiande Huang
机构: Glasgow College, University of Electronic Science and Technology of China (电子科技大学格拉斯哥学院); De AI Lab, De Intelligence Technology Co., Ltd (德睿智药科技有限公司 AI 实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 11 pages, 7 figures

点击查看摘要

[CV-237] CalliReader: Contextualizing Chinese Calligraphy via an Embedding-Aligned Vision-Language Model

链接: https://arxiv.org/abs/2503.06472
作者: Yuxuan Luo,Jiaqi Tang,Chenyi Huang,Feiyang Hao,Zhouhui Lian
机构: Wangxuan Institute of Computer Technology, Peking University (王选计算机研究所，北京大学); Xi’an Jiaotong University (西安交通大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注: 11 pages

点击查看摘要

[CV-238] Online Dense Point Tracking with Streaming Memory

链接: https://arxiv.org/abs/2503.06471
作者: Qiaole Dong,Yanwei Fu
机构: School of Data Science, Fudan University (复旦大学数据科学学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-239] Vector Quantized Feature Fields for Fast 3D Semantic Lifting

链接: https://arxiv.org/abs/2503.06469
作者: George Tang,Aditya Agarwal,Weiqiao Han,Trevor Darrell,Yutong Bai
机构: MIT(麻省理工学院); UC Berkeley(加州大学伯克利分校)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-240] SP3D: Boosting Sparsely-Supervised 3D Object Detection via Accurate Cross-Modal Semantic Prompts

链接: https://arxiv.org/abs/2503.06467
作者: Shijia Zhao,Qiming Xia,Xusheng Guo,Pufan Zou,Maoji Zheng,Hai Wu,Chenglu Wen,Cheng Wang
机构: Fujian Key Laboratory of Sensing and Computing for Smart Cities, Xiamen University (厦门大学), China; Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University (厦门大学), China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 11 pages, 3 figures

点击查看摘要

[CV-241] StructGS: Adaptive Spherical Harmonics and Rendering Enhancements for Superior 3D Gaussian Splatting

链接: https://arxiv.org/abs/2503.06462
作者: Zexu Huang,Min Xu,Stuart Perry
机构: Perceptual Imaging Laboratory (PILab), School of Electrical and Data Engineering, University of Technology Sydney (悉尼科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-242] Long-tailed Adversarial Training with Self-Distillation ICLR2025

链接: https://arxiv.org/abs/2503.06461
作者: Seungju Cho,Hongsin Lee,Changick Kim
机构: Korea Advanced Institute of Science and Technology (KAIST)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: ICLR 2025

点击查看摘要

[CV-243] Reconstructing Depth Images of Moving Objects from Wi-Fi CSI Data

链接: https://arxiv.org/abs/2503.06458
作者: Guanyu Cao,Takuya Maekawa,Kazuya Ohara,Yasue Kishino
机构: Graduate School of Information Science and Technology (信息科学与技术研究生院), Osaka University (大阪大学), Osaka, Japan; NTT Communication Science Laboratories (NTT通信科学实验室), NTTCSL, Kyoto, Japan
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-244] Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learning CVPR2025

链接: https://arxiv.org/abs/2503.06457
作者: Yanbiao Ma,Wei Dai,Wenke Huang,Jiayi Chen
机构: Xidian University (西安电子科技大学); Wuhan University (武汉大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Accepted by CVPR 2025

点击查看摘要

[CV-245] DynCIM: Dynamic Curriculum for Imbalanced Multimodal Learning

链接: https://arxiv.org/abs/2503.06456
作者: Chengxuan Qian,Kai Han,Jingchao Wang,Zhenlong Yuan,Rui Qian,Chongwen Lyu,Jun Chen,Zhe Liu
机构: Jiangsu University (江苏大学); Peking University (北京大学); Institute of Computing Technology, Chinese Academy of Science (中国科学院计算技术研究所); Fudan University (复旦大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-246] A Quantitative Evaluation of the Expressivity of BMI Pose and Gender in Body Embeddings for Recognition and Identification

链接: https://arxiv.org/abs/2503.06451
作者: Basudha Pal,Siyuan(Cyan)Huang,Rama Chellappa
机构: Johns Hopkins University (约翰斯·霍普金斯大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-247] M3amba: CLIP-driven Mamba Model for Multi-modal Remote Sensing Classification

链接: https://arxiv.org/abs/2503.06446
作者: Mingxiang Cao,Weiying Xie,Xin Zhang,Jiaqing Zhang,Kai Jiang,Jie Lei,Yunsong Li
机构: State Key Laboratory of Integrated Services Networks, Xidian University (西安电子科技大学集成服务网络国家重点实验室); School of Electrical and Data Engineering, University of Technology Sydney (悉尼科技大学电气与数据工程学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-248] OT-DETECTOR: Delving into Optimal Transport for Zero-shot Out-of-Distribution Detection

链接: https://arxiv.org/abs/2503.06442
作者: Yu Liu,Hao Tang,Haiqi Zhang,Jing Qin,Zechao Li
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注: The first two authors contributed equally to this work

点击查看摘要

[CV-249] SEED: Towards More Accurate Semantic Evaluation for Visual Brain Decoding

链接: https://arxiv.org/abs/2503.06437
作者: Juhyeon Park,Peter Yongho Kim,Jiook Cha,Shinjae Yoo,Taesup Moon
机构: Seoul National University (首尔国立大学); Brookhaven National Lab (布鲁克海文国家实验室); ASRI / INMC / AIIS (首尔国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Under Review

点击查看摘要

[CV-250] OV-SCAN: Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection

链接: https://arxiv.org/abs/2503.06435
作者: Adrian Chow,Evelien Riddell,Yimu Wang,Sean Sedwards,Krzysztof Czarnecki
机构: University of Waterloo (滑铁卢大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-251] Pre-Training Meta-Rule Selection Policy for Visual Generative Abductive Learning

链接: https://arxiv.org/abs/2503.06427
作者: Yu Jin,Jingming Liu,Zhexu Luo,Yifei Peng,Ziang Qin,Wang-Zhou Dai,Yao-Xiang Ding,Kun Zhou
机构: State Key Laboratory of CAD&CG, Zhejiang University (浙江大学国家重点实验室); National Key Laboratory for Novel Software Technology, Nanjing University (南京大学新型软件技术国家重点实验室)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: Published as a conference paper at IJCLR’24

点击查看摘要

[CV-252] Federated Learning for Diffusion Models

链接: https://arxiv.org/abs/2503.06426
作者: Zihao Peng,Xijun Wang,Shengbo Chen,Hong Rao,Cong Shen
机构: School of Mathematics and Computer Science, Nanchang University, Nanchang 330000, China (南昌大学数学与计算机科学学院); School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou 510006, China (中山大学电子与信息工程学院); School of Software, Nanchang University, Nanchang 330000, China (南昌大学软件学院); Charles L. Brown Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA 22904, USA (美国弗吉尼亚大学查尔斯·布朗电气与计算机工程系)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Distributed, Parallel, and Cluster Computing (cs.DC)
备注:

点击查看摘要

[CV-253] Consistent Image Layout Editing with Diffusion Models

链接: https://arxiv.org/abs/2503.06419
作者: Tao Xia,Yudi Zhang,Ting Liu Lei Zhang
机构: Beijing Institute 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-254] Polygonal network disorder and the turning distance

链接: https://arxiv.org/abs/2503.06415
作者: Alex Dolce,Ryan Lavelle,Bernard Scott,Ashlyn Urbanski,Joseph Klobusicky
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-255] FEDS: Feature and Entropy-Based Distillation Strategy for Efficient Learned Image Compression

链接: https://arxiv.org/abs/2503.06399
作者: Haisheng Fu,Jie Liang,Zhenman Fang,Jingning Han
机构: Simon Fraser University (西蒙弗雷泽大学); Google (谷歌)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
备注: 16 pages

点击查看摘要

[CV-256] Removing Averag ing: Personalized Lip-Sync Driven Characters Based on Identity Adapter

链接: https://arxiv.org/abs/2503.06397
作者: Yanyu Zhu,Licheng Bai,Jintao Xu,Jiwei Tang,Hai-tao Zheng
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-257] A Good Start Matters: Enhancing Continual Learning with Data-Driven Weight Initialization

链接: https://arxiv.org/abs/2503.06385
作者: Md Yousuf Harun,Christopher Kanan
机构: Rochester Institute of Technology (罗切斯特理工学院); University of Rochester (罗彻斯特大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: Preprint

点击查看摘要

[CV-258] Spectral State Space Model for Rotation-Invariant~Visual~Representation~Learning

链接: https://arxiv.org/abs/2503.06369
作者: Sahar Dastani,Ali Bahri,Moslem Yazdanpanah,Mehrdad Noori,David Osowiechi,Gustavo Adolfo Vargas Hakim,Farzad Beizaee,Milad Cheraghalikhani,Arnab Kumar Mondal,Herve Lombaert,Christian Desrosiers
机构: LIVIA, ILLS, ÉTS Montréal (LIVIA, ILLS, 蒙特利尔ÉTS); Mila - Quebec AI Institute (Mila - 魁北克人工智能研究所); Apple (苹果); Polytechnique Montreal (蒙特利尔理工学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-259] VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token Encodings

链接: https://arxiv.org/abs/2503.06368
作者: Leonardo Scabini,Kallil M. Zielinski,Emir Konuk,Ricardo T. Fares,Lucas C. Ribas,Kevin Smith,Odemir M. Bruno
机构: São Carlos Institute of Physics, University of São Paulo (圣保罗大学圣卡洛斯物理研究所); São Paulo State University, Institute of Biosciences, Humanities and Exact Sciences (圣保罗州立大学生物科学、人文学科和精密科学学院); KTH Royal Institute of Technology, and Science for Life Laboratory (瑞典皇家理工学院和生命科学实验室)
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-260] Generative Video Bi-flow

链接: https://arxiv.org/abs/2503.06364
作者: Chen Liu,Tobias Ritschel
机构: University College London (伦敦大学学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-261] Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLM s

链接: https://arxiv.org/abs/2503.06362
作者: Umberto Cappellazzo,Minsu Kim,Stavros Petridis
机构: Imperial College London; Meta AI (元人工智能)
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM); Sound (cs.SD); Audio and Speech Processing (eess.AS)
备注:

点击查看摘要

[CV-262] Adversarial Robustness of Discriminative Self-Supervised Learning in Vision

链接: https://arxiv.org/abs/2503.06361
作者: Ömer Veysel Çağatan,Ömer Faruk Tal,M. Emre Gürsoy
机构: Department of Computer Engineering, Koç University (科奇大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 53 pages

点击查看摘要

[CV-263] Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning

链接: https://arxiv.org/abs/2503.06339
作者: Gaurav Patel,Qiang Qiu
机构: Purdue University (普渡大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-264] Accurate and Efficient Two-Stage Gun Detection in Video

链接: https://arxiv.org/abs/2503.06317
作者: Badhan Chandra Das,M. Hadi Amini,Yanzhao Wu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-265] End-to-End Action Segmentation Transformer

链接: https://arxiv.org/abs/2503.06316
作者: Tieqiao Wang,Sinisa Todorovic
机构: Oregon State University (俄勒冈州立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-266] GeoLangBind: Unifying Earth Observation with Agglomerative Vision-Language Foundation Models

链接: https://arxiv.org/abs/2503.06312
作者: Zhitong Xiong,Yi Wang,Weikang Yu,Adam J Stewart,Jie Zhao,Nils Lehmann,Thomas Dujardin,Zhenghang Yuan,Pedram Ghamisi,Xiao Xiang Zhu
机构: Technical University of Munich (慕尼黑工业大学); Helmholtz-Zentrum Dresden-Rossendorf (德累斯顿亥姆霍兹研究中心)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: code weights: this https URL

点击查看摘要

[CV-267] xt2Story: Advancing Video Storytelling with Text Guidance

链接: https://arxiv.org/abs/2503.06310
作者: Taewon Kang,Divya Kothandaraman,Ming C. Lin
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 15 pages, 6 figures

点击查看摘要

[CV-268] ACAM-KD: Adaptive and Cooperative Attention Masking for Knowledge Distillation

链接: https://arxiv.org/abs/2503.06307
作者: Qizhen Lan,Qing Tian
机构: University of Alabama at Birmingham (阿拉巴马大学伯明翰分校)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 10 tables, 3 figures

点击查看摘要

[CV-269] Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding

链接: https://arxiv.org/abs/2503.06287
作者: Seil Kang,Jinyeong Kim,Junhyeok Kim,Seong Jae Hwang
机构: Yonsei University (延世大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-270] From Dataset to Real-world: General 3D Object Detection via Generalized Cross-domain Few-shot Learning

链接: https://arxiv.org/abs/2503.06282
作者: Shuangzhi Li,Junlong Shen,Lei Ma,Xingyu Li
机构: Department of Electrical and Computer Engineering, University of Alberta (阿尔伯塔大学), Alberta, Canada
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-271] STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classification CVPR2025

链接: https://arxiv.org/abs/2503.06277
作者: Siyi Du,Xinzhe Luo,Declan P. O’Regan,Chen Qin
机构: Department of Electrical and Electronic Engineering & I-X (电子与电气工程系&I-X), MRC Laboratory of Medical Science (医学研究委员会医学科学实验室), Imperial College London (帝国理工学院), London, UK
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 16 pages (including 5 pages of supplementary materials), accepted by CVPR 2025

点击查看摘要

[CV-272] Exploring Adversarial Transferability between Kolmogorov-arnold Networks

链接: https://arxiv.org/abs/2503.06276
作者: Songping Wang,Xinquan Yue,Yueming Lyu,Caifeng Shan
机构: Nanjing University (南京大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-273] Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLM s by Learning Language-Agnostic Speech Representations

链接: https://arxiv.org/abs/2503.06273
作者: Jeong Hun Yeo,Minsu Kim,Chae Won Kim,Stavros Petridis,Yong Man Ro
机构: KAIST (高丽科技大学); Imperial College London (帝国理工学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM); Sound (cs.SD); Audio and Speech Processing (eess.AS)
备注:

点击查看摘要

[CV-274] SplatTalk: 3D VQA with Gaussian Splatting

链接: https://arxiv.org/abs/2503.06271
作者: Anh Thai,Songyou Peng,Kyle Genova,Leonidas Guibas,Thomas Funkhouser
机构: Georgia Institute of Technology (乔治亚理工学院); Google DeepMind (谷歌深度思维)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-275] Get In Video: Add Anything You Want to the Video

链接: https://arxiv.org/abs/2503.06268
作者: Shaobin Zhuang,Zhipeng Huang,Binxin Yang,Ying Zhang,Fangyikang Wang,Canmiao Fu,Chong Sun,Zheng-Jun Zha,Chen Li,Yali Wang
机构: Shanghai Jiao Tong University (上海交通大学); WeChat, Tencent Inc (微信，腾讯公司); University of Science and Technology of China (中国科学技术大学); Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences (中国科学院深圳先进技术研究院); Shanghai Artificial Intelligence Laboratory (上海人工智能实验室); Zhejiang University (浙江大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-276] Segment Anything Even Occluded

链接: https://arxiv.org/abs/2503.06261
作者: Wei-En Tai,Yu-Lin Shih,Cheng Sun,Yu-Chiang Frank Wang,Hwann-Tzong Chen
机构: National Tsing Hua University (清华大学); NVIDIA (英伟达); National Taiwan University (台湾大学); Aeolus Robotics (艾欧洛斯机器人)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-277] From Captions to Rewards (CAREVL): Leverag ing Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models

链接: https://arxiv.org/abs/2503.06260
作者: Muzhi Dai,Jiashuo Sun,Zhiyuan Zhao,Shixuan Liu,Rui Li,Junyu Gao,Xuelong Li
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-278] Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?

链接: https://arxiv.org/abs/2503.06252
作者: Kun Xiang,Zhili Liu,Zihao Jiang,Yunshuang Nie,Kaixin Cai,Yiyang Yin,Runhui Huang,Haoxiang Fan,Hanhui Li,Weiran Huang,Yihan Zeng,Yu-Jie Yuan,Jianhua Han,Lanqing Hong,Hang Xu,Xiaodan Liang
机构: Sun Yat-sen University (中山大学); Hong Kong University of Science and Technology (香港科技大学); Shanghai Jiaotong University (上海交通大学); University of Hong Kong (香港大学); Huawei Noah’s Ark Lab (华为诺亚方舟实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-279] Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection CVPR2025

链接: https://arxiv.org/abs/2503.06237
作者: Yifan Chang,Junjie Huang,Xiaofeng Wang,Yun Ye,Zhujin Liang,Yi Shan,Dalong Du,Xingang Wang
机构: Institute of Automation, Chinese Academy of Sciences (自动化研究所，中国科学院); PhiGent Robotics (PhiGent 机器人); UCAS (中国科学院大学); Luoyang Institute for Robot and Intelligent Equipment, Luoyang, China (洛阳智能装备研究所，中国洛阳); IEEE (电气电子工程师学会)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: CVPR2025

点击查看摘要

[CV-280] Dynamically evolving segment anything model with continuous learning for medical image segmentation

链接: https://arxiv.org/abs/2503.06236
作者: Zhaori Liu,Mengyang Li,Hu Han,Enli Zhang,Shiguang Shan,Zhiming Zhao
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-281] StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams

链接: https://arxiv.org/abs/2503.06235
作者: Yang LI,Jinglu Wang,Lei Chu,Xiao Li,Shiu-hong Kao,Ying-Cong Chen,Yan Lu
机构: Media Computing Group, Microsoft Research Asia (微软研究亚洲); CSE Dept., HKUST (香港科技大学); AI Thrust, HKUST(GZ) (香港科技大学广州校区人工智能研究所)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages

点击查看摘要

[CV-282] Reinforced Diffuser for Red Teaming Large Vision-Language Models

链接: https://arxiv.org/abs/2503.06223
作者: Ruofan Wang,Xiang Zheng,Xiaosen Wang,Cong Wang,Xingjun Ma
机构: Fudan University (复旦大学); City University of Hong Kong (香港城市大学); Huawei Technologies Ltd. (华为技术有限公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-283] Vision-based 3D Semantic Scene Completion via Capture Dynamic Representations

链接: https://arxiv.org/abs/2503.06222
作者: Meng Wang,Fan Wu,Yunchuan Qin,Ruihui Li,Zhuo Tang,Kenli Li
机构: Hunan University (湖南大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-284] StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition

链接: https://arxiv.org/abs/2503.06220
作者: Xin Ding,Hao Wu,Yifan Yang,Shiqi Jiang,Donglin Bai,Zhibo Chen,Ting Cao
机构: Microsoft Research (微软研究院); Nanjing University (南京大学); Beijing Zhongke Research Institue (北京中科研究院)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-285] VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene Completion AAAI-2025

链接: https://arxiv.org/abs/2503.06219
作者: Meng Wang,Huilong Pi,Ruihui Li,Yunchuan Qin,Zhuo Tang,Kenli Li
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accept by AAAI-2025(Oral)

点击查看摘要

[CV-286] Removing Multiple Hybrid Adverse Weather in Video via a Unified Model

链接: https://arxiv.org/abs/2503.06200
作者: Yecong Wan,Mingwen Shao,Yuanshuo Cheng,Jun Shu,Shuigen Wang
机构: China University of Petroleum (East China) (中国石油大学（华东）); Xi’an Jiaotong University (西安交通大学); IRay Technology Co., Ltd. (爱瑞科技有限公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-287] NeuroADDA: Active Discriminative Domain Adaptation in Connectomic

链接: https://arxiv.org/abs/2503.06196
作者: Shashata Sawmya,Thomas L. Athey,Gwyneth Liu,Nir Shavit
机构: Massachusetts Institute of Technology (麻省理工学院); Red Hat
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 3 figures, 3 tables

点击查看摘要

[CV-288] MSConv: Multiplicative and Subtractive Convolution for Face Recognition

链接: https://arxiv.org/abs/2503.06187
作者: Si Zhou,Yain-Whar Si,Xiaochen Yuan,Xiaofan Li,Xiaoxiang Liu,Xinyuan Zhang,Cong Lin,Xueyuan Gong
机构: Jinan University (暨南大学); Jinan University (暨南大学); Macau University of Science and Technology (澳门科技大学); Macau Polytechnic University (澳门城市大学); Jinan University (暨南大学); Jinan University (暨南大学); Jinan University (暨南大学); Jinan University (暨南大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-289] PTDiffusion: Free Lunch for Generating Optical Illusion Hidden Pictures with Phase-Transferred Diffusion Model CVPR2025

链接: https://arxiv.org/abs/2503.06186
作者: Xiang Gao,Shuai Yang,Jiaying Liu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025)

点击查看摘要

[CV-290] FORESCENE: FOREcasting human activity via latent SCENE graphs diffusion

链接: https://arxiv.org/abs/2503.06182
作者: Antonio Alliegro,Francesca Pistilli,Tatiana Tommasi,Giuseppe Averta
机构: Politecnico di Torino (都灵理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-291] ForestSplats: Deformable transient field for Gaussian Splatting in the Wild

链接: https://arxiv.org/abs/2503.06179
作者: Wongi Park,Myeongseok Nam,Siwon Kim,Sangwoo Jo,Soomok Lee
机构: Department of Software and Artificial Intelligence, Ajou University (Ajou大学软件与人工智能系); Minds and Company (Minds and Company)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-292] Object-Centric World Model for Language-Guided Manipulation

链接: https://arxiv.org/abs/2503.06170
作者: Youngjoon Jeong,Junha Chun,Soonwoo Cha,Taesup Kim
机构: Graduate School of Data Science (数据科学研究生院), Seoul National University (首尔国立大学); Department of Electrical and Computer Engineering (电气与计算机工程系), Seoul National University (首尔国立大学)
类目: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-293] reble Counterfactual VLMs: A Causal Approach to Hallucination

链接: https://arxiv.org/abs/2503.06169
作者: Li Li,Jiashu Qu,Yuxiao Zhou,Yuehan Qin,Tiankai Yang,Yue Zhao
机构: University of Southern California (南加州大学); University of Cincinnati (辛辛那提大学); National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-294] VACT: A Video Automatic Causal Testing System and a Benchmark

链接: https://arxiv.org/abs/2503.06163
作者: Haotong Yang,Qingyuan Zheng,Yunjian Gao,Yongkun Yang,Yangbo He,Zhouchen Lin,Muhan Zhang
机构: 未知
类目: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Applications (stat.AP)
备注:

点击查看摘要

[CV-295] Feature-EndoGaussian: Feature Distilled Gaussian Splatting in Surgical Deformable Scene Reconstruction

链接: https://arxiv.org/abs/2503.06161
作者: Kai Li,Junhao Wang,William Han,Ding Zhao
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 14 pages, 5 figures

点击查看摘要

[CV-296] UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces

链接: https://arxiv.org/abs/2503.06157
作者: Baining Zhao,Jianjie Fang,Zichao Dai,Ziyou Wang,Jirong Zha,Weichen Zhang,Chen Gao,Yue Wang,Jinqiang Cui,Xinlei Chen,Yong Li
机构: Tsinghua University (清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 22 pages

点击查看摘要

[CV-297] SRM-Hair: Single Image Head Mesh Reconstruction via 3D Morphable Hair

链接: https://arxiv.org/abs/2503.06154
作者: Zidu Wang,Jiankuo Zhao,Miao Xu,Xiangyu Zhu,Zhen Lei
机构: State Key Laboratory of Multimodal Artificial Intelligence Systems (多模态人工智能系统国家重点实验室), Institute of Automation, Chinese Academy of Sciences (自动化研究所，中国科学院); School of Artificial Intelligence, University of Chinese Academy of Sciences (中国科学院大学人工智能学院); Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences (香港创新科学研究院人工智能与机器人中心，中国科学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Under review

点击查看摘要

[CV-298] BioMoDiffuse: Physics-Guided Biomechanical Diffusion for Controllable and Authentic Human Motion Synthesis

链接: https://arxiv.org/abs/2503.06151
作者: Zixi Kang,Xinghan Wang,Yadong Mu
机构: Peking University (北京大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-299] OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Images

链接: https://arxiv.org/abs/2503.06146
作者: Ziyue Huang,Yongchao Feng,Shuai Yang,Ziqi Liu,Qingjie Liu,Yunhong Wang
机构: Beihang University (北京航空航天大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 11 pages, 4 figures

点击查看摘要

[CV-300] VLForgery Face Triad: Detection Localization and Attribution via Multimodal Large Language Models

链接: https://arxiv.org/abs/2503.06142
作者: Xinan He,Yue Zhou,Bing Fan,Bin Li,Guopu Zhu,Feng Ding
机构: Nanchang University (南昌大学); Shenzhen University (深圳大学); University of North Texas (北德克萨斯大学); Harbin Institute of Technology (哈尔滨工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-301] Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model

链接: https://arxiv.org/abs/2503.06141
作者: Mingxing Li,Rui Wang,Lei Sun,Yancheng Bai,Xiangxiang Chu
机构: Amap (高德), Alibaba Group (阿里巴巴集团); BUPT (北京邮电大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-302] Boosting the Local Invariance for Better Adversarial Transferability

链接: https://arxiv.org/abs/2503.06140
作者: Bohan Liu,Xiaosen Wang
机构: Xidian Univeristy (西安电子科技大学); Huazhong University of Science and Technology (华中科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-303] GSV3D: Gaussian Splatting-based Geometric Distillation with Stable Video Diffusion for Single-Image 3D Object Generation

链接: https://arxiv.org/abs/2503.06136
作者: Ye Tao,Jiawei Zhang,Yahao Shi,Dongqing Zou,Bin Zhou
机构: State Key Laboratory of Virtual Reality Technology and Systems, Beihang University (北航); SenseTime Research (商汤科技); PBVR
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-304] X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distillation

链接: https://arxiv.org/abs/2503.06134
作者: Jian Ma,Qirong Peng,Xu Guo,Chen Chen,Haonan Lu,Zhenyu Yang
机构: OPPO AI Center; Tsinghua University (清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: this https URL

点击查看摘要

[CV-305] USP: Unified Self-Supervised Pretraining for Image Generation and Understanding

链接: https://arxiv.org/abs/2503.06132
作者: Xiangxiang Chu,Renda Li,Yong Wang
机构: AMAP, Alibaba Group (阿里云)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-306] Viewport-Unaware Blind Omnidirectional Image Quality Assessment: A Flexible and Effective Paradigm

链接: https://arxiv.org/abs/2503.06129
作者: Jiebin Yan,Kangcheng Wu,Junjie Chen,Ziwen Tan,Yuming Fang
机构: School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics(Nanchang, China); Harvard Medical School, Harvard University(Boston, USA)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-307] SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography ICLR2025

链接: https://arxiv.org/abs/2503.06118
作者: Xuanyu Zhang,Jiarui Meng,Zhipei Xu,Shuzhou Yang,Yanmin Wu,Ronggang Wang,Jian Zhang
机构: School of Electronic and Computer Engineering, Peking University (北京大学电子与计算机工程学院); Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School, Peking University (北京大学深圳研究生院超高清晰沉浸式媒体技术广东省重点实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by ICLR 2025

点击查看摘要

[CV-308] NeuraLoc: Visual Localization in Neural Implicit Map with Dual Complementary Features ICRA2025

链接: https://arxiv.org/abs/2503.06117
作者: Hongjia Zhai,Boming Zhao,Hai Li,Xiaokun Pan,Yijia He,Zhaopeng Cui,Hujun Bao,Guofeng Zhang
机构: State Key Lab of CAD&CG, Zhejiang University (浙江大学国家重点实验室); RayNeo (RayNeo)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: ICRA 2025

点击查看摘要

[CV-309] Feature Fusion Attention Network with CycleGAN for Image Dehazing De-Snowing and De-Raining

链接: https://arxiv.org/abs/2503.06107
作者: Akshat Jain
机构: IIT Bombay (印度理工学院孟买分校)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-310] Vision-aware Multimodal Prompt Tuning for Uploadable Multi-source Few-shot Domain Adaptation AAAI2025

链接: https://arxiv.org/abs/2503.06106
作者: Kuanghong Liu,Jin Wang,Kangjian He,Dan Xu,Xuejie Zhang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by AAAI 2025

点击查看摘要

[CV-311] Handwritten Digit Recognition: An Ensemble-Based Approach for Superior Performance

链接: https://arxiv.org/abs/2503.06104
作者: Syed Sajid Ullah,Li Gang,Mudassir Riaz,Ahsan Ashfaq,Salman Khan,Sajawal Khan
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 11 pages,6 figures

点击查看摘要

[CV-312] Patch-Depth Fusion: Dichotomous Image Segmentation via Fine-Grained Patch Strategy and Depth Integrity-Prior

链接: https://arxiv.org/abs/2503.06100
作者: Xianjie Liu,Keren Fu,Qijun Zhao
机构: Sichuan university (四川大学); College of Computer Science (计算机科学学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-313] PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentation

链接: https://arxiv.org/abs/2503.06094
作者: Yong He,Hongshan Yu,Mingtao Feng,Tongjia Chen,Zechuan Li,Anwaar Ulhaq,Saeed Anwar,Ajmal Saeed Mian
机构: Anhui University (安徽大学); Hunan University (湖南大学); Xidian University (西安电子科技大学); University of Western Australia (西澳大利亚大学); Central Queensland University (中央昆士兰大学); Australian National University (澳大利亚国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 3 figures, 7 tables

点击查看摘要

[CV-314] ZO-DARTS: An Efficient and Size-Variable Zeroth-Order Neural Architecture Search Algorithm

链接: https://arxiv.org/abs/2503.06092
作者: Lunchen Xie,Eugenio Lomurno,Matteo Gambella,Danilo Ardagna,Manual Roveri,Matteo Matteucci,Qingjiang Shi
机构: School of Computer Science and Technology, Tongji University, Shanghai, China (同济大学计算机科学与技术学院，中国上海); Shenzhen Research Institute of Big Data, Shenzhen, China (深圳大数据研究院，中国深圳); Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB), Politecnico di Milano, Milan, Italy (意大利米兰理工电子、信息与生物工程系(DEIB))
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 14 pages, 8 figures

点击查看摘要

[CV-315] Fish2Mesh Transformer: 3D Human Mesh Recovery from Egocentric Vision

链接: https://arxiv.org/abs/2503.06089
作者: David C. Jeong,Aditya Puranik,James Vong,Vrushabh Abhijit Deogirikar,Ryan Fell,Julianna Dietrich,Maria Kyrarini,Christopher Kitts
机构: Santa Clara University (圣克拉拉大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-316] Exploring Interpretability for Visual Prompt Tuning with Hierarchical Concepts

链接: https://arxiv.org/abs/2503.06084
作者: Yubin Wang,Xinyang Jiang,De Cheng,Xiangqian Zhao,Zilong Wang,Dongsheng Li,Cairong Zhao
机构: Microsoft Research Asia (微软研究院亚洲); Tongji University (同济大学); Xidian University (西安电子科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 9 figures

点击查看摘要

[CV-317] ransParking: A Dual-Decoder Transformer Framework with Soft Localization for End-to-End Automatic Parking

链接: https://arxiv.org/abs/2503.06071
作者: Hangyu Du,Chee-Meng Chew
机构: College of Design and Engineering, National University of Singapore (设计与工程学院, 新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-318] Multi-Layer Visual Feature Fusion in Multimodal LLM s: Methods Analysis and Best Practices CVPR2025

链接: https://arxiv.org/abs/2503.06063
作者: Junyan Lin,Haoran Chen,Yue Fan,Yingqi Fan,Xin Jin,Hui Su,Jinlan Fu,Xiaoyu Shen
机构: Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative (宁波空间智能与数字衍生重点实验室), Institute of Digital Twin (数字孪生研究院), EIT (Electronic Information Technology); Ocean University of China (中国海洋大学); Zhejiang Gongshang University (浙江工商大学); Genmo.ai; Meituan Inc. (美团); Engineering Research Center of Chiplet Design and Manufacturing of Zhejiang Province (浙江省Chiplet设计与制造工程研究中心); NUS (National University of Singapore, 新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR2025

点击查看摘要

[CV-319] STAR: A Foundation Model-driven Framework for Robust Task Planning and Failure Recovery in Robotic Systems

链接: https://arxiv.org/abs/2503.06060
作者: Md Sadman Sakib,Yu Sun
机构: University of South Florida (南佛罗里达大学)
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-320] Pathological Prior-Guided Multiple Instance Learning For Mitigating Catastrophic Forgetting in Breast Cancer Whole Slide Image Classification ICASSP2025

链接: https://arxiv.org/abs/2503.06056
作者: Weixi Zheng,Aoling Huang. Jingping Yuan,Haoyu Zhao,Zhou Zhao,Yongchao Xu,Thierry Géraud
机构: School of Computer Science, Wuhan University (武汉大学); Renmin Hospital of Wuhan University (武汉大学人民医院); School of Computer Science, Central China Normal University (华中师范大学); EPITA Research Laboratory (EPITA 研究实验室), Le Kremlin-Bicêtre, France
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: ICASSP2025(Oral)

点击查看摘要

[CV-321] DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation

链接: https://arxiv.org/abs/2503.06053
作者: Runze Zhang,Guoguang Du,Xiaochuan Li,Qi Jia,Liang Jin,Lu Liu,Jingjing Wang,Cong Xu,Zhenhua Guo,Yaqian Zhao,Xiaoli Gong,Rengang Li,Baoyu Fan
机构: IEIT System Co., Ltd. (IEIT系统有限公司); Nankai University (南开大学); Tsinghua University (清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-322] Improving SAM for Camouflaged Object Detection via Dual Stream Adapters

链接: https://arxiv.org/abs/2503.06042
作者: Jiaming Liu,Linghe Kong,Guihai Chen
机构: Department of Computer Science and Engineering, Shanghai Jiao Tong University (上海交通大学计算机科学与工程系)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-323] A Label-Free High-Precision Residual Moveout Picking Method for Travel Time Tomography based on Deep Learning

链接: https://arxiv.org/abs/2503.06038
作者: Hongtao Wang,Jiandong Liang,Lei Wang,Shuaizhe Liang,Jinping Zhu,Chunxia Zhang,Jiangshe Zhang
机构: School of Mathematics and Statistics, Xi’an Jiaotong University (西安交通大学数学与统计学院); China National Petroleum Corp Bureau of Geophysical Prospecting Inc, Geophysical Technology Research Center Zhuozhou, Hebei (中国石油集团东方物探研究院涿州分院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-324] owards Universal Text-driven CT Image Segmentation

链接: https://arxiv.org/abs/2503.06030
作者: Yuheng Li,Yuxiang Lai,Maria Thor,Deborah Marshall,Zachary Buchwald,David S. Yu,Xiaofeng Yang
机构: Department of Biomedical Engineering, Georgia Institute of Technology, Emory University (生物医学工程系, 佐治亚理工学院, 埃默里大学); Department of Medical Physics, Memorial Sloan Kettering Cancer Center (放射物理学系, 纪念斯隆凯特琳癌症中心); Department of Radiation Oncology, Icahn School of Medicine at Mount Sinai (放射肿瘤学系, 西奈山伊坎医学院); Department of Radiation Oncology, Emory University School of Medicine (放射肿瘤学系, 埃默里大学医学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-325] Zero-Shot Peg Insertion: Identifying Mating Holes and Estimating SE(2) Poses with Vision-Language Models

链接: https://arxiv.org/abs/2503.06026
作者: Masaru Yajima,Kei Ota,Asako Kanezaki,Rei Kawakami
机构: Institute of Science Tokyo (东京科学研究所); Mitsubishi Electric (三菱电机)
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: Under submission

点击查看摘要

[CV-326] owards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity

链接: https://arxiv.org/abs/2503.06014
作者: Xiaohao Xu,Feng Xue,Xiang Li,Haowei Li,Shusheng Yang,Tianyi Zhang,Matthew Johnson-Roberson,Xiaonan Huang
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: 32 pages, 31 figures, github repo: this https URL

点击查看摘要

[CV-327] End-to-End HOI Reconstruction Transformer with Graph-based Encoding

链接: https://arxiv.org/abs/2503.06012
作者: Zhenrong Wang,Qi Zheng,Sihan Ma,Maosheng Ye,Yibing Zhan,Dongjiang Li
机构: Shenzhen University (深圳大学); University of Sydney (悉尼大学); DeepRoute.AI; JD Explore Academy
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-328] Integrating Frequency-Domain Representations with Low-Rank Adaptation in Vision-Language Models

链接: https://arxiv.org/abs/2503.06003
作者: Md Azim Khan,Aryya Gangopadhyay,Jianwu Wang,Robert F. Erbacher
机构: University of Maryland Baltimore County (UMBC)(马里兰大学巴尔的摩郡分校); Center for Real-time Distributed Sensing and Autonomy (CARDS), UMBC (实时分布式传感与自主性研究中心，UMBC); DEVCOM Army Research Laboratory (阿德尔菲，马里兰州，美国陆军研究实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 4 figures

点击查看摘要

[CV-329] MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice WWW

链接: https://arxiv.org/abs/2503.05978
作者: Hongwei Yi,Tian Ye,Shitong Shao,Xuancheng Yang,Jiantong Zhao,Hanzhong Guo,Terrance Wang,Qingyu Yin,Zeke Xie,Lei Zhu,Wei Li,Michael Lingelbach,Daquan Zhou
机构: Hedra Inc. (Hedra Inc.); Peking University (北京大学); HKUST(GZ) (香港科技大学（广州）); HKU (香港大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: MagicInfinite is publicly accessible at this https URL . More examples are at this https URL

点击查看摘要

[CV-330] Is Your Video Language Model a Reliable Judge?

链接: https://arxiv.org/abs/2503.05977
作者: Ming Liu,Wensheng Zhang
机构: Department of Computer Science, Iowa State University (爱荷华州立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-331] OSCAR: Object Status and Contextual Awareness for Recipes to Support Non-Visual Cooking

链接: https://arxiv.org/abs/2503.05962
作者: Franklin Mingzhe Li,Kaitlyn Ng,Bin Zhu,Patrick Carrington
机构: Carnegie Mellon University (卡内基梅隆大学); Carnegie Mellon University (卡内基梅隆大学); Singapore Management University (新加坡管理大学)
类目: Human-Computer Interaction (cs.HC); Computer Vision and Pattern Recognition (cs.CV)
备注: CHI 2025 Late Breaking Work

点击查看摘要

[CV-332] Bayesian Fields: Task-driven Open-Set Semantic Gaussian Splatting

链接: https://arxiv.org/abs/2503.05949
作者: Dominic Maggio,Luca Carlone
机构: Laboratory for Information & Decision Systems, Massachusetts Institute of Technology (麻省理工学院信息系统实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-333] CASP: Compression of Large Multimodal Models Based on Attention Sparsity

链接: https://arxiv.org/abs/2503.05936
作者: Mohsen Gholami,Mohammad Akbari,Kevin Cannons,Yong Zhang
机构: Huawei Technologies Canada Co., Ltd. (华为加拿大技术有限公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-334] Generalizable Image Repair for Robust Visual Autonomous Racing IROS2025

链接: https://arxiv.org/abs/2503.05911
作者: Carson Sobolewski,Zhenjiang Mao,Kshitij Vejre,Ivan Ruchkin
机构: Trustworthy Engineered Autonomy (TEA) Lab, Department of Electrical and Computer Engineering, University of Florida (佛罗里达大学)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 4 figures, Submitted to 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)

点击查看摘要

[CV-335] Encrypted Vector Similarity Computations Using Partially Homomorphic Encryption: Applications and Performance Analysis

链接: https://arxiv.org/abs/2503.05850
作者: Sefik Serengil,Alper Ozpinar
机构: Vorboss Limited (Vorboss 有限公司); Department of Business, Ibn Haldun University (工商管理系, 伊本哈杜恩大学)
类目: Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-336] Enhancing AUTOSAR-Based Firmware Over-the-Air Updates in the Automotive Industry with a Practical Implementation on a Steering System

链接: https://arxiv.org/abs/2503.05839
作者: Mostafa Ahmed Mostafa Ahmed,Mohamed Khaled Mohamed Elsayed,Radwa Waheed Ezzat Abdelmohsen
机构: 未知
类目: Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV); Systems and Control (eess.SY)
备注: Bachelor’s thesis

点击查看摘要

[CV-337] Randomized based restricted kernel machine for hyperspectral image classification

链接: https://arxiv.org/abs/2503.05837
作者: A. Quadir,M. Tanveer
机构: IIT Indore(印度理工学院印多尔分校)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-338] NeAS: 3D Reconstruction from X-ray Images using Neural Attenuation Surface

链接: https://arxiv.org/abs/2503.07491
作者: Chengrui Zhu,Ryoichi Ishikawa,Masataka Kagesawa,Tomohisa Yuzawa,Toru Watsuji,Takeshi Oishi
机构: The Institute of Industrial Science, The University of Tokyo (东京大学产业技术研究所), Japan; Air Water Inc. (日本碍滨株式会社), Minami Semba, Chuo-ku, Osaka, Japan
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-339] Skelite: Compact Neural Networks for Efficient Iterative Skeletonization

链接: https://arxiv.org/abs/2503.07369
作者: Luis D. Reyes Vargas,Martin J. Menten,Johannes C. Paetzold,Nassir Navab,Mohammad Farid Azampour
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-340] AI-Driven Automated Tool for Abdominal CT Body Composition Analysis in Gastrointestinal Cancer Management

链接: https://arxiv.org/abs/2503.07248
作者: Xinyu Nan,Meng He,Zifan Chen,Bin Dong,Lei Tang,Li Zhang
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:

点击查看摘要

[CV-341] he 4D Human Embryonic Brain Atlas: spatiotemporal atlas generation for rapid anatomical changes using first-trimester ultrasound from the Rotterdam Periconceptional Cohort

链接: https://arxiv.org/abs/2503.07177
作者: Wietske A.P. Bastiaansen,Melek Rousian,Anton H.J. Koning,Wiro J. Niessen,Bernadette S. de Bakker,Régine P.M. Steegers-Theunissen,Stefan Klein
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Quantitative Methods (q-bio.QM)
备注:

点击查看摘要

[CV-342] Global Context Is All You Need for Parallel Efficient Tractography Parcellation

链接: https://arxiv.org/abs/2503.07104
作者: Valentin von Bornhaupt,Johannes Grün,and Justus Bisten,Tobias Bauer,Theodor Rüber,Thomas Schultz
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
备注: 8 pages, 2 pages references, 3 figures, 2 tables

点击查看摘要

[CV-343] A Comprehensive Survey on Magnetic Resonance Image Reconstruction

链接: https://arxiv.org/abs/2503.07097
作者: Xiaoyan Kui,Zijie Fan,Zexin Ji,Qinsong Li,Chengtao Liu,Weixin Si,Beiji Zou
机构: School of Computer Science and Engineering, Central South University (中南大学计算机科学与工程学院), Changsha, 410083, China; Big Data Institute, Central South University (中南大学大数据研究院), Changsha, 410083, Hunan, China; Shenzhen Institute of Advanced Technology, Chinese Academy of Science (中国科学院深圳先进技术研究院), Shenzheng, 518055, Guangdong, China
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-344] Dynamic Cross-Modal Feature Interaction Network for Hyperspectral and LiDAR Data Classification

链接: https://arxiv.org/abs/2503.06945
作者: Junyan Lin,Feng Gap,Lin Qi,Junyu Dong,Qian Du,Xinbo Gao
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by IEEE TGRS 2025

点击查看摘要

[CV-345] CAFusion: Controllable Anatomical Synthesis of Perirectal Lymph Nodes via SDF-guided Diffusion

链接: https://arxiv.org/abs/2503.06919
作者: Weidong Guo,Hantao Zhang,Shouhong Wan,Bingbing Zou,Wanqin Wang,Chenyang Qiu,Peiquan Jin
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-346] owards a Multimodal MRI-Based Foundation Model for Multi-Level Feature Exploration in Segmentation Molecular Subtyping and Grading of Glioma

链接: https://arxiv.org/abs/2503.06828
作者: Somayeh Farahani,Marjaneh Hejazi,Antonio Di Ieva,Emad Fatemizadeh,Sidong Liu
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:

点击查看摘要

[CV-347] wo-stage Deep Denoising with Self-guided Noise Attention for Multimodal Medical Images

链接: https://arxiv.org/abs/2503.06827
作者: S M A Sharif,Rizwan Ali Naqvi,Woong-Kee Loh
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注: IEEE Transactions on Radiation and Plasma Medical Sciences (2024)

点击查看摘要

[CV-348] Semi-Supervised Medical Image Segmentation via Knowledge Mining from Large Models

链接: https://arxiv.org/abs/2503.06816
作者: Yuchen Mao,Hongwei Li,Yinyi Lai,Giorgos Papanastasiou,Peng Qi,Yunjie Yang,Chengjia Wang
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: 18 pages, 2 figures

点击查看摘要

[CV-349] Interactive Tumor Progression Modeling via Sketch-Based Image Editing

链接: https://arxiv.org/abs/2503.06809
作者: Gexin Huang,Ruinan Jin,Yucheng Tang,Can Zhao,Tatsuya Harada,Xiaoxiao Li,Gu Lin
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages, 4 figures

点击查看摘要

[CV-350] X-GAN: A Generative AI-Powered Unsupervised Model for High-Precision Segmentation of Retinal Main Vessels toward Early Detection of Glaucoma

链接: https://arxiv.org/abs/2503.06743
作者: Cheng Huang,Weizheng Xie,Tsengdar J. Lee,Jui-Kai Wang,Karanjit Kooner,Jia Zhang
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注: 11 pages, 8 figures

点击查看摘要

[CV-351] ImplicitCell: Resolution Cell Modeling of Joint Implicit Volume Reconstruction and Pose Refinement in Freehand 3D Ultrasound

链接: https://arxiv.org/abs/2503.06686
作者: Sheng Song,Yiting Chen,Duo Xu,Songhan Ge,Yunqian Huang,Junni Shi,Man Chen,Hongbo Chen,Rui Zheng
机构: School of Information Science and Technology, ShanghaiTech University (上海科技大学信息科学与技术学院); Tongren Hospital, Shanghai Jiao Tong University School of Medicine (上海交通大学医学院附属同仁医院); School of Information Science and Technology, Shanghai Engineering Research Center of Energy Efficient and Custom AI IC, ShanghaiTech University (上海科技大学信息科学与技术学院，上海高效能定制化人工智能集成电路工程研究中心)
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-352] LSA: Latent Style Augmentation Towards Stain-Agnostic Cervical Cancer Screening

链接: https://arxiv.org/abs/2503.06563
作者: Jiangdong Cai,Haotian Jiang,Zhenrong Shen,Yonghao Li,Honglin Xiong,Lichi Zhang,Qian Wang
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:

点击查看摘要

[CV-353] X-LRM: X-ray Large Reconstruction Model for Extremely Sparse-View Computed Tomography Recovery in One Second

链接: https://arxiv.org/abs/2503.06382
作者: Guofeng Zhang,Ruyi Zha,Hao He,Yixun Liang,Alan Yuille,Hongdong Li,Yuanhao Cai
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注: A large reconstruction model and the largest dataset (16K samples) for sparse-view CT recovery

点击查看摘要

[CV-354] Enhanced Pediatric Dental Segmentation Using a Custom SegUNet with VGG19 Backbone on Panoramic Radiographs

链接: https://arxiv.org/abs/2503.06321
作者: Md Ohiduzzaman Ovi,Maliha Sanjana,Fahad Fahad,Mahjabin Runa,Zarin Tasnim Rothy,Tanmoy Sarkar Pias,A.M. Tayeful Islam,Rumman Ahmed Prodhan
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-355] Attention on the Wires (AttWire): A Foundation Model for Detecting Devices and Catheters in X-ray Fluoroscopic Images

链接: https://arxiv.org/abs/2503.06190
作者: YingLiang Ma,Sandra Howell,Aldo Rinaldi,Tarv Dhanjal,Kawal S. Rhode
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-356] RGB-Phase Speckle: Cross-Scene Stereo 3D Reconstruction via Wrapped Pre-Normalization ICCV2025

链接: https://arxiv.org/abs/2503.06125
作者: Kai Yang,Zijian Bai,Yang Xiao,Xinyu Li,Xiaohan Shi
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注: Submitted to ICCV 2025

点击查看摘要

[CV-357] Pathology-Guided AI System for Accurate Segmentation and Diagnosis of Cervical Spondylosis

链接: https://arxiv.org/abs/2503.06114
作者: Qi Zhang,Xiuyuan Chen,Ziyi He,Lianming Wu,Kun Wang,Jianqi Sun,Hongxing Shen
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-358] GrInAdapt: Scaling Retinal Vessel Structural Map Segmentation Through Grounding Integrating and Adapting Multi-device Multi-site and Multi-modal Fundus Domains

链接: https://arxiv.org/abs/2503.05991
作者: Zixuan Liu,Aaron Honjaya,Yuekai Xu,Yi Zhang,Hefu Pan,Xin Wang,Linda G Shapiro,Sheng Wang,Ruikang K Wang
机构: 未知
类目: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-359] HealthiVert-GAN: A Novel Framework of Pseudo-Healthy Vertebral Image Synthesis for Interpretable Compression Fracture Grading

链接: https://arxiv.org/abs/2503.05990
作者: Qi Zhang,Shunan Zhang,Ziqi Zhao,Kun Wang,Jun Xu,Jianqi Sun
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-360] LapLoss: Laplacian Pyramid-based Multiscale loss for Image Translation ICLR2025

链接: https://arxiv.org/abs/2503.05974
作者: Krish Didwania,Ishaan Gakhar,Prakhar Arya,Sanskriti Labroo
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at the DeLTa Workshop, ICLR 2025

点击查看摘要

[CV-361] Beyond HE: Unlocking Pathological Insights with Polarization via Self-supervised Learning

链接: https://arxiv.org/abs/2503.05933
作者: Yao Du,Jiaxin Zhuang,Xiaoyu Zheng,Jing Cong,Limei Guo,Chao He,Lin Luo,Xiaomeng Li
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-362] SAS: Segment Anything Small for Ultrasound – A Non-Generative Data Augmentation Technique for Robust Deep Learning in Ultrasound Imaging

链接: https://arxiv.org/abs/2503.05916
作者: Danielle L. Ferreira,Ahana Gangopadhyay,Hsi-Ming Chang,Ravi Soni,Gopal Avinash
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: 25 pages, 8 figures

点击查看摘要

[CV-363] Decadal analysis of sea surface temperature patterns climatology and anomalies in temperate coastal waters with Landsat-8 TIRS observations

链接: https://arxiv.org/abs/2503.05843
作者: Yiqing Guo,Nagur Cherukuru,Eric Lehmann,Xiubin Qi,Mark Doubelld,S. L. Kesav Unnithan,Ming Feng
机构: 未知
类目: Atmospheric and Oceanic Physics (physics.ao-ph); Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV); Signal Processing (eess.SP); Geophysics (physics.geo-ph)
备注: Submitted to GIScience Remote Sensing

点击查看摘要

[CV-364] Illuminant and light direction estimation using Wasserstein distance method

链接: https://arxiv.org/abs/2503.05802
作者: Selcuk Yazar
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:

点击查看摘要

人工智能

[AI-0] A Representationalist Functionalist and Naturalistic Conception of Intelligence as a Foundation for AGI

链接: https://arxiv.org/abs/2503.07600
作者: Rolf Pfister
类目: Artificial Intelligence (cs.AI); Robotics (cs.RO)
*备注:

点击查看摘要

[AI-1] NeuroChat: A Neuroadaptive AI Chatbot for Customizing Learning Experiences

链接: https://arxiv.org/abs/2503.07599
作者: Dünya Baradari,Nataliya Kosmyna,Oscar Petrov,Rebecah Kaplun,Pattie Maes
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET)
*备注: 16 pages, 6 figures, 1 table

点击查看摘要

[AI-2] Denoising Hamiltonian Network for Physical Reasoning

链接: https://arxiv.org/abs/2503.07596
作者: Congyue Deng,Brandon Y. Feng,Cecilia Garraffo,Alan Garbarz,Robin Walters,William T. Freeman,Leonidas Guibas,Kaiming He
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-3] Runtime Detection of Adversarial Attacks in AI Accelerators Using Performance Counters

链接: https://arxiv.org/abs/2503.07568
作者: Habibur Rahaman,Atri Chatterjee,Swarup Bhunia
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: 7 pages, 8 figures

点击查看摘要

[AI-4] Inductive Moment Matching

链接: https://arxiv.org/abs/2503.07565
作者: Linqi Zhou,Stefano Ermon,Jiaming Song
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
*备注:

点击查看摘要

[AI-5] Queueing Predictions and LLM s: Challenges and Open Problems

链接: https://arxiv.org/abs/2503.07545
作者: Michael Mitzenmacher,Rana Shahout
类目: Artificial Intelligence (cs.AI); Data Structures and Algorithms (cs.DS)
*备注:

点击查看摘要

[AI-6] Geometric Retargeting: A Principled Ultrafast Neural Hand Retargeting Algorithm

链接: https://arxiv.org/abs/2503.07541
作者: Zhao-Heng Yin,Changhao Wang,Luis Pineda,Krishna Bodduluri,Tingfan Wu,Pieter Abbeel,Mustafa Mukadam
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Graphics (cs.GR); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
*备注: Project Website: this https URL

点击查看摘要

[AI-7] AI-Enabled Knowledge Sharing for Enhanced Collaboration and Decision-Making in Non-Profit Healthcare Organizations: A Scoping Review Protocol

链接: https://arxiv.org/abs/2503.07540
作者: Maurice Ongala,Ruth Kiraka,Jyoti Choundrie,Javan Okello
类目: Artificial Intelligence (cs.AI)
*备注: 14 pages

点击查看摘要

[AI-8] Interference-Aware Super-Constellation Design for NOMA

链接: https://arxiv.org/abs/2503.07509
作者: Mojtaba Vaezi,Xinliang Zhang
类目: Information Theory (cs.IT); Artificial Intelligence (cs.AI); Signal Processing (eess.SP)
*备注: Accepted for publication at IEEE International Conference on Communications (ICC), 2025

点击查看摘要

[AI-9] From Centralized to Decentralized Federated Learning: Theoretical Insights Privacy Preservation and Robustness Challenges

链接: https://arxiv.org/abs/2503.07505
作者: Qiongxiu Li,Wenrui Yu,Yufei Xia,Jun Pang
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注:

点击查看摘要

[AI-10] Efficient Membership Inference Attacks by Bayesian Neural Network

链接: https://arxiv.org/abs/2503.07482
作者: Zhenlong Liu,Wenyu Jiang,Feng Zhou,Hongxin Wei
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 8 pages, under review

点击查看摘要

[AI-11] Advancing Vietnamese Information Retrieval with Learning Objective and Benchmark

链接: https://arxiv.org/abs/2503.07470
作者: Phu-Vinh Nguyen,Minh-Nam Tran,Long Nguyen,Dien Dinh
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-12] From Idea to Implementation: Evaluating the Influence of Large Language Models in Software Development – An Opinion Paper

链接: https://arxiv.org/abs/2503.07450
作者: Sargam Yadav(1),Asifa Mehmood Qureshi(1),Abhishek Kaushik(1),Shubham Sharma(2),Roisin Loughran(1),Subramaniam Kazhuparambil(3),Andrew Shaw(1),Mohammed Sabry(4),Niamh St John Lynch(1). Nikhil Singh(5),Padraic O’Hara(1),Pranay Jaiswal(1),Roshan Chandru(1),David Lillis(6) ((1) School of Informatics and Creative Arts, Dundalk Institute of Technology, Dundalk, Ireland, (2) The Centre for Research in Engineering Surface Technology (CREST) TU Dublin Dublin, Ireland, (3) Zendesk, Dublin, Ireland, (4) ADAPT Centre Dublin, Ireland, (5) National College of Ireland, Dublin, Ireland, (6) University College Dublin (UCD) Dundalk, Ireland )
类目: Artificial Intelligence (cs.AI)
*备注: The project is partially supported by the DkIT Postgraduate Scholarship, Research Ireland under Grant number 13/RC/2094_2, and Grant number 21/FFP-A/925

点击查看摘要

[AI-13] From Text to Visuals: Using LLM s to Generate Math Diagrams with Vector Graphics

链接: https://arxiv.org/abs/2503.07429
作者: Jaewook Lee,Jeongah Lee,Wanyong Feng,Andrew Lan
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-14] RePO: ReLU-based Preference Optimization

链接: https://arxiv.org/abs/2503.07426
作者: Junkang Wu,Kexin Huang,Xue Wang,Jinyang Gao,Bolin Ding,Jiancan Wu,Xiangnan He,Xiang Wang
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-15] Artificial Utopia: Simulation and Intelligent Agents for a Democratised Future

链接: https://arxiv.org/abs/2503.07364
作者: Yannick Oswald
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
*备注:

点击查看摘要

[AI-16] Encoding Argumentation Frameworks to Propositional Logic Systems

链接: https://arxiv.org/abs/2503.07351
作者: Shuai Tang,Jiachao Wu,Ning Zhou
类目: Artificial Intelligence (cs.AI); Logic (math.LO)
*备注: 31 pages

点击查看摘要

[AI-17] Research and Design on Intelligent Recognition of Unordered Targets for Robots Based on Reinforcement Learning

链接: https://arxiv.org/abs/2503.07340
作者: Yiting Mao,Dajun Tao,Shengyuan Zhang,Tian Qi,Keqin Li
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-18] mporal Triplane Transformers as Occupancy World Models

链接: https://arxiv.org/abs/2503.07338
作者: Haoran Xu,Peixi Peng,Guang Tan,Yiqian Chang,Yisen Zhao,Yonghong Tian
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-19] AI Biases as Asymmetries: A Review to Guide Practice

链接: https://arxiv.org/abs/2503.07326
作者: Gabriella Waters,Phillip Honenberger
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: 24 pages

点击查看摘要

[AI-20] Experimental Exploration: Investigating Cooperative Interaction Behavior Between Humans and Large Language Model Agents

链接: https://arxiv.org/abs/2503.07320
作者: Guanxuan Jiang,Yuyang Wang,Pan Hui
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-21] Human Machine Co-Adaptation Model and Its Convergence Analysis

链接: https://arxiv.org/abs/2503.07319
作者: Steven W. Su,Yaqi Li,Kairui Guo,Rob Duffield
类目: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA); Robotics (cs.RO)
*备注:

点击查看摘要

[AI-22] Self-Corrective Task Planning by Inverse Prompting with Large Language Models ICRA

链接: https://arxiv.org/abs/2503.07317
作者: Jiho Lee,Hayun Lee,Jonghyeon Kim,Kyungjae Lee,Eunwoo Kim
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注: 7 pages, 5 figures, IEEE International Conference on Robotics and Automation (ICRA) 2025

点击查看摘要

[AI-23] Automatic Curriculum Design for Zero-Shot Human-AI Coordination

链接: https://arxiv.org/abs/2503.07275
作者: Won-Sang You,Tae-Gwan Ha,Seo-Young Lee,Kyung-Joong Kim
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-24] Federated Learning in NTNs: Design Architecture and Challenges

链接: https://arxiv.org/abs/2503.07272
作者: Amin Farajzadeh,Animesh Yadav,Halim Yanikomeroglu
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI); Signal Processing (eess.SP)
*备注: Accepted in IEEE Communications Magazine

点击查看摘要

[AI-25] Discrete Gaussian Process Representations for Optimising UAV-based Precision Weed Mapping

链接: https://arxiv.org/abs/2503.07210
作者: Jacob Swindell,Madeleine Darbyshire,Marija Popovic,Riccardo Polvara
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-26] A Zero-shot Learning Method Based on Large Language Models for Multi-modal Knowledge Graph Embedding

链接: https://arxiv.org/abs/2503.07202
作者: Bingchen Liu,Jingchen Li,Naixing Xu,Xin Li
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-27] Lawful and Accountable Personal Data Processing with GDPR-based Access and Usage Control in Distributed Systems

链接: https://arxiv.org/abs/2503.07172
作者: L. Thomas van Binsbergen,Marten C. Steketee,Milen G. Kebede,Heleen L. Janssen,Tom M. van Engers
类目: Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO); Software Engineering (cs.SE)
*备注: Submitted for review to the Journal of AI and Law, 49 pages (including)

点击查看摘要

[AI-28] Generative AI in Transportation Planning : A Survey

链接: https://arxiv.org/abs/2503.07158
作者: Longchao Da,Tiejin Chen,Zhuoheng Li,Shreyas Bachiraju,Huaiyuan Yao,Xiyang Hu,Zhengzhong Tu,Yue Zhao,Dongjie Wang,Xuanyu(Ben)Zhou,Ram Pendyala,Benjamin Stabler,Yezhou Yang,Xuesong Zhou,Hua Wei
类目: Artificial Intelligence (cs.AI)
*备注: 56 pages

点击查看摘要

[AI-29] Ideas in Inference-time Scaling can Benefit Generative Pre-training Algorithms

链接: https://arxiv.org/abs/2503.07154
作者: Jiaming Song,Linqi Zhou
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-30] PTMs-TSCIL Pre-Trained Models Based Class-Incremental Learning

链接: https://arxiv.org/abs/2503.07153
作者: Yuanlong Wu,Mingxing Nie,Tao Zhu,Liming Chen,Huansheng Ning,Yaping Wan
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 13 pages,6 figures

点击查看摘要

[AI-31] Hierarchical Neuro-Symbolic Decision Transformer

链接: https://arxiv.org/abs/2503.07148
作者: Ali Baheri,Cecilia O. Alm
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Systems and Control (eess.SY)
*备注:

点击查看摘要

[AI-32] A Comprehensive Survey of Mixture-of-Experts: Algorithms Theory and Applications

链接: https://arxiv.org/abs/2503.07137
作者: Siyuan Mu,Sen Lin
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 28 pages, 3 figures

点击查看摘要

[AI-33] Correctness Learning: Deductive Verification Guided Learning for Human-AI Collaboration

链接: https://arxiv.org/abs/2503.07096
作者: Zhao Jin,Lu Jin,Yizhe Luo,Shuo Feng,Yucheng Shi,Kai Zheng,Xinde Yu,Mingliang Xu
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-34] An Experience Report on Regression-Free Repair of Deep Neural Network Model

链接: https://arxiv.org/abs/2503.07079
作者: Takao Nakagawa,Susumu Tokumoto,Shogo Tokui,Fuyuki Ishikawa
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-35] Rule-Based Conflict-Free Decision Framework in Swarm Confrontation

链接: https://arxiv.org/abs/2503.07077
作者: Zhaoqi Dong,Zhinan Wang,Quanqi Zheng,Bin Xu,Lei Chen,Jinhu Lv
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-36] PIED: Physics-Informed Experimental Design for Inverse Problems ICLR2025

链接: https://arxiv.org/abs/2503.07070
作者: Apivich Hemachandra,Gregory Kang Ruey Lau,See-Kiong Ng,Bryan Kian Hsiang Low
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computational Physics (physics.comp-ph); Data Analysis, Statistics and Probability (physics.data-an); Machine Learning (stat.ML)
*备注: Accepted to 13th International Conference on Learning Representations (ICLR 2025), 31 pages

点击查看摘要

[AI-37] Generative method for aerodynamic optimization based on classifier-free guided denoising diffusion probabilistic model

链接: https://arxiv.org/abs/2503.07056
作者: Shisong Deng,Qiang Zhang,Zhengyang Cai
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: Under Review

点击查看摘要

[AI-38] Weak Supervision for Improved Precision in Search Systems AAAI2025

链接: https://arxiv.org/abs/2503.07025
作者: Sriram Vasudevan
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: Accepted to the AAAI 2025 Workshop on Computational Jobs Marketplace

点击查看摘要

[AI-39] Combating Partial Perception Deficit in Autonomous Driving with Multimodal LLM Commonsense

链接: https://arxiv.org/abs/2503.07020
作者: Yuting Hu,Chenhui Xu,Ruiyang Qin,Dancheng Liu,Amir Nassereldine,Yiyu Shi,Jinjun Xiong
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-40] Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization

链接: https://arxiv.org/abs/2503.06982
作者: Ziqing Xu,Hancheng Min,Lachlan Ewen MacDonald,Jinqi Luo,Salma Tarmoun,Enrique Mallada,Rene Vidal
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-41] Multi-Behavior Recommender Systems: A Survey PAKDD2025

链接: https://arxiv.org/abs/2503.06963
作者: Kyungho Kim,Sunwoo Kim,Geon Lee,Jinhong Jung,Kijung Shin
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
*备注: Accepted in the PAKDD 2025 Survey Track

点击查看摘要

[AI-42] Capture Global Feature Statistics for One-Shot Federated Learning AAAI2025

链接: https://arxiv.org/abs/2503.06962
作者: Zenghao Guan,Yucan Zhou,Xiaoyan Gu
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: AAAI 2025

点击查看摘要

[AI-43] ReAgent : Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA

链接: https://arxiv.org/abs/2503.06951
作者: Zhao Xinjie,Fan Gao,Rui Yang,Yingjian Chen,Yuyang Wang,Ying Zhu,Jiacheng Tang,Irene Li
类目: Artificial Intelligence (cs.AI)
*备注: 25pages, 3 figures

点击查看摘要

[AI-44] Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning

链接: https://arxiv.org/abs/2503.06893
作者: Zhenghai Xue,Lang Feng,Jiacheng Xu,Kang Kang,Xiang Wen,Bo An,Shuicheng Yan
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: Preprint. Under Review

点击查看摘要

[AI-45] Enhancing Time Series Forecasting via Logic-Inspired Regularization

链接: https://arxiv.org/abs/2503.06867
作者: Jianqi Zhang,Jingyao Wang,Xingchen Shen,Wenwen Qiang
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-46] Graphormer-Guided Task Planning : Beyond Static Rules with LLM Safety Perception

链接: https://arxiv.org/abs/2503.06866
作者: Wanjing Huang,Tongjie Pan,Yalan Ye
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-47] Can Proof Assistants Verify Multi-Agent Systems?

链接: https://arxiv.org/abs/2503.06812
作者: Julian Alfredo Mendez,Timotheus Kampik
类目: Programming Languages (cs.PL); Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO); Multiagent Systems (cs.MA)
*备注:

点击查看摘要

[AI-48] Mitigating Preference Hacking in Policy Optimization with Pessimism

链接: https://arxiv.org/abs/2503.06810
作者: Dhawal Gupta,Adam Fisch,Christoph Dann,Alekh Agarwal
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-49] Privacy Auditing of Large Language Models ICLR2025

链接: https://arxiv.org/abs/2503.06808
作者: Ashwinee Panda,Xinyu Tang,Milad Nasr,Christopher A. Choquette-Choo,Prateek Mittal
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: ICLR 2025

点击查看摘要

[AI-50] Actionable AI: Enabling Non Experts to Understand and Configure AI Systems

链接: https://arxiv.org/abs/2503.06803
作者: Cécile Boulard,Sruthi Viswanathan,Wanda Fey,Thierry Jacquin
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-51] Characterizing Learning in Spiking Neural Networks with Astrocyte-Like Units

链接: https://arxiv.org/abs/2503.06798
作者: Christopher S. Yang,Sylvester J. Gates III,Dulara De Zoysa,Jaehoon Choe,Wolfgang Losert,Corey B. Hart
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Biological Physics (physics.bio-ph)
*备注: 6 pages, 4 figures

点击查看摘要

[AI-52] AutoMisty: A Multi-Agent LLM Framework for Automated Code Generation in the Misty Social Robot

链接: https://arxiv.org/abs/2503.06791
作者: Xiao Wang,Lu Dong,Sahana Rangasrinivasan,Ifeoma Nwogu,Srirangaraj Setlur,Venugopal Govindaraju
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA)
*备注:

点击查看摘要

[AI-53] Dubito Ergo Sum: Exploring AI Ethics

链接: https://arxiv.org/abs/2503.06788
作者: Viktor Dorfler,Giles Cuthbert
类目: Artificial Intelligence (cs.AI)
*备注: 10 pages, 1 figure, HICSS 57: Hawaii International Conference on System Sciences, Honolulu, HI, published January 2024

点击查看摘要

[AI-54] Fully-Decentralized MADDPG with Networked Agents

链接: https://arxiv.org/abs/2503.06747
作者: Diego Bolliger,Lorenz Zauter,Robert Ziegler
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
*备注:

点击查看摘要

[AI-55] Beyond Black-Box Benchmarking: Observability Analytics and Optimization of Agent ic Systems

链接: https://arxiv.org/abs/2503.06745
作者: Dany Moshkovich,Hadar Mulian,Sergey Zeltyn,Natti Eder,Inna Skarbovsky,Roy Abitbol
类目: Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
*备注: 14 pages, 19 figures

点击查看摘要

[AI-56] ACAI for SBOs: AI Co-creation for Advertising and Inspiration for Small Business Owners

链接: https://arxiv.org/abs/2503.06729
作者: Nimisha Karnatak,Adrien Baranes,Rob Marchant,Triona Butler,Kristen Olson
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Emerging Technologies (cs.ET)
*备注:

点击查看摘要

[AI-57] Pull-Based Query Scheduling for Goal-Oriented Semantic Communication

链接: https://arxiv.org/abs/2503.06725
作者: Pouya Agheli,Nikolaos Pappas,Marios Kountouris
类目: Information Theory (cs.IT); Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI)
*备注: Submitted for possible publication

点击查看摘要

[AI-58] Censoring-Aware Tree-Based Reinforcement Learning for Estimating Dynamic Treatment Regimes with Censored Outcomes

链接: https://arxiv.org/abs/2503.06690
作者: Animesh Kumar Paul,Russell Greiner
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Methodology (stat.ME)
*备注:

点击查看摘要

[AI-59] UniGenX: Unified Generation of Sequence and Structure with Autoregressive Diffusion

链接: https://arxiv.org/abs/2503.06687
作者: Gongbo Zhang,Yanting Li,Renqian Luo,Pipi Hu,Zeru Zhao,Lingbo Li,Guoqing Liu,Zun Wang,Ran Bi,Kaiyuan Gao,Liya Guo,Yu Xie,Chang Liu,Jia Zhang,Tian Xie,Robert Pinsler,Claudio Zeni,Ziheng Lu,Yingce Xia,Marwin Segler,Maik Riechert,Li Yuan,Lei Chen,Haiguang Liu,Tao Qin
类目: Machine Learning (cs.LG); Materials Science (cond-mat.mtrl-sci); Artificial Intelligence (cs.AI); Biological Physics (physics.bio-ph); Chemical Physics (physics.chem-ph)
*备注:

点击查看摘要

[AI-60] Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets ICLR2025

链接: https://arxiv.org/abs/2503.06664
作者: Tommaso Bendinelli,Artur Dox,Christian Holz
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 14 pages, 1 main figure, 3 plots, Published at ICLR 2025 Workshop on Foundation Models in the Wild

点击查看摘要

[AI-61] Deep Cut-informed Graph Embedding and Clustering

链接: https://arxiv.org/abs/2503.06635
作者: Zhiyuan Ning,Zaitian Wang,Ran Zhang,Ping Xu,Kunpeng Liu,Pengyang Wang,Chong Chen,Pengfei Wang,Yuanchun Zhou,Erik Cambria
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-62] BTFL: A Bayesian-based Test-Time Generalization Method for Internal and External Data Distributions in Federated learning KDD2025

链接: https://arxiv.org/abs/2503.06633
作者: Yu Zhou,Bingyan Liu
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: accepted as KDD 2025 research track paper

点击查看摘要

[AI-63] Hardware-Accelerated Event-Graph Neural Networks for Low-Latency Time-Series Classification on SoC FPGA

链接: https://arxiv.org/abs/2503.06629
作者: Hiroshi Nakano,Krzysztof Blachut,Kamil Jeziorek,Piotr Wzorek,Manon Dampfhoffer,Thomas Mesquida,Hiroaki Nishi,Tomasz Kryjak,Thomas Dalgaty
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Signal Processing (eess.SP)
*备注: Paper accepted for the 21st International Symposium on Applied Reconfigurable Computing ARC 2025, Sevilla, Spain, April 9-11, 2025

点击查看摘要

[AI-64] Using Subgraph GNNs for Node Classification:an Overlooked Potential Approach

链接: https://arxiv.org/abs/2503.06614
作者: Qian Zeng,Xin Lin,Jingyi Gao,Yang Yu
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 16 pages

点击查看摘要

[AI-65] Agent models: Internalizing Chain-of-Action Generation into Reasoning models

链接: https://arxiv.org/abs/2503.06580
作者: Yuxiang Zhang,Yuqi Yang,Jiangming Shu,Xinyan Wen,Jitao Sang
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-66] SHIP: A Shapelet-based Approach for Interpretable Patient-Ventilator Asynchrony Detection PAKDD2025

链接: https://arxiv.org/abs/2503.06571
作者: Xuan-May Le,Ling Luo,Uwe Aickelin,Minh-Tuan Tran,David Berlowitz,Mark Howard
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: Accepted at PAKDD 2025

点击查看摘要

[AI-67] Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving

链接: https://arxiv.org/abs/2503.06567
作者: Yao Cheng,Yibo Zhao,Jiapeng Zhu,Yao Liu,Xing Sun,Xiang Li
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-68] ChatGPT -4 in the Turing Test: A Critical Analysis

链接: https://arxiv.org/abs/2503.06551
作者: Marco Giunti
类目: Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC)
*备注: 14 pages, 1 Appendix

点击查看摘要

[AI-69] From Motion Signals to Insights: A Unified Framework for Student Behavior Analysis and Feedback in Physical Education Classes

链接: https://arxiv.org/abs/2503.06525
作者: Xian Gao,Jiacheng Ruan,Jingsheng Gao,Mingye Xie,Zongyun Zhang,Ting Liu,Yuzhuo Fu
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注: Work in progress

点击查看摘要

[AI-70] Generative AI as Digital Media

链接: https://arxiv.org/abs/2503.06523
作者: Gilad Abiri
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-71] Can Small Language Models Reliably Resist Jailbreak Attacks? A Comprehensive Evaluation

链接: https://arxiv.org/abs/2503.06519
作者: Wenhui Zhang,Huiyu Xu,Zhibo Wang,Zeqing He,Ziqi Zhu,Kui Ren
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
*备注: 19 pages, 12 figures

点击查看摘要

[AI-72] owards Superior Quantization Accuracy: A Layer-sensitive Approach

链接: https://arxiv.org/abs/2503.06518
作者: Feng Zhang,Yanbin Liu,Weihua Li,Jie Lv,Xiaodan Wang,Quan Bai
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-73] HFedCKD: Toward Robust Heterogeneous Federated Learning via Data-free Knowledge Distillation and Two-way Contrast

链接: https://arxiv.org/abs/2503.06511
作者: Yiting Zheng,Bohan Lin,Jinqian Chen,Jihua Zhu
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-74] ExKG-LLM : Leverag ing Large Language Models for Automated Expansion of Cognitive Neuroscience Knowledge Graphs

链接: https://arxiv.org/abs/2503.06479
作者: Ali Sarabadani(1),Kheirolah Rahsepar Fard(2),Hamid Dalvand(3) ((1) Department of Computer Engineering and Information Technology, University of Qom, Iran, (2) Department of Computer Engineering and Information Technology, University of Qom, Iran, (3) Department of Occupational Therapy, School of Rehabilitation, Tehran University of Medical Sciences, Iran)
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-75] CtrTab: Tabular Data Synthesis with High-Dimensional and Limited Data

链接: https://arxiv.org/abs/2503.06444
作者: Zuqing Li,Jianzhong Qi,Junhao Gan
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Databases (cs.DB)
*备注:

点击查看摘要

[AI-76] Seesaw: High-throughput LLM Inference via Model Re-sharding

链接: https://arxiv.org/abs/2503.06433
作者: Qidong Su,Wei Zhao,Xin Li,Muralidhar Andoorveedu,Chenhao Jiang,Zhanda Zhu,Kevin Song,Christina Giannoula,Gennady Pekhimenko
类目: Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-77] GenAI for Simulation Model in Model-Based Systems Engineering

链接: https://arxiv.org/abs/2503.06422
作者: Lin Zhang,Yuteng Zhang,Dusit Niyato,Lei Ren,Pengfei Gu,Zhen Chen,Yuanjun Laili,Wentong Cai,Agostino Bruzzone
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
*备注: This work has been submitted to the IEEE for possible publication

点击查看摘要

[AI-78] Explaining Control Policies through Predicate Decision Diagrams

链接: https://arxiv.org/abs/2503.06420
作者: Debraj Chakraborty,Clemens Dubslaff,Sudeep Kanav,Jan Kretinsky,Christoph Weinhuber
类目: Artificial Intelligence (cs.AI); Systems and Control (eess.SY)
*备注:

点击查看摘要

[AI-79] Advancing AI Negotiations: New Theory and Evidence from a Large-Scale Autonomous Negotiations Competition

链接: https://arxiv.org/abs/2503.06416
作者: Michelle Vaccaro,Michael Caoson,Harang Ju,Sinan Aral,Jared R. Curhan
类目: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
*备注:

点击查看摘要

[AI-80] Decoding the Black Box: Integrating Moral Imagination with Technical AI Governance

链接: https://arxiv.org/abs/2503.06411
作者: Krti Tallam
类目: ystems and Control (eess.SY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-81] Performant LLM Agent ic Framework for Conversational AI

链接: https://arxiv.org/abs/2503.06410
作者: Alex Casella,Wayne Wang
类目: Artificial Intelligence (cs.AI)
*备注: 6 pages, 3 figures

点击查看摘要

[AI-82] Heterogeneous bimodal attention fusion for speech emotion recognition

链接: https://arxiv.org/abs/2503.06405
作者: Jiachen Luo,Huy Phan,Lin Wang,Joshua Reiss
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS)
*备注:

点击查看摘要

[AI-83] Causality Enhanced Origin-Destination Flow Prediction in Data-Scarce Cities

链接: https://arxiv.org/abs/2503.06398
作者: Tao Feng,Yunke Zhang,Huandong Wang,Yong Li
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-84] Optimizing Minimum Vertex Cover Solving via a GCN-assisted Heuristic Algorithm

链接: https://arxiv.org/abs/2503.06396
作者: Enqiang Zhu,Qiqi Bao,Yu Zhang,Chanjuan Liu
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-85] Causal Discovery and Inference towards Urban Elements and Associated Factors

链接: https://arxiv.org/abs/2503.06395
作者: Tao Feng,Yunke Zhang,Xiaochen Fan,Huandong Wang,Yong Li
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-86] EPR-GAIL: An EPR-Enhanced Hierarchical Imitation Learning Framework to Simulate Complex User Consumption Behaviors

链接: https://arxiv.org/abs/2503.06392
作者: Tao Feng,Yunke Zhang,Huandong Wang,Yong Li
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-87] Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics

链接: https://arxiv.org/abs/2503.06366
作者: Herman Chau,Helen Jenne,Davis Brown,Jesse He,Mark Raugas,Sara Billey,Henry Kvinge
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Combinatorics (math.CO); Representation Theory (math.RT)
*备注: 26 pages, comments welcome

点击查看摘要

[AI-88] he AI Pentad the CHARME2D Model and an Assessment of Current-State AI Regulation

链接: https://arxiv.org/abs/2503.06353
作者: Di Kevin Gao,Sudip Mittal,Jiming Wu,Hongwei Du,Jingdao Chen,Shahram Rahimi
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-89] Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning ICLR2025

链接: https://arxiv.org/abs/2503.06343
作者: Samuel Garcin,Trevor McInroe,Pablo Samuel Castro,Prakash Panangaden,Christopher G. Lucas,David Abel,Stefano V. Albrecht
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: Published as a conference paper at ICLR 2025. 10 pages

点击查看摘要

[AI-90] Higher-Order Belief in Incomplete Information MAIDs

链接: https://arxiv.org/abs/2503.06323
作者: Jack Foxabbott,Rohan Subramani,Francis Rhys Ward
类目: Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
*备注:

点击查看摘要

[AI-91] Synergizing AI and Digital Twins for Next-Generation Network Optimization Forecasting and Security

链接: https://arxiv.org/abs/2503.06302
作者: Zifan Zhang,Minghong Fang,Dianwei Chen,Xianfeng Yang,Yuchen Liu
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: Accepted by IEEE Wireless Communications

点击查看摘要

[AI-92] Single Domain Generalization with Adversarial Memory

链接: https://arxiv.org/abs/2503.06288
作者: Hao Yan,Marzi Heidari,Yuhong Guo
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-93] Applied Machine Learning Methods with Long-Short Term Memory Based Recurrent Neural Networks for Multivariate Temperature Prediction

链接: https://arxiv.org/abs/2503.06278
作者: Bojan Lukić
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 11 pages, 16 figures, private research

点击查看摘要

[AI-94] Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models

链接: https://arxiv.org/abs/2503.06269
作者: Thomas Winninger,Boussad Addad,Katarzyna Kapusta
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-95] Infant Cry Detection Using Causal Temporal Representation ICASSP2025

链接: https://arxiv.org/abs/2503.06247
作者: Minghao Fu,Danning Li,Aryan Gadhiya,Benjamin Lambright,Mohamed Alowais,Mohab Bahnassy,Saad El Dine Elletter,Hawau Olamide Toyin,Haiyan Jiang,Kun Zhang,Hanan Aldarmaki
类目: ound (cs.SD); Artificial Intelligence (cs.AI)
*备注: Accepted to ICASSP 2025

点击查看摘要

[AI-96] LapSum – One Method to Differentiate Them All: Ranking Sorting and Top-k Selection

链接: https://arxiv.org/abs/2503.06242
作者: Łukasz Struski,Michał B. Bednarczyk,Igor T. Podolak,Jacek Tabor
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-97] Image is All You Need: Towards Efficient and Effective Large Language Model-Based Recommender Systems

链接: https://arxiv.org/abs/2503.06238
作者: Kibum Kim,Sein Kim,Hongseok Kang,Jiwan Kim,Heewoong Noh,Yeonjun In,Kanghoon Yoon,Jinoh Oh,Chanyoung Park
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-98] A Frank System for Co-Evolutionary Hybrid Decision-Making

链接: https://arxiv.org/abs/2503.06229
作者: Federico Mazzoni,Riccardo Guidotti,Alessio Malizia
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG)
*备注: 13 pages

点击查看摘要

[AI-99] Optimal Output Feedback Learning Control for Discrete-Time Linear Quadratic Regulation

链接: https://arxiv.org/abs/2503.06226
作者: Kedi Xiea,Martin Guay,Shimin Wang,Fang Deng,Maobin Lu
类目: ystems and Control (eess.SY); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Optimization and Control (math.OC)
*备注: 16 pages, 5 figures

点击查看摘要

[AI-100] GraphGen: Advancing Distributed Subgraph Generation and Graph Learning On Industrial Graphs EUROSYS2025

链接: https://arxiv.org/abs/2503.06212
作者: Yue Jin,Yongchao Liu,Chuntao Hong
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注: Accepted By EuroSys 2025 (poster)

点击查看摘要

[AI-101] Distributed Graph Neural Network Inference With Just-In-Time Compilation For Industry-Scale Graphs EUROSYS2025

链接: https://arxiv.org/abs/2503.06208
作者: Xiabao Wu,Yongchao Liu,Wei Qin,Chuntao Hong
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注: Accepted by EuroSys 2025 (poster)

点击查看摘要

[AI-102] Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization

链接: https://arxiv.org/abs/2503.06202
作者: Wei Liu,Zhiying Deng,Zhongyu Niu,Jun Wang,Haozhao Wang,Zhigang Zeng,Ruixuan Li
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-103] Human-AI Experience in Integrated Development Environments: A Systematic Literature Review

链接: https://arxiv.org/abs/2503.06195
作者: Agnia Sergeyuk,Ilya Zakharov,Ekaterina Koshchenko,Maliheh Izadi
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
*备注: Submitted to Empirical Software Engineering (EMSE) special issue Human-Centered AI for Software Engineering (HumanAISE), 28 pages, 1 figure

点击查看摘要

[AI-104] Lightweight Software Kernels and Hardware Extensions for Efficient Sparse Deep Neural Networks on Microcontrollers

链接: https://arxiv.org/abs/2503.06183
作者: Francesco Daghero,Daniele Jahier Pagliari,Francesco Conti,Luca Benini,Massimo Poncino,Alessio Burrello
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Performance (cs.PF)
*备注: Accepted at MLSys 2025

点击查看摘要

[AI-105] Minion Gated Recurrent Unit for Continual Learning

链接: https://arxiv.org/abs/2503.06175
作者: Abdullah M. Zyarah,Dhireesha Kudithipudi
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-106] ROCM: RLHF on consistency models

链接: https://arxiv.org/abs/2503.06171
作者: Shivanshu Shekhar,Tong Zhang
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-107] Secure On-Device Video OOD Detection Without Backpropagation

链接: https://arxiv.org/abs/2503.06166
作者: Li Li,Peilin Cai,Yuxiao Zhou,Zhiyu Ni,Renjie Liang,You Qin,Yi Nian,Zhengzhong Tu,Xiyang Hu,Yue Zhao
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-108] System 0/1/2/3: Quad-process theory for multi-timescale embodied collective cognitive systems

链接: https://arxiv.org/abs/2503.06138
作者: Tadahiro Taniguchi,Yasushi Hirai,Masahiro Suzuki,Shingo Murata,Takato Horii,Kazutoshi Tanaka
类目: Artificial Intelligence (cs.AI); Robotics (cs.RO); Neurons and Cognition (q-bio.NC)
*备注: Under review

点击查看摘要

[AI-109] Multi-modal expressive personality recognition in data non-ideal audiovisual based on multi-scale feature enhancement and modal augment

链接: https://arxiv.org/abs/2503.06108
作者: Weixuan Kong,Jinpeng Yu,Zijun Li,Hanwei Liu,Jiqing Qu,Hui Xiao,Xuefeng Li
类目: ound (cs.SD); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-110] ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning

链接: https://arxiv.org/abs/2503.06101
作者: Mingqi Yuan,Bo Li,Xin Jin,Wenjun Zeng
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 23 pages, 22 figures

点击查看摘要

[AI-111] -CBF: Traversability-based Control Barrier Function to Navigate Vertically Challenging Terrain

链接: https://arxiv.org/abs/2503.06083
作者: Manas Gupta,Xuesu Xiao
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-112] MANDARIN: Mixture-of-Experts Framework for Dynamic Delirium and Coma Prediction in ICU Patients: Development and Validation of an Acute Brain Dysfunction Prediction Model

链接: https://arxiv.org/abs/2503.06059
作者: Miguel Contreras,Jessica Sena,Andrea Davidson,Jiaqing Zhang,Tezcan Ozrazgat-Baslanti,Yuanfang Ren,Ziyuan Guan,Jeremy Balch,Tyler Loftus,Subhash Nerella,Azra Bihorac,Parisa Rashidi
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-113] Vairiational Stochastic Games

链接: https://arxiv.org/abs/2503.06037
作者: Zhiyu Zhao,Haifeng Zhang
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-114] Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models

链接: https://arxiv.org/abs/2503.06027
作者: Xubin Wang,Zhiqing Tang,Jianxiong Guo,Tianhui Meng,Chenhao Wang,Tian Wang,Weijia Jia
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI)
*备注:

点击查看摘要

[AI-115] Learning to Drive by Imitating Surrounding Vehicles

链接: https://arxiv.org/abs/2503.05997
作者: Yasin Sonmez,Hanna Krasowski,Murat Arcak
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-116] owards Improving Reward Design in RL: A Reward Alignment Metric for RL Practitioners

链接: https://arxiv.org/abs/2503.05996
作者: Calarina Muslimani,Kerrick Johnstonbaugh,Suyog Chandramouli,Serena Booth,W. Bradley Knox,Matthew E. Taylor
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-117] Black Box Causal Inference: Effect Estimation via Meta Prediction

链接: https://arxiv.org/abs/2503.05985
作者: Lucius E.J. Bynum,Aahlad Manas Puli,Diego Herrero-Quevedo,Nhi Nguyen,Carlos Fernandez-Granda,Kyunghyun Cho,Rajesh Ranganath
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation (stat.CO); Methodology (stat.ME); Machine Learning (stat.ML)
*备注:

点击查看摘要

[AI-118] Learning-Order Autoregressive Models with Application to Molecular Graph Generation

链接: https://arxiv.org/abs/2503.05979
作者: Zhe Wang,Jiaxin Shi,Nicolas Heess,Arthur Gretton,Michalis K. Titsias
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
*备注:

点击查看摘要

[AI-119] Optimal sensor deception in stochastic environments with partial observability to mislead a robot to a decoy goal

链接: https://arxiv.org/abs/2503.05972
作者: Hazhar Rahmani,Mukulika Ghosh,Syed Md Hasnayeen
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-120] A Real-time Multimodal Transformer Neural Network-powered Wildfire Forecasting System

链接: https://arxiv.org/abs/2503.05971
作者: Qijun Chen,Shaofan Li
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-121] Bayesian Graph Traversal

链接: https://arxiv.org/abs/2503.05963
作者: William N. Caballero,Phillip R. Jenkins,David Banks,Matthew Robbins
类目: Artificial Intelligence (cs.AI); Computer Science and Game Theory (cs.GT); Other Statistics (stat.OT)
*备注: 26 pages, 7 tables, 2 figures

点击查看摘要

[AI-122] PU-Gen: LLM -Driven Custom Tensor Processing Unit Generator

链接: https://arxiv.org/abs/2503.05951
作者: Deepak Vungarala,Mohammed E. Elbtity,Sumiya Syed,Sakila Alam,Kartik Pandit,Arnob Ghosh,Ramtin Zand,Shaahin Angizi
类目: Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI)
*备注: 8 Pages, 9 Figures, 5 Tables

点击查看摘要

[AI-123] Enhancing Reasoning with Collaboration and Memory

链接: https://arxiv.org/abs/2503.05944
作者: Julie Michelman,Nasrin Baratalipour,Matthew Abueg
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: 17 pages, 6 figures

点击查看摘要

[AI-124] Uncertainty Quantification From Scaling Laws in Deep Neural Networks

链接: https://arxiv.org/abs/2503.05938
作者: Ibrahim Elsharkawy,Yonatan Kahn,Benjamin Hooberman
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); High Energy Physics - Experiment (hep-ex); High Energy Physics - Phenomenology (hep-ph); High Energy Physics - Theory (hep-th)
*备注: 18+3 pages, 6 figures

点击查看摘要

[AI-125] he Unified Control Framework: Establishing a Common Foundation for Enterprise AI Governance Risk Management and Regulatory Compliance

链接: https://arxiv.org/abs/2503.05937
作者: Ian W. Eisenberg,Lucía Gamboa,Eli Sherman
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-126] Audio-to-Image Encoding for Improved Voice Characteristic Detection Using Deep Convolutional Neural Networks

链接: https://arxiv.org/abs/2503.05929
作者: Youness Atif
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS)
*备注: 11 pages, 24 figures, 1 table, 3 algorithms. Submitted to F1000Research

点击查看摘要

[AI-127] ElementaryNet: A Non-Strategic Neural Network for Predicting Human Behavior in Normal-Form Games

链接: https://arxiv.org/abs/2503.05925
作者: Greg d’Eon,Hala Murad,Kevin Leyton-Brown,James R. Wright
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Science and Game Theory (cs.GT)
*备注: 14 pages. Submitted to EC 2025

点击查看摘要

[AI-128] owards Understanding the Use of MLLM -Enabled Applications for Visual Interpretation by Blind and Low Vision People

链接: https://arxiv.org/abs/2503.05899
作者: Ricardo E. Gonzalez Penuela,Ruiying Hu,Sharon Lin,Tanisha Shende,Shiri Azenkot
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
*备注: 8 pages, 1 figure, 4 tables, to appear at CHI 2025

点击查看摘要

[AI-129] Zero-shot Medical Event Prediction Using a Generative Pre-trained Transformer on Electronic Health Records

链接: https://arxiv.org/abs/2503.05893
作者: Ekaterina Redekop,Zichen Wang,Rushikesh Kulkarni,Mara Pleasure,Aaron Chin,Hamid Reza Hassanzadeh,Brian L. Hill,Melika Emami,William Speier,Corey W. Arnold
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-130] Practical Topics in Optimization

链接: https://arxiv.org/abs/2503.05882
作者: Jun Lu
类目: Numerical Analysis (math.NA); Artificial Intelligence (cs.AI); Optimization and Control (math.OC)
*备注:

点击查看摘要

[AI-131] Benchmarking AI Models in Software Engineering: A Review Search Tool and Enhancement Protocol

链接: https://arxiv.org/abs/2503.05860
作者: Roham Koohestani,Philippe de Bekker,Maliheh Izadi
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-132] Quantum-like cognition and decision making in the light of quantum measurement theory

链接: https://arxiv.org/abs/2503.05859
作者: Miho Fuyama,Andrei Khrennikov,Masanao Ozawa
类目: Artificial Intelligence (cs.AI); Biological Physics (physics.bio-ph); Quantum Physics (quant-ph)
*备注:

点击查看摘要

[AI-133] SYMBIOSIS: Systems Thinking and Machine Intelligence for Better Outcomes in Society

链接: https://arxiv.org/abs/2503.05857
作者: Sameer Sethi,Donald Martin Jr.,Emmanuel Klu
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-134] Accelerating Earth Science Discovery via Multi-Agent LLM Systems

链接: https://arxiv.org/abs/2503.05854
作者: Dmitrii Pantiukhin,Boris Shapkin,Ivan Kuznetsov,Antonia Anna Jost,Nikolay Koldunov
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI)
*备注: 10 pages, 1 figure. Perspective article

点击查看摘要

[AI-135] Evaluating Large Language Models in Code Generation: INFINITE Methodology for Defining the Inference Index

链接: https://arxiv.org/abs/2503.05852
作者: Nicholas Christakis,Dimitris Drikakis
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
*备注: 20 pages, 6 figures

点击查看摘要

[AI-136] AI-Facilitated Collective Judgements

链接: https://arxiv.org/abs/2503.05830
作者: Manon Revel,Théophile Pénigaud
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-137] Market-based Architectures in RL and Beyond AAMAS2025

链接: https://arxiv.org/abs/2503.05828
作者: Abhimanyu Pallavi Sudhir,Long Tran-Thanh
类目: Artificial Intelligence (cs.AI); Theoretical Economics (econ.TH)
*备注: Accepted at AAMAS 2025

点击查看摘要

[AI-138] Introduction to Artificial Consciousness: History Current Trends and Ethical Challenges

链接: https://arxiv.org/abs/2503.05823
作者: Aïda Elamrani
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注: 65 pages

点击查看摘要

[AI-139] he impact of AI and peer feedback on research writing skills: a study using the CGScholar platform among Kazakhstani scholars

链接: https://arxiv.org/abs/2503.05820
作者: Raigul Zheldibayeva
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注: 11 pages, 5 figures

点击查看摘要

[AI-140] rust Experience and Innovation: Key Factors Shaping American Attitudes About AI

链接: https://arxiv.org/abs/2503.05815
作者: Risa Palm,Justin Kingsland,Toby Bolsen
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); General Economics (econ.GN)
*备注: 35 pages, 3 figures, 2 tables, appendix

点击查看摘要

[AI-141] Intolerable Risk Threshold Recommendations for Artificial Intelligence

链接: https://arxiv.org/abs/2503.05812
作者: Deepika Raman,Nada Madkour,Evan R. Murphy,Krystal Jackson,Jessica Newman
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
*备注: 79 pages

点击查看摘要

[AI-142] A Transformer Model for Predicting Chemical Reaction Products from Generic Templates

链接: https://arxiv.org/abs/2503.05810
作者: Derin Ozer,Sylvain Lamprier,Thomas Cauchy,Nicolas Gutowski,Benoit Da Mota
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Chemical Physics (physics.chem-ph)
*备注:

点击查看摘要

[AI-143] DriveGen: Towards Infinite Diverse Traffic Scenarios with Large Models

链接: https://arxiv.org/abs/2503.05808
作者: Shenyu Zhang,Jiaguo Tian,Zhengbang Zhu,Shan Huang,Jucheng Yang,Weinan Zhang
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Robotics (cs.RO)
*备注: 8 pages, 3 figures

点击查看摘要

[AI-144] Multi-agent Auto-Bidding with Latent Graph Diffusion Models

链接: https://arxiv.org/abs/2503.05805
作者: Dom Huh,Prasant Mohapatra
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
*备注:

点击查看摘要

[AI-145] Holistically Evaluating the Environmental Impact of Creating Language Models ICLR2025

链接: https://arxiv.org/abs/2503.05804
作者: Jacob Morrison,Clara Na,Jared Fernandez,Tim Dettmers,Emma Strubell,Jesse Dodge
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: ICLR 2025 (spotlight)

点击查看摘要

[AI-146] Federated Learning Framework via Distributed Mutual Learning

链接: https://arxiv.org/abs/2503.05803
作者: Yash Gupta
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-147] Fault Localization and State Estimation of Power Grid under Parallel Cyber-Physical Attacks

链接: https://arxiv.org/abs/2503.05797
作者: Junhao Ren,Kai Zhao,Guangxiao Zhang,Xinghua Liu,Chao Zhai,Gaoxi Xiao
类目: ystems and Control (eess.SY); Artificial Intelligence (cs.AI)
*备注: 10 pages, 3 figures, 5 tables, journal

点击查看摘要

[AI-148] owards Multi-Stakeholder Evaluation of ML Models: A Crowdsourcing Study on Metric Preferences in Job-matching System WWW

链接: https://arxiv.org/abs/2503.05796
作者: Takuya Yokota,Yuri Nakao
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注: This version of the contribution has been accepted for publication, after peer review (when applicable) but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use this https URL

点击查看摘要

[AI-149] CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking ICASSP’21

链接: https://arxiv.org/abs/2503.05794
作者: Yiming Li,Kaiying Yan,Shuo Shao,Tongqing Zhai,Shu-Tao Xia,Zhan Qin,Dacheng Tao
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS)
*备注: 14 pages. The journal extension of our ICASSP’21 paper ( arXiv:2010.11607 )

点击查看摘要

[AI-150] Artificial Intelligence in Sports: Insights from a Quantitative Survey among Sports Students in Germany about their Perceptions Expectations and Concerns regarding the Use of AI Tools

链接: https://arxiv.org/abs/2503.05785
作者: Dennis Krämer,Anja Bosold,Martin Minarik,Cleo Schyvinck,Andre Hajek
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注: 36 Tables, 18 Figures

点击查看摘要

[AI-151] he Illusion of Rights based AI Regulation

链接: https://arxiv.org/abs/2503.05784
作者: Yiyang Mei,Matthew Sag
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-152] Knowledge representation and scalable abstract reasoning for simulated democracy in Unity

链接: https://arxiv.org/abs/2503.05783
作者: Eleftheria Katsiri,Alexandros Gazis,Angelos Protopapas
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
*备注: 23 pages, 11 figures, 76 references. This article is under review at WSEAS Transactions on Information Science and Applications from 02.2025

点击查看摘要

[AI-153] AI Mentors for Student Projects: Spotting Early Issues in Computer Science Proposals AAAI2025

链接: https://arxiv.org/abs/2503.05782
作者: Gati Aher,Robin Schmucker,Tom Mitchell,Zachary C. Lipton
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注: Accepted for oral presentation at Workshop on Innovation and Responsibility in AI-Supported Education (iRAISE), AAAI 2025

点击查看摘要

[AI-154] Homomorphic Encryption of Intuitionistic Logic Proofs and Functional Programs: A Categorical Approach Inspired by Composite-Order Bilinear Groups

链接: https://arxiv.org/abs/2503.05779
作者: Ben Goertzel
类目: Logic in Computer Science (cs.LO); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-155] FAA-CLIP: Federated Adversarial Adaptation of CLIP

链接: https://arxiv.org/abs/2503.05776
作者: Yihang Wu,Ahmad Chaddad,Christian Desrosiers,Tareef Daqqaq,Reem Kateb
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: Accepted in IEEE Internet of Things Journal

点击查看摘要

[AI-156] Between Innovation and Oversight: A Cross-Regional Study of AI Risk Management Frameworks in the EU U.S. UK and China

链接: https://arxiv.org/abs/2503.05773
作者: Amir Al-Maamari
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-157] Generative Artificial Intelligence: Evolving Technology Growing Societal Impact and Opportunities for Information Systems Research

链接: https://arxiv.org/abs/2503.05770
作者: Veda C. Storey,Wei Thoo Yue,J. Leon Zhao,Roman Lukyanenko
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-158] A Collection of Innovations in Medical AI for patient records in 2024

链接: https://arxiv.org/abs/2503.05768
作者: Yuanyun Zhang,Shi Li
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-159] Mesterséges Intelligencia Kutatások Magyarországon

链接: https://arxiv.org/abs/2503.05767
作者: András A. Benczúr,Tibor Gyimóthy,Balázs Szegedy
类目: General Literature (cs.GL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: in Hungarian language. Submitted to Magyar Tudomány

点击查看摘要

[AI-160] Encoding Inequity: Examining Demographic Bias in LLM -Driven Robot Caregiving

链接: https://arxiv.org/abs/2503.05765
作者: Raj Korpan
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
*备注: Accepted at the 4th Diversity, Equity, Inclusion in HRI Workshop at HRI’25, the 20th edition of the ACM/IEEE International Conference on Human-Robot Interaction

点击查看摘要

[AI-161] he Lazy Students Dream: ChatGPT Passing an Engineering Course on Its Own

链接: https://arxiv.org/abs/2503.05760
作者: Gokul Puthumanaillam,Melkior Ornik
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-162] ADAPT Centre Contribution on Implementation of the EU AI Act and Fundamental Right Protection

链接: https://arxiv.org/abs/2503.05758
作者: Dave Lewis,Marta Lasek-Markey,Harshvardhan J. Pandit,Delaram Golpayegani,Darren McCabe,Louise McCormack,Joshua Hovsha,Deirdre Ahern,Arthit Suriyawongku
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-163] SEAFL: Enhancing Efficiency in Semi-Asynchronous Federated Learning through Adaptive Aggregation and Selective Training

链接: https://arxiv.org/abs/2503.05755
作者: Md Sirajul Islam,Sanjeev Panta,Fei Xu,Xu Yuan,Li Chen,Nian-Feng Tzeng
类目: Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-164] Exploring AI Writers: Technology Impact and Future Prospects

链接: https://arxiv.org/abs/2503.05753
作者: Zhiqian Huang
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-165] Alignment Agency and Autonomy in Frontier AI: A Systems Engineering Perspective

链接: https://arxiv.org/abs/2503.05748
作者: Krti Tallam
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-166] Balancing Innovation and Integrity: AI Integration in Liberal Arts College Administration

链接: https://arxiv.org/abs/2503.05747
作者: Ian Olivo Read
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注: Number of Pages: 19; Number of Figures: 3. This submission explores AI integration in liberal arts college administration, focusing on academic and student affairs. It addresses ethical, legal, and institutional alignment issues. For related discussions, see: Friedler et al. (2016), Katsamakas et al. (2024), Łodzikowski et al. (2023), Zhang et al. (2024)

点击查看摘要

[AI-167] Local Differences Global Lessons: Insights from Organisation Policies for International Legislation

链接: https://arxiv.org/abs/2503.05737
作者: Lucie-Aimée Kaffee,Pepa Atanasova,Anna Rogers
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-168] Modeling Behavior Change for Multi-model At-Risk Students Early Prediction (extended version)

链接: https://arxiv.org/abs/2503.05734
作者: Jiabei Cheng,Zhen-Qun Yang,Jiannong Cao,Yu Yang,Kai Cheung Franky Poon,Daniel Lai
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-169] Design an Ontology for Cognitive Business Strategy Based on Customer Satisfaction

链接: https://arxiv.org/abs/2503.05733
作者: Neda Bagherzadeh,Saeed Setayeshi,Samaneh Yazdani
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-170] AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons

链接: https://arxiv.org/abs/2503.05731
作者: Shaona Ghosh,Heather Frase,Adina Williams,Sarah Luger,Paul Röttger,Fazl Barez,Sean McGregor,Kenneth Fricklas,Mala Kumar,Quentin Feuillade–Montixi,Kurt Bollacker,Felix Friedrich,Ryan Tsang,Bertie Vidgen,Alicia Parrish,Chris Knotz,Eleonora Presani,Jonathan Bennion,Marisa Ferrara Boston,Mike Kuniavsky,Wiebke Hutiri,James Ezick,Malek Ben Salem,Rajat Sahay,Sujata Goswami,Usman Gohar,Ben Huang,Supheakmungkol Sarin,Elie Alhajjar,Canyu Chen,Roman Eng,Kashyap Ramanandula Manjusha,Virendra Mehta,Eileen Long,Murali Emani,Natan Vidra,Benjamin Rukundo,Abolfazl Shahbazi,Kongtao Chen,Rajat Ghosh,Vithursan Thangarasa,Pierre Peigné,Abhinav Singh,Max Bartolo,Satyapriya Krishna,Mubashara Akhtar,Rafael Gold,Cody Coleman,Luis Oala,Vassil Tashev,Joseph Marvin Imperial,Amy Russ,Sasidhar Kunapuli,Nicolas Miailhe,Julien Delaunay,Bhaktipriya Radharapu,Rajat Shinde,Tuesday,Debojyoti Dutta,Declan Grabb,Ananya Gangavarapu,Saurav Sahay,Agasthya Gangavarapu,Patrick Schramowski,Stephen Singam,Tom David,Xudong Han,Priyanka Mary Mammen,Tarunima Prabhakar,Venelin Kovatchev,Ahmed Ahmed,Kelvin N. Manyeki,Sandeep Madireddy,Foutse Khomh,Fedor Zhdanov,Joachim Baumann,Nina Vasan,Xianjun Yang,Carlos Mougn,Jibin Rajan Varghese,Hussain Chinoy,Seshakrishna Jitendar,Manil Maskey,Claire V. Hardgrove,Tianhao Li,Aakash Gupta,Emil Joswin,Yifan Mai,Shachi H Kumar,Cigdem Patlak,Kevin Lu,Vincent Alessi,Sree Bhargavi Balija,Chenhe Gu,Robert Sullivan,James Gealy,Matt Lavrisa,James Goel,Peter Mattson,Percy Liang,Joaquin Vanschoren
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注: 51 pages, 8 figures and an appendix

点击查看摘要

[AI-171] Robust Optimization with Diffusion Models for Green Security

链接: https://arxiv.org/abs/2503.05730
作者: Lingkai Kong,Haichuan Wang,Yuqi Pan,Cheol Woo Kim,Mingxiao Song,Alayna Nguyen,Tonghan Wang,Haifeng Xu,Milind Tambe
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-172] Political Neutrality in AI is Impossible- But Here is How to Approximate it

链接: https://arxiv.org/abs/2503.05728
作者: Jillian Fisher,Ruth E. Appel,Chan Young Park,Yujin Potter,Liwei Jiang,Taylor Sorensen,Shangbin Feng,Yulia Tsvetkov,Margaret E. Roberts,Jennifer Pan,Dawn Song,Yejin Choi
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注: Code: this https URL

点击查看摘要

[AI-173] A new framework for prognostics in decentralized industries: Enhancing fairness security and transparency through Blockchain and Federated Learning

链接: https://arxiv.org/abs/2503.05725
作者: T.Q.D. Pham,K.D. Tran,Khanh T. P. Nguyen,X.V. Tran,K.P. Tran
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-174] Addressing Moral Uncertainty using Large Language Models for Ethical Decision-Making

链接: https://arxiv.org/abs/2503.05724
作者: Rohit K. Dubey,Damian Dailisan,Sachit Mahajan
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注: 13 pages, 5 figures. All authors contributed equally to this work

点击查看摘要

[AI-175] AI Mimicry and Human Dignity: Chatbot Use as a Violation of Self-Respect

链接: https://arxiv.org/abs/2503.05723
作者: Jan-Willem van der Rijt,Dimitri Coelho Mollo,Bram Vaassen
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-176] he Butterfly Effect of Technology: How Various Factors accelerate or hinder the Arrival of Technological Singularity

链接: https://arxiv.org/abs/2503.05715
作者: Hooman Shababi
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注: 20 Pages, 0 Figures, 0 Tables

点击查看摘要

[AI-177] Automatic Evaluation Metrics for Artificially Generated Scientific Research

链接: https://arxiv.org/abs/2503.05712
作者: Niklas Höpner,Leon Eshuijs,Dimitrios Alivanistos,Giacomo Zamprogno,Ilaria Tiddi
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-178] Labeling Synthetic Content: User Perceptions of Warning Label Designs for AI-generated Content on Social Media

链接: https://arxiv.org/abs/2503.05711
作者: Dilrukshi Gamage,Dilki Sewwandi,Min Zhang,Arosha Bandara
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Emerging Technologies (cs.ET)
*备注: This is a pre print longer version of a paper accepted to CHI 2025; after rebuttal we had to short the paper to 25 pages. Currently its in overleaf manuscript format with one column. All data for the file is in the osf link

点击查看摘要

[AI-179] Inference Scaling Reshapes AI Governance

链接: https://arxiv.org/abs/2503.05705
作者: Toby Ord
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注: 17 pages, 3 figures

点击查看摘要

[AI-180] What I cannot execute I do not understand: Training and Evaluating LLM s on Program Execution Traces

链接: https://arxiv.org/abs/2503.05703
作者: Jordi Armengol-Estapé,Quentin Carbonneaux,Tianjun Zhang,Aram H. Markosyan,Volker Seeker,Chris Cummins,Melanie Kambadur,Michael F.P. O’Boyle,Sida Wang,Gabriel Synnaeve,Hugh James Leather
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Programming Languages (cs.PL)
*备注:

点击查看摘要

[AI-181] A Comprehensive Survey of Fuzzy Implication Functions

链接: https://arxiv.org/abs/2503.05702
作者: Raquel Fernandez-Peralta
类目: Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO)
*备注:

点击查看摘要

[AI-182] he Economics of p(doom): Scenarios of Existential Risk and Economic Growth in the Age of Transformative AI

链接: https://arxiv.org/abs/2503.07341
作者: Jakub Growiec,Klaus Prettner
类目: General Economics (econ.GN); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-183] A LSTM-Transformer Model for pulsation control of pVADs

链接: https://arxiv.org/abs/2503.07110
作者: Chaoran E,Chenghan Chen,Yuyang Shi,Haiyun Wang,Peixin Hua,Xiwen Zhang
类目: Medical Physics (physics.med-ph); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-184] Multimodal AI-driven Biomarker for Early Detection of Cancer Cachexia

链接: https://arxiv.org/abs/2503.06797
作者: Sabeen Ahmed,Nathan Parker,Margaret Park,Evan W. Davis,Jennifer B. Permuth,Matthew B. Schabath,Yasin Yilmaz,Ghulam Rasool
类目: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM)
*备注: 17 pages, 6 figures, 3 Tables

点击查看摘要

[AI-185] Physics-Informed Residual Neural Ordinary Differential Equations for Enhanced Tropical Cyclone Intensity Forecasting

链接: https://arxiv.org/abs/2503.06436
作者: Fan Meng
类目: Atmospheric and Oceanic Physics (physics.ao-ph); Artificial Intelligence (cs.AI)
*备注: 14 pages, 9 figures

点击查看摘要

[AI-186] Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models

链接: https://arxiv.org/abs/2503.06413
作者: Nguyen Do,Truc Nguyen,Malik Hassanaly,Raed Alharbi,Jung Taek Seo,My T. Thai
类目: Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-187] Exploring the usage of Probabilistic Neural Networks for Ionospheric electron density estimation

链接: https://arxiv.org/abs/2503.06144
作者: Miquel Garcia-Fernandez
类目: ignal Processing (eess.SP); Artificial Intelligence (cs.AI)
*备注: 13 pages, 7 figures

点击查看摘要

[AI-188] Explaining the Unexplainable: A Systematic Review of Explainable AI in Finance

链接: https://arxiv.org/abs/2503.05966
作者: Md Talha Mohsin,Nabid Bin Nasim
类目: General Finance (q-fin.GN); Artificial Intelligence (cs.AI)
*备注: 2 tables, 11 figures

点击查看摘要

[AI-189] Machine Learned Force Fields: Fundamentals its reach and challenges

链接: https://arxiv.org/abs/2503.05845
作者: Carlos A. Vital,Román J. Armenta-Rico,Huziel E. Sauceda
类目: Materials Science (cond-mat.mtrl-sci); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: 9 figures

点击查看摘要

[AI-190] Will Neural Scaling Laws Activate Jevons Paradox in AI Labor Markets? A Time-Varying Elasticity of Substitution (VES) Analysis

链接: https://arxiv.org/abs/2503.05816
作者: Rajesh P. Narayanan,R. Kelley Pace
类目: General Economics (econ.GN); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
*备注:

点击查看摘要

机器学习

[LG-0] Preserving clusters and correlations: a dimensionality reduction method for exceptionally high global structure preservation

链接: https://arxiv.org/abs/2503.07609
作者: Jacob Gildenblat,Jens Pahnke
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-1] Neural Combinatorial Optimization via Preference Optimization

链接: https://arxiv.org/abs/2503.07580
作者: Zijun Liao,Jinbiao Chen,Debing Wang,Zizhen Zhang,Jiahai Wang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-2] Split-n-Chain: Privacy-Preserving Multi-Node Split Learning with Blockchain-Based Auditability

链接: https://arxiv.org/abs/2503.07570
作者: Mukesh Sahani,Binanda Sengupta
类目: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-3] Incentive-Compatible Recovery from Manipulated Signals with Applications to Decentralized Physical Infrastructure

链接: https://arxiv.org/abs/2503.07558
作者: Jason Milionis,Jens Ernstberger,Joseph Bonneau,Scott Duke Kominers,Tim Roughgarden
类目: Computer Science and Game Theory (cs.GT); Emerging Technologies (cs.ET); Machine Learning (cs.LG); Theoretical Economics (econ.TH); Trading and Market Microstructure (q-fin.TR)
*备注:

点击查看摘要

[LG-4] Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference

链接: https://arxiv.org/abs/2503.07555
作者: Fateme Jamshidi,Mohammad Shahverdikondori,Negar Kiyavash
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-5] An Empirical Comparison of Cost Functions in Inductive Logic Programming

链接: https://arxiv.org/abs/2503.07554
作者: Céline Hocquette,Andrew Cropper
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-6] Federated Multimodal Learning with Dual Adapters and Selective Pruning for Communication and Computational Efficiency

链接: https://arxiv.org/abs/2503.07552
作者: Duy Phuong Nguyen,J. Pablo Munoz,Tanya Roosta,Ali Jannesari
类目: Machine Learning (cs.LG)
*备注: Accepted at CCGrid 2025

点击查看摘要

[LG-7] Real-Time Structural Deflection Estimation in Hydraulically Actuated Systems Using 3D Flexible Multibody Simulation and DNNs

链接: https://arxiv.org/abs/2503.07528
作者: Qasim Khadim,Peter Manzl,Emil Kurvinen,Aki Mikkola,Grzegorz Orzechowski,Johannes Gerstmayr
类目: ystems and Control (eess.SY); Machine Learning (cs.LG); Robotics (cs.RO); Dynamical Systems (math.DS)
*备注: 20 pages and 30 figures, Preprint version of the article submitted to MSSP (Mechanical Systems and Signal Processing)

点击查看摘要

[LG-8] rustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions Tradeoffs and Beyond

链接: https://arxiv.org/abs/2503.07501
作者: Qiongxiu Li,Xiaoyu Luo,Yiyi Chen,Johannes Bjerva
类目: Machine Learning (cs.LG)
*备注: 28 pages, 2 figures

点击查看摘要

[LG-9] Poisoning Attacks to Local Differential Privacy Protocols for Trajectory Data

链接: https://arxiv.org/abs/2503.07483
作者: I-Jung Hsu,Chih-Hsun Lin,Chia-Mu Yu,Sy-Yen Kuo,Chun-Ying Huang
类目: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-10] Sample Complexity of Nonparametric Closeness Testing for Continuous Distributions and Its Application to Causal Discovery with Hidden Confounding

链接: https://arxiv.org/abs/2503.07475
作者: Fateme Jamshidi,Sina Akbari,Negar Kiyavash
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-11] Learning to Localize Leakage of Cryptographic Sensitive Variables

链接: https://arxiv.org/abs/2503.07464
作者: Jimmy Gammell,Anand Raghunathan,Abolfazl Hashemi,Kaushik Roy
类目: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
*备注: 52 pages, 30 figures. Our code can be found at this https URL

点击查看摘要

[LG-12] Inorganic Catalyst Efficiency Prediction Based on EAPCR Model: A Deep Learning Solution for Multi-Source Heterogeneous Data

链接: https://arxiv.org/abs/2503.07424
作者: Zhangdi Liu,Ling An,Mengke Song,Zhuohang Yu,Shan Wang,Kezhen Qi,Zhenyu Zhang,Chichun Zhou
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-13] PER-DPP Sampling Framework and Its Application in Path Planning

链接: https://arxiv.org/abs/2503.07411
作者: Junzhe Wang
类目: Robotics (cs.RO); Machine Learning (cs.LG); Optimization and Control (math.OC)
*备注:

点击查看摘要

[LG-14] Q-MARL: A quantum-inspired algorithm using neural message passing for large-scale multi-agent reinforcement learning

链接: https://arxiv.org/abs/2503.07397
作者: Kha Vo,Chin-Teng Lin
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-15] Diagnostic-free onboard battery health assessment

链接: https://arxiv.org/abs/2503.07383
作者: Yunhong Che,Vivek N. Lam,Jinwook Rhyu,Joachim Schaeffer,Minsu Kim,Martin Z. Bazant,William C. Chueh,Richard D. Braatz
类目: ystems and Control (eess.SY); Machine Learning (cs.LG)
*备注: 25 pages

点击查看摘要

[LG-16] Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models

链接: https://arxiv.org/abs/2503.07325
作者: Khoat Than,Dat Phan
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-17] When Selection Meets Intervention: Additional Complexities in Causal Discovery ICLR2025

链接: https://arxiv.org/abs/2503.07302
作者: Haoyue Dai,Ignavier Ng,Jianle Sun,Zeyu Tang,Gongxu Luo,Xinshuai Dong,Peter Spirtes,Kun Zhang
类目: Machine Learning (cs.LG)
*备注: Appears at ICLR 2025 (oral)

点击查看摘要

[LG-18] MC-GRU:a Multi-Channel GRU network for generalized nonlinear structural response prediction across structures

链接: https://arxiv.org/abs/2503.07258
作者: Shan He,Ruiyang Zhang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-19] Coreset Spectral Clustering

链接: https://arxiv.org/abs/2503.07227
作者: Ben Jourdan,Gregory Schwartzman,Peter Macgregor,He Sun
类目: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS)
*备注:

点击查看摘要

[LG-20] FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updates

链接: https://arxiv.org/abs/2503.07216
作者: Sangwoo Park,Seanie Lee,Byungjoo Kim,Sung Ju Hwang
类目: Machine Learning (cs.LG)
*备注: Preprint

点击查看摘要

[LG-21] How Well Can Differential Privacy Be Audited in One Run?

链接: https://arxiv.org/abs/2503.07199
作者: Amit Keinan,Moshe Shenfeld,Katrina Ligett
类目: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
*备注:

点击查看摘要

[LG-22] Performance-driven Constrained Optimal Auto-Tuner for MPC

链接: https://arxiv.org/abs/2503.07127
作者: Albert Gassol Puigjaner,Manish Prajapat,Andrea Carron,Andreas Krause,Melanie N. Zeilinger
类目: Machine Learning (cs.LG); Robotics (cs.RO)
*备注: 8 pages

点击查看摘要

[LG-23] Improving Deep Ensembles by Estimating Confusion Matrices

链接: https://arxiv.org/abs/2503.07119
作者: Danil Kuzin,Olga Isupova,Steven Reece,Brooke D Simmons
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-24] Sequential Function-Space Variational Inference via Gaussian Mixture Approximation

链接: https://arxiv.org/abs/2503.07114
作者: Menghao Waiyan William Zhu,Pengcheng Hao,Ercan Engin Kuruoğlu
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-25] You Only Debias Once: Towards Flexible Accuracy-Fairness Trade-offs at Inference Time

链接: https://arxiv.org/abs/2503.07066
作者: Xiaotian Han,Tianlong Chen,Kaixiong Zhou,Zhimeng Jiang,Zhangyang Wang,Xia Hu
类目: Machine Learning (cs.LG)
*备注: CPAL2025(Oral)

点击查看摘要

[LG-26] Learning Energy-Based Models by Self-normalising the Likelihood

链接: https://arxiv.org/abs/2503.07021
作者: Hugo Senetaire,Paul Jeha,Pierre-Alexandre Mattei,Jes Frellsen
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 10pages, 3figures

点击查看摘要

[LG-27] How to Train Your Robots? The Impact of Demonstration Modality on Imitation Learning ICRA

链接: https://arxiv.org/abs/2503.07017
作者: Haozhuo Li,Yuchen Cui,Dorsa Sadigh
类目: Robotics (cs.RO); Machine Learning (cs.LG)
*备注: 8 pages, ICRA

点击查看摘要

[LG-28] Learning Nash Equilibrial Hamiltonian for Two-Player Collision-Avoiding Interactions

链接: https://arxiv.org/abs/2503.07013
作者: Lei Zhang,Siddharth Das,Tanner Merry,Wenlong Zhang,Yi Ren
类目: Robotics (cs.RO); Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG)
*备注: Accepted by 2025 ACC

点击查看摘要

[LG-29] Water Quality Data Imputation via A Fast Latent Factorization of Tensors with PID-based Optimizer

链接: https://arxiv.org/abs/2503.06997
作者: Qian Liu,Lan Wang,Bing Yang,Hao Wu
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-30] Ger: Self-Supervised Purification for Time-evolving Graphs PAKDD2025

链接: https://arxiv.org/abs/2503.06990
作者: Hyeonsoo Jo,Jongha Lee,Fanchen Bu,Kijung Shin
类目: Machine Learning (cs.LG)
*备注: PAKDD 2025

点击查看摘要

[LG-31] Learning Decision Trees as Amortized Structure Inference

链接: https://arxiv.org/abs/2503.06985
作者: Mohammed Mahfoud,Ghait Boukachab,Michał Koziarski,Alex Hernandez-Garcia,Stefan Bauer,Yoshua Bengio,Nikolay Malkin
类目: Machine Learning (cs.LG)
*备注: Code: $\href{ [this https URL](https://github.com/GFNOrg/dt-gfn) }{ [this https URL](https://github.com/GFNOrg/dt-gfn) }$

点击查看摘要

[LG-32] FinTSBridge: A New Evaluation Suite for Real-world Financial Prediction with Advanced Time Series Models ICLR2025

链接: https://arxiv.org/abs/2503.06928
作者: Yanlong Wang,Jian Xu,Tiantian Gao,Hongkang Zhang,Shao-Lun Huang,Danny Dongning Sun,Xiao-Ping Zhang
类目: Machine Learning (cs.LG); Trading and Market Microstructure (q-fin.TR)
*备注: ICLR 2025 Workshop Advances in Financial AI

点击查看摘要

[LG-33] ask Vector Quantization for Memory-Efficient Model Merging

链接: https://arxiv.org/abs/2503.06921
作者: Youngeun Kim,Seunghwan Lee,Aecheon Jung,Bogon Ryu,Sungeun Hong
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-34] Combinatorial Optimization via LLM -driven Iterated Fine-tuning

链接: https://arxiv.org/abs/2503.06917
作者: Pranjal Awasthi,Sreenivas Gollapudi,Ravi Kumar,Kamesh Munagala
类目: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-35] You Are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-tailed Data

链接: https://arxiv.org/abs/2503.06916
作者: Shanshan Yan,Zexi Li,Chao Wu,Meng Pang,Yang Lu,Yan Yan,Hanzi Wang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-36] ResMoE: Space-efficient Compression of Mixture of Experts LLM s via Residual Restoration KDD2025

链接: https://arxiv.org/abs/2503.06881
作者: Mengting Ai,Tianxin Wei,Yifan Chen,Zhichen Zeng,Ritchie Zhao,Girish Varatkar,Bita Darvish Rouhani,Xianfeng Tang,Hanghang Tong,Jingrui He
类目: Machine Learning (cs.LG)
*备注: KDD 2025

点击查看摘要

[LG-37] MoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference

链接: https://arxiv.org/abs/2503.06823
作者: Suraiya Tairin,Shohaib Mahmud,Haiying Shen,Anand Iyer
类目: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注:

点击查看摘要

[LG-38] Agile Climate-Sensor Design and Calibration Algorithms Using Machine Learning: Experiments From Cape Point

链接: https://arxiv.org/abs/2503.06777
作者: Travis Barrett,Amit Kumar Mishra
类目: ystems and Control (eess.SY); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-39] ask-Oriented Connectivity for Networked Robotics with Generative AI and Semantic Communications

链接: https://arxiv.org/abs/2503.06771
作者: Peizheng Li,Adnan Aijaz
类目: Robotics (cs.RO); Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI)
*备注: 6 pages, 7 figures. This paper has been submitted to IEEE for possible publication

点击查看摘要

[LG-40] Primal-Dual Sample Complexity Bounds for Constrained Markov Decision Processes with Multiple Constraints

链接: https://arxiv.org/abs/2503.06751
作者: Max Buckley,Konstantinos Papathanasiou,Andreas Spanopoulos
类目: Machine Learning (cs.LG)
*备注: 28 pages (9 main text + 1 references + 18 appendix) 0 figures

点击查看摘要

[LG-41] Faster and Space Efficient Indexing for Locality Sensitive Hashing

链接: https://arxiv.org/abs/2503.06737
作者: Bhisham Dev Verma,Rameshwar Pratap
类目: Data Structures and Algorithms (cs.DS); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-42] Data Efficient Subset Training with Differential Privacy

链接: https://arxiv.org/abs/2503.06732
作者: Ninad Jayesh Gandhi,Moparthy Venkata Subrahmanya Sri Harsha
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-43] Enhancing CBMs Through Binary Distillation with Applications to Test-Time Intervention

链接: https://arxiv.org/abs/2503.06730
作者: Matthew Shen,Aliyah Hsu,Abhineet Agarwal,Bin Yu
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-44] Precise Insulin Delivery for Artificial Pancreas: A Reinforcement Learning Optimized Adaptive Fuzzy Control Approach

链接: https://arxiv.org/abs/2503.06701
作者: Omar Mameche,Abdelhadi Abedou,Taqwa Mezaache,Mohamed Tadjine
类目: ystems and Control (eess.SY); Machine Learning (cs.LG); Optimization and Control (math.OC)
*备注:

点击查看摘要

[LG-45] Reinforcement Learning with Verifiable Rewards: GRPOs Effective Loss Dynamics and Success Amplification

链接: https://arxiv.org/abs/2503.06639
作者: Youssef Mroueh
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-46] Synthetic Data Generation for Minimum-Exposure Navigation in a Time-Varying Environment using Generative AI Models

链接: https://arxiv.org/abs/2503.06619
作者: Nachiket U. Bapat,Randy C. Paffenroth,Raghvendra V. Cowlagi
类目: Machine Learning (cs.LG); Systems and Control (eess.SY)
*备注: Accepted for 2025 ECC

点击查看摘要

[LG-47] Inverse Reinforcement Learning for Minimum-Exposure Paths in Spatiotemporally Varying Scalar Fields

链接: https://arxiv.org/abs/2503.06611
作者: Alexandra E. Ballentine,Raghvendra V. Cowlagi
类目: Machine Learning (cs.LG); Systems and Control (eess.SY)
*备注: Joint submission to MECC-JAVS 2025

点击查看摘要

[LG-48] Interpretable Model Drift Detection

链接: https://arxiv.org/abs/2503.06606
作者: Pranoy Panda,Kancheti Sai Srinivas,Vineeth N Balasubramanian,Gaurav Sinha
类目: Machine Learning (cs.LG)
*备注: Accepted at CODS-COMAD 2024

点击查看摘要

[LG-49] FW-Shapley: Real-time Estimation of Weighted Shapley Values ICASSP2024

链接: https://arxiv.org/abs/2503.06602
作者: Pranoy Panda,Siddharth Tandon,Vineeth N Balasubramanian
类目: Machine Learning (cs.LG)
*备注: Accepted at ICASSP 2024

点击查看摘要

[LG-50] Automated Proof of Polynomial Inequalities via Reinforcement Learning

链接: https://arxiv.org/abs/2503.06592
作者: Banglong Liu,Niuniu Qi,Xia Zeng,Lydia Dehbi,Zhengfeng Yang
类目: Machine Learning (cs.LG); Optimization and Control (math.OC)
*备注:

点击查看摘要

[LG-51] Generative modelling with jump-diffusions

链接: https://arxiv.org/abs/2503.06558
作者: Adrian Baule
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-52] Privacy Protection in Prosumer Energy Management Based on Federated Learning

链接: https://arxiv.org/abs/2503.06455
作者: Yunfeng Li,Xiaolin Li Zhitao Li,Gangqiang Li
类目: Machine Learning (cs.LG)
*备注: 9 pages, 8 figures

点击查看摘要

[LG-53] Generalizable Machine Learning Models for Predicting Data Center Server Power Efficiency and Throughput

链接: https://arxiv.org/abs/2503.06439
作者: Nuoa Lei,Arman Shehabi,Jun Lu,Zhi Cao,Jonathan Koomey,Sarah Smith,Eric Masanet
类目: Machine Learning (cs.LG); Systems and Control (eess.SY)
*备注:

点击查看摘要

[LG-54] Interference-Aware Edge Runtime Prediction with Conformal Matrix Completion

链接: https://arxiv.org/abs/2503.06428
作者: Tianshu Huang,Arjun Ramesh,Emily Ruppel,Nuno Pereira,Anthony Rowe,Carlee Joe-Wong
类目: Machine Learning (cs.LG)
*备注: To appear at MLSys 2025

点击查看摘要

[LG-55] Language Model Personalization via Reward Factorization

链接: https://arxiv.org/abs/2503.06358
作者: Idan Shenfeld,Felix Faltings,Pulkit Agrawal,Aldo Pacchiano
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-56] GIN-Graph: A Generative Interpretation Network for Model-Level Explanation of Graph Neural Networks

链接: https://arxiv.org/abs/2503.06352
作者: Xiao Yue,Guangzhi Qu,Lige Gan
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-57] AI-Driven Optimization of Hardware Overlay Configurations

链接: https://arxiv.org/abs/2503.06351
作者: Rasha Karakchi
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-58] Curriculum Learning-Driven PIELMs for Fluid Flow Simulations

链接: https://arxiv.org/abs/2503.06347
作者: Vikas Dwivedi,Bruno Sixou,Monica Sigovan
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-59] Exploring the Performance Improvement of Tensor Processing Engines through Transformation in the Bit-weight Dimension of MACs

链接: https://arxiv.org/abs/2503.06342
作者: Qizhe Wu,Huawen Liang,Yuchen Gui,Zhichen Zeng,Zerong He,Linfeng Tao,Xiaotian Wang,Letian Zhao,Zhaoxi Zeng,Wei Yuan,Wei Wu,Xi Jin
类目: Hardware Architecture (cs.AR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-60] Backdoor Attacks on Discrete Graph Diffusion Models

链接: https://arxiv.org/abs/2503.06340
作者: Jiawen Wang,Samin Karim,Yuan Hong,Binghui Wang
类目: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-61] Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation

链接: https://arxiv.org/abs/2503.06337
作者: Mohit Pandey,Gopeshh Subbaraj,Artem Cherkasov,Emmanuel Bengio
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-62] Understanding the role of autoencoders for stiff dynamical systems using information theory

链接: https://arxiv.org/abs/2503.06325
作者: Vijayamanikandan Vijayarangan,Harshavardhana A. Uranakara,Francisco E. Hernández-Pérez,Hong G. Im
类目: Machine Learning (cs.LG); Computational Physics (physics.comp-ph)
*备注:

点击查看摘要

[LG-63] Learning and discovering multiple solutions using physics-informed neural networks with random initialization and deep ensemble

链接: https://arxiv.org/abs/2503.06320
作者: Zongren Zou,Zhicheng Wang,George Em Karniadakis
类目: Machine Learning (cs.LG); Computational Physics (physics.comp-ph)
*备注:

点击查看摘要

[LG-64] Poisoned-MRAG : Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation

链接: https://arxiv.org/abs/2503.06254
作者: Yinuo Liu,Zenghui Yuan,Guiyao Tie,Jiawen Shi,Lichao Sun,Neil Zhenqiang Gong
类目: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-65] MAD-MAX: Modular And Diverse Malicious Attack MiXtures for Automated LLM Red Teaming

链接: https://arxiv.org/abs/2503.06253
作者: Stefan Schoepf,Muhammad Zaid Hameed,Ambrish Rawat,Kieran Fraser,Giulio Zizzo,Giandomenico Cornacchia,Mark Purcell
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-66] WaveStitch: Flexible and Fast Conditional Time Series Generation with Diffusion Models

链接: https://arxiv.org/abs/2503.06231
作者: Aditya Shankar,Lydia Y. Chen,Arie van Deursen,Rihan Hai
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-67] Lifelong Learning with Task-Specific Adaptation: Addressing the Stability-Plasticity Dilemma

链接: https://arxiv.org/abs/2503.06213
作者: Ruiyu Wang,Sen Wang,Xinxin Zuo,Qiang Sun
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-68] Generation of Optimized Solidity Code for Machine Learning Models using LLM s

链接: https://arxiv.org/abs/2503.06203
作者: Nikumbh Sarthak Sham(Indian Institute of Technology Kharagpur, India),Sandip Chakraborty(Indian Institute of Technology Kharagpur, India),Shamik Sural(Indian Institute of Technology Kharagpur, India)
类目: Emerging Technologies (cs.ET); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-69] Attackers Can Do Better: Over- and Understated Factors of Model Stealing Attacks

链接: https://arxiv.org/abs/2503.06188
作者: Daryna Oliynyk,Rudolf Mayer,Andreas Rauber
类目: Machine Learning (cs.LG)
*备注: This work has been accepted for publication in the IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). The final version will be available on IEEE Xplore

点击查看摘要

[LG-70] Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks ICLR

链接: https://arxiv.org/abs/2503.06181
作者: Devon Jarvis,Richard Klein,Benjamin Rosman,Andrew M. Saxe
类目: Machine Learning (cs.LG)
*备注: 35 pages; 9 figures; accepted at the International Conference on Learning Representations (ICLR)

点击查看摘要

[LG-71] Invariant Federated Learning: A Novel Approach to Addressing Challenges in Federated Learning for Edge Intelligence

链接: https://arxiv.org/abs/2503.06158
作者: Ziruo Hao,Zhenhua Cui,Tao Yang,Bo Hu,Xiaofeng Wu,Hui Feng
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-72] Do Fairness Interventions Come at the Cost of Privacy: Evaluations for Binary Classifiers

链接: https://arxiv.org/abs/2503.06150
作者: Huan Tian,Guangsheng Zhang,Bo Liu,Tianqing Zhu,Ming Ding,Wanlei Zhou
类目: Machine Learning (cs.LG)
*备注: under review

点击查看摘要

[LG-73] Adaptive UAV-Assisted Hierarchical Federated Learning: Optimizing Energy Latency and Resilience for Dynamic Smart IoT Networks

链接: https://arxiv.org/abs/2503.06145
作者: Xiaohong Yang,Minghui Liwang,Liqun Fu,Yuhan Su,Seyyedali Hosseinalipour,Xianbin Wang,Yiguang Hong
类目: Machine Learning (cs.LG)
*备注: 18 pages, 43 figures

点击查看摘要

[LG-74] BlackGoose Rimer: Harnessing RWKV-7 as a Simple yet Superior Replacement for Transformers in Large-Scale Time Series Modeling

链接: https://arxiv.org/abs/2503.06121
作者: Li weile,Liu Xiao
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-75] Unlocking Pretrained LLM s for Motion-Related Multimodal Generation: A Fine-Tuning Approach to Unify Diffusion and Next-Token Prediction

链接: https://arxiv.org/abs/2503.06119
作者: Shinichi Tanaka,Zhao Wang,Yoichi Kato,Jun Ohya
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-76] Attention-Based Synthetic Data Generation for Calibration-Enhanced Survival Analysis: A Case Study for Chronic Kidney Disease Using Electronic Health Records

链接: https://arxiv.org/abs/2503.06096
作者: Nicholas I-Hsien Kuo,Blanca Gallego,Louisa Jorm
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-77] Clustering-based Meta Bayesian Optimization with Theoretical Guarantee PAKDD2025

链接: https://arxiv.org/abs/2503.06093
作者: Khoa Nguyen,Viet Huynh,Binh Tran,Tri Pham,Tin Huynh,Thin Nguyen
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: Accepted at PAKDD 2025

点击查看摘要

[LG-78] Biased Federated Learning under Wireless Heterogeneity

链接: https://arxiv.org/abs/2503.06078
作者: Muhammad Faraz Ul Abrar,Nicolò Michelusi
类目: Machine Learning (cs.LG); Information Theory (cs.IT); Signal Processing (eess.SP)
*备注: Submitted to IEEE Transactions on Wireless Communications

点击查看摘要

[LG-79] Multi-view Spectral Clustering on the Grassmannian Manifold With Hypergraph Representation

链接: https://arxiv.org/abs/2503.06066
作者: Murong Yang,Shihui Ying,Xin-Jian Xu,Yue Gao
类目: Machine Learning (cs.LG); Social and Information Networks (cs.SI)
*备注: 14 pages, 6 figures, 4 tables

点击查看摘要

[LG-80] Interpretable High-order Knowledge Graph Neural Network for Predicting Synthetic Lethality in Human Cancers

链接: https://arxiv.org/abs/2503.06052
作者: Xuexin Chen,Ruichu Cai,Zhengting Huang,Zijian Li,Jie Zheng,Min Wu
类目: Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
*备注:

点击查看摘要

[LG-81] Data-Free Black-Box Federated Learning via Zeroth-Order Gradient Estimation AAAI2025

链接: https://arxiv.org/abs/2503.06028
作者: Xinge Ma,Jin Wang,Xuejie Zhang
类目: Machine Learning (cs.LG)
*备注: Accepted by AAAI 2025

点击查看摘要

[LG-82] FedEM: A Privacy-Preserving Framework for Concurrent Utility Preservation in Federated Learning

链接: https://arxiv.org/abs/2503.06021
作者: Mingcong Xu,Xiaojin Zhang,Wei Chen,Hai Jin
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-83] Nearly Optimal Differentially Private ReLU Regression

链接: https://arxiv.org/abs/2503.06009
作者: Meng Ding,Mingxi Lei,Shaowei Wang,Tianhang Zheng,Di Wang,Jinhui Xu
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 47 pages

点击查看摘要

[LG-84] Near-Polynomially Competitive Active Logistic Regression

链接: https://arxiv.org/abs/2503.05981
作者: Yihan Zhou,Eric Price,Trung Nguyen
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-85] Generative Multi-Agent Q-Learning for Policy Optimization: Decentralized Wireless Networks

链接: https://arxiv.org/abs/2503.05970
作者: Talha Bozkus,Urbashi Mitra
类目: Machine Learning (cs.LG); Signal Processing (eess.SP)
*备注: This work has been submitted to the IEEE for possible publication

点击查看摘要

[LG-86] Dependency-aware Maximum Likelihood Estimation for Active Learning

链接: https://arxiv.org/abs/2503.05969
作者: Beyza Kalkanli,Tales Imbiriba,Stratis Ioannidis,Deniz Erdogmus,Jennifer Dy
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 26 pages, 8 figures

点击查看摘要

[LG-87] Validating LLM -as-a-Judge Systems in the Absence of Gold Labels

链接: https://arxiv.org/abs/2503.05965
作者: Luke Guerdan,Solon Barocas,Kenneth Holstein,Hanna Wallach,Zhiwei Steven Wu,Alexandra Chouldechova
类目: Machine Learning (cs.LG); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC)
*备注:

点击查看摘要

[LG-88] A Survey on Tabular Data Generation: Utility Alignment Fidelity Privacy and Beyond

链接: https://arxiv.org/abs/2503.05954
作者: Mihaela Cătălina Stoian,Eleonora Giunchiglia,Thomas Lukasiewicz
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-89] Performance Comparisons of Reinforcement Learning Algorithms for Sequential Experimental Design AAAI2025

链接: https://arxiv.org/abs/2503.05905
作者: Yasir Zubayr Barlas,Kizito Salako
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 7 main pages, 19 pages of appendices - paper accepted at the 8th Workshop on Generalization in Planning at AAAI 2025

点击查看摘要

[LG-90] Interpretable Visualizations of Data Spaces for Classification Problems

链接: https://arxiv.org/abs/2503.05861
作者: Christian Jorgensen,Arthur Y. Lin,Rose K. Cersonsky
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 10 pages, 4 figures

点击查看摘要

[LG-91] Slim attention: cut your context memory in half without loss of accuracy – K-cache is all you need for MHA

链接: https://arxiv.org/abs/2503.05840
作者: Nils Graef,Andrew Wasielewski
类目: Machine Learning (cs.LG)
*备注: 17 pages, 7 figures

点击查看摘要

[LG-92] Refined Policy Distillation: From VLA Generalists to RL Experts

链接: https://arxiv.org/abs/2503.05833
作者: Tobias Jülg,Wolfram Burgard,Florian Walter
类目: Robotics (cs.RO); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-93] Closing the Intent-to-Reality Gap via Fulfillm ent Priority Logic

链接: https://arxiv.org/abs/2503.05818
作者: Bassel El Mabsout,Abdelrahman AbdelGawad,Renato Mancuso
类目: Machine Learning (cs.LG); Robotics (cs.RO)
*备注:

点击查看摘要

[LG-94] GraphGarment: Learning Garment Dynamics for Bimanual Cloth Manipulation Tasks

链接: https://arxiv.org/abs/2503.05817
作者: Wei Chen,Kelin Li,Dongmyoung Lee,Xiaoshuai Chen,Rui Zong,Petar Kormushev
类目: Robotics (cs.RO); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-95] How Do Consumers Really Choose: Exposing Hidden Preferences with the Mixture of Experts Model

链接: https://arxiv.org/abs/2503.05800
作者: Diego Vallarino
类目: Machine Learning (cs.LG); Econometrics (econ.EM)
*备注:

点击查看摘要

[LG-96] EXALT: EXplainable ALgorithmic Tools for Optimization Problems

链接: https://arxiv.org/abs/2503.05789
作者: Zuzanna Bączek,Michał Bizoń,Aneta Pawelec,Piotr Sankowski
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-97] Evaluation of Missing Data Imputation for Time Series Without Ground Truth

链接: https://arxiv.org/abs/2503.05775
作者: Rania Farjallah,Bassant Selim,Brigitte Jaumard,Samr Ali,Georges Kaddoum
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: Accepted for publication in IEEE ICC 2025 (International Conference on Communications). The paper consists of 6 pages including references and contains 5 figures

点击查看摘要

[LG-98] GeoJEPA: Towards Eliminating Augmentation- and Sampling Bias in Multimodal Geospatial Learning

链接: https://arxiv.org/abs/2503.05774
作者: Theodor Lundqvist,Ludvig Delvret
类目: Machine Learning (cs.LG); Databases (cs.DB)
*备注: 131 pages, 49 figures, 48 tables

点击查看摘要

[LG-99] Complex Networks for Pattern-Based Data Classification

链接: https://arxiv.org/abs/2503.05772
作者: Josimar Chire,Khalid Mahmood,Zhao Liang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-100] A Materials Foundation Model via Hybrid Invariant-Equivariant Architectures

链接: https://arxiv.org/abs/2503.05771
作者: Keqiang Yan,Montgomery Bohde,Andrii Kryvenko,Ziyu Xiang,Kaiji Zhao,Siya Zhu,Saagar Kolachina,Doğuhan Sarıtürk,Jianwen Xie,Raymundo Arroyave,Xiaoning Qian,Xiaofeng Qian,Shuiwang Ji
类目: Machine Learning (cs.LG); Materials Science (cond-mat.mtrl-sci); Computational Physics (physics.comp-ph)
*备注: Preprint

点击查看摘要

[LG-101] Geometric Properties and Graph-Based Optimization of Neural Networks: Addressing Non-Linearity Dimensionality and Scalability

链接: https://arxiv.org/abs/2503.05761
作者: Michael Wienczkowski,Addisu Desta,Paschal Ugochukwu
类目: Machine Learning (cs.LG)
*备注: 12 pages

点击查看摘要

[LG-102] Examining the Dynamics of Local and Transfer Passenger Share Patterns in Air Transportation

链接: https://arxiv.org/abs/2503.05754
作者: Xufang Zheng,Qilei Zhang,Victoria Cobb,Max Z. Li
类目: Computers and Society (cs.CY); Machine Learning (cs.LG); General Economics (econ.GN)
*备注: 30 pages, 14 figures, 1 table

点击查看摘要

[LG-103] Unsupervised Clustering Approaches for Autism Screening: Achieving 95.31% Accuracy with a Gaussian Mixture Model

链接: https://arxiv.org/abs/2503.05746
作者: Nora Fink
类目: Computers and Society (cs.CY); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-104] Identifying Dealbreakers and Robust Policies for the Energy Transition Amid Unexpected Events

链接: https://arxiv.org/abs/2503.05735
作者: Diederik Coppitters,Gabriel Wiest,Leonard Göke,Francesco Contino,André Bardow,Stefano Moret
类目: Computers and Society (cs.CY); Machine Learning (cs.LG); Physics and Society (physics.soc-ph)
*备注: 60 pages, 23 figures

点击查看摘要

[LG-105] Discovering the influence of personal features in psychological processes using Artificial Intelligence techniques: the case of COVID19 lockdown in Spain

链接: https://arxiv.org/abs/2503.05729
作者: Blanca Mellor-Marsa,Alfredo Guitian,Andrew Coney,Berta Padilla,Alberto Nogales
类目: Computers and Society (cs.CY); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-106] Investigating Role of Personal Factors in Shaping Responses to Active Shooter Incident using Machine Learning

链接: https://arxiv.org/abs/2503.05719
作者: Ruying Liu,Burçin Becerik-Gerber,Gale M. Lucas
类目: Computers and Society (cs.CY); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-107] zScore: A Universal Decentralised Reputation System for the Blockchain Economy

链接: https://arxiv.org/abs/2503.05718
作者: Himanshu Udupi,Ashutosh Sahoo,Akshay S. P.,Gurukiran S.,Parag Paul,Petrus C. Martens
类目: Computers and Society (cs.CY); Computational Engineering, Finance, and Science (cs.CE); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-108] Using Artificial Intelligence to Improve Classroom Learning Experience

链接: https://arxiv.org/abs/2503.05709
作者: Shadeeb Hossain
类目: Computers and Society (cs.CY); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-109] Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up

链接: https://arxiv.org/abs/2503.07594
作者: Paul Mangold,Alain Durmus,Aymeric Dieuleveut,Eric Moulines
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Optimization and Control (math.OC)
*备注:

点击查看摘要

[LG-110] Efficient Distributed Learning over Decentralized Networks with Convoluted Support Vector Machine

链接: https://arxiv.org/abs/2503.07563
作者: Canyi Chen,Nan Qiao,Liping Zhu
类目: Machine Learning (stat.ML); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-111] ECNN: A Low-complex Adjustable CNN for Industrial Pump Monitoring Using Vibration Data

链接: https://arxiv.org/abs/2503.07401
作者: Jonas Ney,Norbert Wehn
类目: ignal Processing (eess.SP); Machine Learning (cs.LG)
*备注: Accepted and to be presented as a poster at the 2025 IEEE Symposium Series on Computational Intelligence (SSCI)

点击查看摘要

[LG-112] Materials Map Integrating Experimental and Computational Data through Graph-Based Machine Learning for Enhanced Materials Discovery

链接: https://arxiv.org/abs/2503.07378
作者: Yusuke Hashimoto,Xue Jia,Li Hao,Takaaki Toma
类目: Materials Science (cond-mat.mtrl-sci); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-113] Score-informed Music Source Separation: Improving Synthetic-to-real Generalization in Classical Music

链接: https://arxiv.org/abs/2503.07352
作者: Eetu Tunturi,David Diaz-Guerra,Archontis Politis,Tuomas Virtanen
类目: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)
*备注: 5 pages, 2 figures, submitted to Eusipco2025

点击查看摘要

[LG-114] Decision-Dependent Stochastic Optimization: The Role of Distribution Dynamics

链接: https://arxiv.org/abs/2503.07324
作者: Zhiyu He,Saverio Bolognani,Florian Dörfler,Michael Muehlebach
类目: Optimization and Control (math.OC); Machine Learning (cs.LG); Systems and Control (eess.SY)
*备注:

点击查看摘要

[LG-115] he influence of missing data mechanisms and simple missing data handling techniques on fairness

链接: https://arxiv.org/abs/2503.07313
作者: Aeysha Bhatti,Trudie Sandrock,Johane Nienkemper-Swanepoel
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-116] A Unified View of Optimal Kernel Hypothesis Testing

链接: https://arxiv.org/abs/2503.07084
作者: Antonin Schrab
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Methodology (stat.ME)
*备注: 46 pages, 1 figure

点击查看摘要

[LG-117] Assessing Uncertainty in Stock Returns: A Gaussian Mixture Distribution-Based Method

链接: https://arxiv.org/abs/2503.06929
作者: Yanlong Wang,Jian Xu,Shao-Lun Huang,Danny Dongning Sun,Xiao-Ping Zhang
类目: Risk Management (q-fin.RM); Machine Learning (cs.LG)
*备注: 23 pages

点击查看摘要

[LG-118] Unique Rashomon Sets for Robust Active Learning

链接: https://arxiv.org/abs/2503.06770
作者: Simon Nugyen,Kentaro Hoffman,Tyler McCormick
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-119] Higher Order Reduced Rank Regression

链接: https://arxiv.org/abs/2503.06528
作者: Leia Greenberg,Haim Avron
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Numerical Analysis (math.NA); Optimization and Control (math.OC)
*备注:

点击查看摘要

[LG-120] Fairness-aware organ exchange and kidney paired donation

链接: https://arxiv.org/abs/2503.06431
作者: Mingrui Zhang,Xiaowu Dai,Lexin Li
类目: Methodology (stat.ME); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-121] Bayesian Optimization for Robust Identification of Ornstein-Uhlenbeck Model

链接: https://arxiv.org/abs/2503.06381
作者: Jinwen Xu,Qin Lu,Yaakov Bar-Shalom
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Methodology (stat.ME)
*备注:

点击查看摘要

[LG-122] A quantum annealing approach to graph node embedding

链接: https://arxiv.org/abs/2503.06332
作者: Hristo N. Djidjev
类目: Quantum Physics (quant-ph); Machine Learning (cs.LG)
*备注: 26 pages, 4 figures

点击查看摘要

[LG-123] Double Debiased Machine Learning for Mediation Analysis with Continuous Treatments AISTATS2025

链接: https://arxiv.org/abs/2503.06156
作者: Houssam Zenati,Judith Abécassis,Julie Josse,Bertrand Thirion
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: To appear in AISTATS 2025

点击查看摘要

[LG-124] On Statistical Estimation of Edge-Reinforced Random Walks

链接: https://arxiv.org/abs/2503.06115
作者: Qinghua(Devon)Ding,Venkat Anantharam
类目: Machine Learning (stat.ML); Information Theory (cs.IT); Machine Learning (cs.LG); Probability (math.PR)
*备注: This is the full version of the conference paper in submission to ISIT 2025

点击查看摘要

[LG-125] Fixing the Pitfalls of Probabilistic Time-Series Forecasting Evaluation by Kernel Quadrature

链接: https://arxiv.org/abs/2503.06079
作者: Masaki Adachi,Masahiro Fujisawa,Michael A Osborne
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: 11 pages, 6 figures

点击查看摘要

[LG-126] Randomized Quasi-Monte Carlo Features for Kernel Approximation

链接: https://arxiv.org/abs/2503.06041
作者: Yian Huang,Zhen Huang
类目: Methodology (stat.ME); Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-127] Analyzing the Role of Permutation Invariance in Linear Mode Connectivity

链接: https://arxiv.org/abs/2503.06001
作者: Keyao Zhan,Puheng Li,Lei Wu
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-128] SODAs: Sparse Optimization for the Discovery of Differential and Algebraic Equations

链接: https://arxiv.org/abs/2503.05993
作者: Manu Jayadharan,Christina Catlett,Arthur N. Montanari,Niall M. Mangan
类目: Dynamical Systems (math.DS); Machine Learning (cs.LG); Computational Physics (physics.comp-ph)
*备注: 23 pages, 5 figures, Supplementary attached: 6 pages

点击查看摘要

[LG-129] Enhanced Denoising and Convergent Regularisation Using Tweedie Scaling

链接: https://arxiv.org/abs/2503.05956
作者: Naïl Khelifa,Ferdia Sherry,Carola-Bibiane Schönlieb
类目: Image and Video Processing (eess.IV); Machine Learning (cs.LG)
*备注: Accepted for publication at SSVM 2025

点击查看摘要

[LG-130] Bypassing orthogonalization in the quantum DPP sampler

链接: https://arxiv.org/abs/2503.05906
作者: Michaël Fanuel,Rémi Bardenet
类目: Quantum Physics (quant-ph); Machine Learning (cs.LG); Computation (stat.CO)
*备注: 44 pages, 16 figures

点击查看摘要

[LG-131] Machine Learning-based Regional Cooling Demand Prediction with Optimised Dataset Partitioning

链接: https://arxiv.org/abs/2503.05813
作者: Meng Zhang,Zhihui Li,Zhibin Yu
类目: Physics and Society (physics.soc-ph); Machine Learning (cs.LG); Computational Physics (physics.comp-ph)
*备注: 20 pages, 10 figures

点击查看摘要

[LG-132] Sample size determination for machine learning in medical research

链接: https://arxiv.org/abs/2503.05809
作者: Wan Nor Arifin,Najib Majdi Yaacob
类目: Methodology (stat.ME); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-133] Learning conformational ensembles of proteins based on backbone geometry

链接: https://arxiv.org/abs/2503.05738
作者: Nicolas Wolf,Leif Seute,Vsevolod Viliuga,Simon Wagner,Jan Stühmer,Frauke Gräter
类目: Biomolecules (q-bio.BM); Statistical Mechanics (cond-mat.stat-mech); Machine Learning (cs.LG); Computational Physics (physics.comp-ph)
*备注:

点击查看摘要

信息检索

[IR-0] alking to GDELT Through Knowledge Graphs

链接: https://arxiv.org/abs/2503.07584
作者: Audun Myers,Max Vargas,Sinan G. Aksoy,Cliff Joslyn,Benjamin Wilson,Tom Grimes
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-1] Process-Supervised LLM Recommenders via Flow-guided Tuning

链接: https://arxiv.org/abs/2503.07377
作者: Chongming Gao,Mengyao Gao,Chenxiao Fan,Shuai Yuan,Wentao Shi,Xiangnan He
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-2] AlignPxtr: Aligning Predicted Behavior Distributions for Bias-Free Video Recommendations

链接: https://arxiv.org/abs/2503.06920
作者: Chengzhi Lin,Chuyuan Wang,Annan Xie,Wuhong Wang,Ziye Zhang,Canguang Ruan,Yuancai Huang,Yongqi Liu
类目: Information Retrieval (cs.IR)
*备注: video recommendation. 7 page, 1 figure

点击查看摘要

[IR-3] Improving Access to Trade and Investment Information in Thailand through Intelligent Document Retrieval

链接: https://arxiv.org/abs/2503.06489
作者: Sirinda Palahan
类目: Information Retrieval (cs.IR); Social and Information Networks (cs.SI)
*备注:

点击查看摘要

附件下载

点击下载今日全部论文列表