Arxiv今日论文 | 2025-03-17

本篇博文主要内容为 2025-03-17 从Arxiv.org论文网站获取的最新论文列表，自动更新，按照NLP、CV、ML、AI、IR五个大方向区分，若需要邮件定时接收，请在评论区留下你的邮箱号。

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

友情提示: 如何您需要邮箱接收每日论文数据，请在评论处留下你的邮箱。

链接: https://arxiv.org/abs/2503.11630
作者: Tamar I. Regev,Chiebuka Ohams,Shaylee Xie,Lukas Wolf,Evelina Fedorenko,Alex Warstadt,Ethan Wilcox,Tiago Pimentel
机构: MIT(麻省理工学院); ETH Zürich(瑞士联邦理工学院); Georgetown University(乔治城大学); UCSD(加州大学圣地亚哥分校)
类目: Computation and Language (cs.CL); Information Theory (cs.IT)
备注: 12 pages, 4 figures, recently submitted to ACL

点击查看摘要

[NLP-1] Neutralizing Bias in LLM Reasoning using Entailment Graphs

链接: https://arxiv.org/abs/2503.11614
作者: Liang Cheng,Tianyi Li,Zhaowei Wang,Tianyang Liu,Mark Steedman
机构: University of Edinburgh (爱丁堡大学); HKUST (香港科技大学)
类目: Computation and Language (cs.CL)
备注: 17 pages, 7 figures

点击查看摘要

[NLP-2] Do Construction Distributions Shape Formal Language Learning In German BabyLMs?

链接: https://arxiv.org/abs/2503.11593
作者: Bastian Bunzeck,Daniel Duran,Sina Zarrieß
机构: Bielefeld University (比勒费尔德大学), Germany
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-3] Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLM s using Semantic Space ICLR2025

链接: https://arxiv.org/abs/2503.11586
作者: Zhiliang Chen,Xinyuan Niu,Chuan-Sheng Foo,Bryan Kian Hsiang Low
机构: Department of Computer Science, National University of Singapore (新加坡国立大学); Institute for Infocomm Research (I2R), ASTAR, Singapore (新加坡科技研究局信息通信研究院); Centre for Frontier AI Research (CFAR), ASTAR, Singapore (前沿人工智能研究中心)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: ICLR 2025 Spotlight

点击查看摘要

[NLP-4] Exploring Typographic Visual Prompts Injection Threats in Cross-Modality Generation Models

链接: https://arxiv.org/abs/2503.11519
作者: Hao Cheng,Erjia Xiao,Yichi Wang,Kaidi Xu,Mengshu Sun,Jindong Gu,Renjing Xu
机构: HKUST (香港科技大学(广州)); BJUT (北京工业大学); Drexel University (德雷塞尔大学); University of Oxford (牛津大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-5] Prompt Injection Detection and Mitigation via AI Multi-Agent NLP Frameworks

链接: https://arxiv.org/abs/2503.11517
作者: Diego Gosmar,Deborah A. Dahl,Dario Gosmar
机构: XCALLY; Open Voice Interoperability Initiative (开放语音互操作性计划), Linux Foundation AI & Data (Linux 基金会人工智能与数据); Conversational Technologies (对话技术); Open Voice Interoperability Initiative (开放语音互操作性计划), Linux Foundation AI & Data (Linux 埡金会人工智能与数据); Polytechnic University of Turin (都灵理工大学); Mu Nu Chapter of IEEE-HKN (IEEE-HKN Mu Nu分会)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA)
备注: 22 pages, 9 figures

点击查看摘要

[NLP-6] kZero: Zero-Shot Text-Guided Graphics Program Synthesis

链接: https://arxiv.org/abs/2503.11509
作者: Jonas Belouadi,Eddy Ilg,Margret Keuper,Hideki Tanaka,Masao Utiyama,Raj Dabre,Steffen Eger,Simone Paolo Ponzetto
机构: 未知
类目: Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[NLP-7] Cerebrum (AIOS SDK): A Platform for Agent Development Deployment Distribution and Discovery NAACL

链接: https://arxiv.org/abs/2503.11444
作者: Balaji Rama,Kai Mei,Yongfeng Zhang
机构: Rutgers University (罗格斯大学)
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Operating Systems (cs.OS)
备注: Accepted to the 2025 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) - System Demonstration Track

点击查看摘要

[NLP-8] xt Compression for Efficient Language Generation NAACL

链接: https://arxiv.org/abs/2503.11426
作者: David Gu,Peter Belcak,Roger Wattenhofer
机构: ETH Zurich; NVIDIA (英伟达)
类目: Computation and Language (cs.CL)
备注: accepted to NAACL SRW 2025

点击查看摘要

[NLP-9] Optimizing Large Language Models for Detecting Symptoms of Comorbid Depression or Anxiety in Chronic Diseases: Insights from Patient Messages

链接: https://arxiv.org/abs/2503.11384
作者: Jiyeong Kim,Stephen P. Ma,Michael L. Chen,Isaac R. Galatzer-Levy,John Torous,Peter J. van Roessel,Christopher Sharp,Michael A. Pfeffer,Carolyn I. Rodriguez,Eleni Linos,Jonathan H. Chen
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-10] Modeling Subjectivity in Cognitive Appraisal with Language Models

链接: https://arxiv.org/abs/2503.11381
作者: Yuxiang Zhou,Hainiu Xu,Desmond C. Ong,Petr Slovak,Yulan He
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-11] Advancing the Database of Cross-Linguistic Colexifications with New Workflows and Data

链接: https://arxiv.org/abs/2503.11377
作者: Annika Tjuka,Robert Forkel,Christoph Rzymski,Johann-Mattis List
机构: Max Planck Institute for Evolutionary Anthropology (马克斯·普朗克进化人类学研究所), Leipzig, Germany; Chair of Multilingual Computational Linguistics (多语言计算语言学主席), University of Passau (帕绍大学), Passau, Germany
类目: Computation and Language (cs.CL); Databases (cs.DB)
备注:

点击查看摘要

[NLP-12] Annotating Scientific Uncertainty: A comprehensive model using linguistic patterns and comparison with existing approaches

链接: https://arxiv.org/abs/2503.11376
作者: Panggih Kusuma Ningrum,Philipp Mayr,Nina Smirnova,Iana Atanassova
机构: Université Marie et Louis Pasteur, CRIT, F-25000 Besançon, France; GESIS –- Leibniz Institute for the Social Sciences, Cologne, Germany; Institut Universitaire de France (IUF), France
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Digital Libraries (cs.DL)
备注: Paper Accepted for Publication in the Journal of Informetrics (2025)

点击查看摘要

[NLP-13] RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation

【速读】：该论文旨在研究大型语言模型（LLMs）在自然灾害情境下的常识推理能力，特别是在不同时间框架内的应对措施。为解决这一问题，论文构建了一个名为\textsfRESPONSE的人类编纂数据集，包含1789个标注实例与6037组问题，用于评估LLMs在灾难场景中的常识推理性能。关键在于设计了一个包含问题描述、缺失资源、时间敏感型解决方案及其合理化说明的数据集，并通过自动化指标与人工评估相结合的方式，对比LLMs生成的建议与人类响应的准确性。研究发现，即使最先进的模型如GPT-4，在即时响应行动方面仅达到37%的人类评估正确率，表明LLMs在危机情境下具备显著提升空间。

链接: https://arxiv.org/abs/2503.11348
作者: Aissatou Diallo,Antonis Bikakis,Luke Dickens,Anthony Hunter,Rob Miller
机构: University College London (伦敦大学学院)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

Abstract:An interesting class of commonsense reasoning problems arises when people are faced with natural disasters. To investigate this topic, we present \textsfRESPONSE, a human-curated dataset containing 1789 annotated instances featuring 6037 sets of questions designed to assess LLMs’ commonsense reasoning in disaster situations across different time frames. The dataset includes problem descriptions, missing resources, time-sensitive solutions, and their justifications, with a subset validated by environmental engineers. Through both automatic metrics and human evaluation, we compare LLM-generated recommendations against human responses. Our findings show that even state-of-the-art models like GPT-4 achieve only 37% human-evaluated correctness for immediate response actions, highlighting significant room for improvement in LLMs’ ability for commonsense reasoning in crises.
zh

[NLP-14] AIstorian lets AI be a historian: A KG-powered multi-agent system for accurate biography generation

链接: https://arxiv.org/abs/2503.11346
作者: Fengyu Li(1),Yilin Li(1),Junhao Zhu(1),Lu Chen(1),Yanfei Zhang(1),Jia Zhou(1),Hui Zu(1),Jingwen Zhao(2),Yunjun Gao(1) ((1) Zhejiang University, (2) Poisson Lab, Huawei)
机构: Zhejiang University (浙江大学); Poisson Lab (泊松实验室), Huawei (华为)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-15] Rule-Guided Feedback: Enhancing Reasoning by Enforcing Rule Adherence in Large Language Models

链接: https://arxiv.org/abs/2503.11336
作者: Aissatou Diallo,Antonis Bikakis,Luke Dickens,Anthony Hunter,Rob Miller
机构: University College London (伦敦大学学院)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-16] Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering

链接: https://arxiv.org/abs/2503.11314
作者: Xinyu Tang,Xiaolei Wang,Zhihao Lv,Yingqian Min,Wayne Xin Zhao,Binbin Hu,Ziqi Liu,Zhiqiang Zhang
机构: Gaoling School of Artificial Intelligence, Renmin University of China (高瓴人工智能学院，中国人民大学); Ant Group (蚂蚁集团)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-17] Are formal and functional linguistic mechanisms dissociated?

链接: https://arxiv.org/abs/2503.11302
作者: Michael Hanna,Sandro Pezzelle,Yonatan Belinkov
机构: Institute for Logic, Language, and Computation (逻辑、语言和计算研究所), University of Amsterdam (阿姆斯特丹大学); Technion – Israel Institute of Technology (以色列理工学院)
类目: Computation and Language (cs.CL)
备注: 35 pages, 10 figures, 3 tables. Code available at this https URL

点击查看摘要

[NLP-18] GNNs as Predictors of Agent ic Workflow Performances

链接: https://arxiv.org/abs/2503.11301
作者: Yuanshuo Zhang,Yuchen Hou,Bohan Tang,Shuo Chen,Muhan Zhang,Xiaowen Dong,Siheng Chen
机构: 未知
类目: Computation and Language (cs.CL); Multiagent Systems (cs.MA)
备注: 15 pages, 11 figures

点击查看摘要

[NLP-19] BriLLM : Brain-inspired Large Language Model

链接: https://arxiv.org/abs/2503.11299
作者: Hai Zhao,Hongqiu Wu,Dongjie Yang,Anni Zou,Jiale Hong
机构: Computer School, Shanghai Jiao Tong University (计算机学院，上海交通大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-20] High-Dimensional Interlingual Representations of Large Language Models

链接: https://arxiv.org/abs/2503.11280
作者: Bryan Wilie,Samuel Cahyawijaya,Junxian He,Pascale Fung
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-21] Line of Duty: Evaluating LLM Self-Knowledge via Consistency in Feasibility Boundaries NAACL2025

链接: https://arxiv.org/abs/2503.11256
作者: Sahil Kale,Vijaykant Nadadur
机构: Knowledgeverse AI (知识宇宙人工智能)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 14 pages, 8 figures, Accepted to the 5th TrustNLP Workshop at NAACL 2025

点击查看摘要

[NLP-22] Step-Video-TI2V Technical Report: A State-of-the-Art Text-Driven Image-to-Video Generation Model

链接: https://arxiv.org/abs/2503.11251
作者: Haoyang Huang,Guoqing Ma,Nan Duan,Xing Chen,Changyi Wan,Ranchen Ming,Tianyu Wang,Bo Wang,Zhiying Lu,Aojie Li,Xianfang Zeng,Xinhao Zhang,Gang Yu,Yuhe Yin,Qiling Wu,Wen Sun,Kang An,Xin Han,Deshan Sun,Wei Ji,Bizhu Huang,Brian Li,Chenfei Wu,Guanzhe Huang,Huixin Xiong,Jiaxin He,Jianchang Wu,Jianlong Yuan,Jie Wu,Jiashuai Liu,Junjing Guo,Kaijun Tan,Liangyu Chen,Qiaohui Chen,Ran Sun,Shanshan Yuan,Shengming Yin,Sitong Liu,Wei Chen,Yaqi Dai,Yuchu Luo,Zheng Ge,Zhisheng Guan,Xiaoniu Song,Yu Zhou,Binxing Jiao,Jiansheng Chen,Jing Li,Shuchang Zhou,Xiangyu Zhang,Yi Xiu,Yibo Zhu,Heung-Yeung Shum,Daxin Jiang
机构: Step-Video Team (StepFun)
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注: 7 pages

点击查看摘要

[NLP-23] Reasoning -Grounded Natural Language Explanations for Language Models

链接: https://arxiv.org/abs/2503.11248
作者: Vojtech Cahlik,Rodrigo Alves,Pavel Kordik
机构: 未知
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-24] Collaboration is all you need: LLM Assisted Safe Code Translation

链接: https://arxiv.org/abs/2503.11237
作者: Rabimba Karanjai,Sam Blackshear,Lei Xu,Weidong Shi
机构: University Of Houston (休斯敦大学); Mysten Labs; Kent State University (肯特州立大学)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Software Engineering (cs.SE)
备注:

点击查看摘要

[NLP-25] PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders

链接: https://arxiv.org/abs/2503.11232
作者: Ahmed Frikha,Muhammad Reza Ar Razi,Krishna Kanth Nakka,Ricardo Mendes,Xue Jiang,Xuebing Zhou
机构: Huawei Munich Research Center (华为慕尼黑研究中心)
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-26] Exploring the Potential of Large Multimodal Models as Effective Alternatives for Pronunciation Assessment

链接: https://arxiv.org/abs/2503.11229
作者: Ke Wang,Lei He,Kun Liu,Yan Deng,Wenning Wei,Sheng Zhao
机构: Microsoft (微软)
类目: ound (cs.SD); Computation and Language (cs.CL); Audio and Speech Processing (eess.AS)
备注: 7 pages

点击查看摘要

[NLP-27] chnologies on Effectiveness and Efficiency: A Survey of State Spaces Models

链接: https://arxiv.org/abs/2503.11224
作者: Xingtai Lv,Youbang Sun,Kaiyan Zhang,Shang Qu,Xuekai Zhu,Yuchen Fan,Yi Wu,Ermo Hua,Xinwei Long,Ning Ding,Bowen Zhou
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-28] Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering

链接: https://arxiv.org/abs/2503.11197
作者: Gang Li,Jizhong Liu,Heinrich Dinkel,Yadong Niu,Junbo Zhang,Jian Luan
机构: Xiaomi Corporation (小米公司), China
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Audio and Speech Processing (eess.AS)
备注:

点击查看摘要

[NLP-29] Cross-Modal Learning for Music-to-Music-Video Description Generation NAACL2025 REPL4NLP2025

链接: https://arxiv.org/abs/2503.11190
作者: Zhuoyuan Mao,Mengjie Zhao,Qiyu Wu,Zhi Zhong,Wei-Hsiang Liao,Hiromi Wakaki,Yuki Mitsufuji
机构: Sony Group Corporation (索尼集团公司); Sony AI (索尼AI)
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: Accepted by RepL4NLP 2025 @ NAACL 2025

点击查看摘要

[NLP-30] Palette of Language Models: A Solver for Controlled Text Generation NAACL2025

链接: https://arxiv.org/abs/2503.11182
作者: Zhe Yang,Yi Huang,Yaqin Chen,Xiaoting Wu,Junlan Feng,Chao Deng
机构: JIUTIAN Team, China Mobile Research Institute (中国移动研究院)
类目: Computation and Language (cs.CL)
备注: Accepted to NAACL 2025, Main, Long Paper

点击查看摘要

[NLP-31] DeskVision: Large Scale Desktop Region Captioning for Advanced GUI Agents

链接: https://arxiv.org/abs/2503.11170
作者: Yibin Xu,Liang Yang,Hao Chen,Hua Wang,Zhi Chen,Yaohua Tang
机构: Moore Threads AI
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-32] owards Extreme Pruning of LLM s with Plug-and-Play Mixed Sparsity

链接: https://arxiv.org/abs/2503.11164
作者: Chi Xu,Gefei Zhang,Yantong Zhu,Luca Benini,Guosheng Hu,Yawei Li,Zhihong Zhang
机构: Xiamen University (厦门大学); ETH Zurich (瑞士苏黎世联邦理工学院); University of Bristol (布里斯托尔大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-33] Dont Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models ICLR2025

链接: https://arxiv.org/abs/2503.11154
作者: Shaotian Yan,Chen Shen,Wenxiao Wang,Liang Xie,Junjie Liu,Jieping Ye
机构: Alibaba Cloud Computing (阿里云); College of Software, Zhejiang University (浙江大学软件学院); Zhejiang University of Technology, College of Computer Science and Technology (浙江工业大学计算机科学与技术学院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Accepted by ICLR2025

点击查看摘要

[NLP-34] MoLEx: Mixture of Layer Experts for Finetuning with Sparse Upcycling

链接: https://arxiv.org/abs/2503.11144
作者: Rachel S.Y. Teo,Tan M. Nguyen
机构: Department of Mathematics (数学系), National University of Singapore (新加坡国立大学)
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-35] X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression

链接: https://arxiv.org/abs/2503.11132
作者: Guihong Li,Mehdi Rezagholizadeh,Mingyu Yang,Vikram Appia,Emad Barsoum
机构: Advanced Micro Devices, Inc. (AMD)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-36] UMB@PerAnsSumm 2025: Enhancing Perspective-Aware Summarization with Prompt Optimization and Supervised Fine-Tuning ALT NAACL

链接: https://arxiv.org/abs/2503.11118
作者: Kristin Qi,Youxiang Zhu,Xiaohui Liang
机构: Department of Computer Science, University of Massachusetts Boston (马萨诸塞大学波士顿分校)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: CL4HEALTH NAACL: Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

点击查看摘要

[NLP-37] rust in Disinformation Narratives: a Trust in the News Experiment

链接: https://arxiv.org/abs/2503.11116
作者: Hanbyul Song,Miguel F. Santos Silva,Jaume Suau,Luis Espinosa-Anke
机构: Universitè Lorraine (洛林大学); Blanquerna University (布兰克内拉大学); CardiffNLP, Cardiff University / AMPLYFI (卡迪夫NLP, 卡迪夫大学 / AMPLYFI)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-38] Limits of KV Cache Compression for Tensor Attention based Autoregressive Transformers

链接: https://arxiv.org/abs/2503.11108
作者: Yifang Chen,Xiaoyu Li,Yingyu Liang,Zhenmei Shi,Zhao Song,Yu Tian
机构: The University of Chicago (芝加哥大学); Stevens Institute of Technology (史蒂文斯理工学院); The University of Hong Kong (香港大学); University of Wisconsin-Madison (威斯康星大学麦迪逊分校); The Simons Institute for the Theory of Computing at UC Berkeley (伯克利加州大学西蒙斯计算理论研究所); Independent Researcher (独立研究员)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computational Complexity (cs.CC); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-39] Semantic and Contextual Modeling for Malicious Comment Detection with BERT-BiLSTM

链接: https://arxiv.org/abs/2503.11084
作者: Zhou Fang,Hanlu Zhang,Jacky He,Zhen Qi,Hongye Zheng
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-40] Joint Training And Decoding for Multilingual End-to-End Simultaneous Speech Translation ICASSP2023

链接: https://arxiv.org/abs/2503.11080
作者: Wuwei Huang,Renren Jin,Wen Zhang,Jian Luan,Bin Wang,Deyi Xiong
机构: 未知
类目: Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)
备注: ICASSP 2023

点击查看摘要

[NLP-41] Large Reasoning Models in Agent Scenarios: Exploring the Necessity of Reasoning Capabilities

链接: https://arxiv.org/abs/2503.11074
作者: Xueyang Zhou,Guiyao Tie,Guowen Zhang,Weidong Wang,Zhigang Zuo,Di Wu,Duanfeng Chu,Pan Zhou,Lichao Sun,Neil Zhenqiang Gong
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 71 pages, 5 figures, 6 tables

点击查看摘要

[NLP-42] RONA: Prag matically Diverse Image Captioning with Coherence Relations NAACL

链接: https://arxiv.org/abs/2503.10997
作者: Aashish Anantha Ramakrishnan,Aadarsh Anantha Ramakrishnan,Dongwon Lee
机构: The Pennsylvania State University (宾夕法尼亚州立大学); National Institute of Technology, Tiruchirappalli (蒂鲁吉拉伯利国立技术学院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: To appear in the NAACL Fourth Workshop on Intelligent and Interactive Writing Assistants (In2Writing), Albuquerque, New Mexico, May 2025, this https URL

点击查看摘要

[NLP-43] aming Knowledge Conflicts in Language Models

链接: https://arxiv.org/abs/2503.10996
作者: Gaotang Li,Yuzhong Chen,Hanghang Tong
机构: 未知
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: 30 pages, 5 figures

点击查看摘要

[NLP-44] gerLLM – A Family of Bangla Large Language Models

链接: https://arxiv.org/abs/2503.10995
作者: Nishat Raihan,Marcos Zampieri
机构: George Mason University (乔治梅森大学), VA, USA
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-45] Combinatorial Optimization for All: Using LLM s to Aid Non-Experts in Improving Optimization Algorithms

链接: https://arxiv.org/abs/2503.10968
作者: Camilo Chacón Sartori,Christian Blum
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Software Engineering (cs.SE)
备注:

点击查看摘要

[NLP-46] Auditing language models for hidden objectives

链接: https://arxiv.org/abs/2503.10965
作者: Samuel Marks,Johannes Treutlein,Trenton Bricken,Jack Lindsey,Jonathan Marcus,Siddharth Mishra-Sharma,Daniel Ziegler,Emmanuel Ameisen,Joshua Batson,Tim Belonax,Samuel R. Bowman,Shan Carter,Brian Chen,Hoagy Cunningham,Carson Denison,Florian Dietz,Satvik Golechha,Akbir Khan,Jan Kirchner,Jan Leike,Austin Meek,Kei Nishimura-Gasparian,Euan Ong,Christopher Olah,Adam Pearce,Fabien Roger,Jeanne Salle,Andy Shih,Meg Tong,Drake Thomas,Kelley Rivoire,Adam Jermyn,Monte MacDiarmid,Tom Henighan,Evan Hubinger
机构: Anthropic; ML Alignment and Theory Scholars
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-47] OASST-ETC Dataset: Alignment Signals from Eye-tracking Analysis of LLM Responses

链接: https://arxiv.org/abs/2503.10927
作者: Angela Lopez-Cardona,Sebastian Idesis,Miguel Barreda-Ángeles,Sergi Abadal,Ioannis Arapakis
机构: Telefónica Scientific Research (Telefónica科学研究院); Universitat Politècnica de Catalunya (巴塞罗那理工学院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: This paper has been accepted to ACM ETRA 2025

点击查看摘要

[NLP-48] HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks ICLR2025

链接: https://arxiv.org/abs/2503.10894
作者: Jiuding Sun,Jing Huang,Sidharth Baskaran,Karel D’Oosterlinck,Christopher Potts,Michael Sklar,Atticus Geiger
机构: Stanford University (斯坦福大学); Confirm Labs; Ghent University (根特大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: ICLR 2025

点击查看摘要

[NLP-49] Chat-TS: Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language Data

链接: https://arxiv.org/abs/2503.10883
作者: Paul Quinlan,Qingguo Li,Xiaodan Zhu
机构: Department of Electrical and Computer Engineering, Queen’s University (电气与计算机工程系, 女王大学); Ingenuity Labs Research Institute, Queen’s University (智慧实验室研究院, 女王大学); Department of Mechanical and Materials Engineering, Queen’s University (机械与材料工程系, 女王大学)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-50] SCE: Scalable Consistency Ensembles Make Blackbox Large Language Model Generation More Reliable

链接: https://arxiv.org/abs/2503.10881
作者: Jiaxin Zhang,Zhuohang Li,Wendi Cui,Kamalika Das,Bradley malin,Sricharan Kumar
机构: Intuit (Intuit); Intuit AI Research (Intuit AI 研究); Vanderbilt University (范德比尔特大学); Vanderbilt University Medical Center (范德比尔特大学医学中心)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-51] owards Understanding Graphical Perception in Large Multimodal Models

链接: https://arxiv.org/abs/2503.10857
作者: Kai Zhang,Jianwei Yang,Jeevana Priya Inala,Chandan Singh,Jianfeng Gao,Yu Su,Chenglong Wang
机构: Microsoft Research (微软研究); The Ohio State University (俄亥俄州立大学)
类目: Graphics (cs.GR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
备注: Work in Progress

点击查看摘要

[NLP-52] Who Relies More on World Knowledge and Bias for Syntactic Ambiguity Resolution: Humans or LLM s?

链接: https://arxiv.org/abs/2503.10838
作者: So Young Lee,Russell Scheinberg,Amber Shore,Ameeta Agrawal
机构: Miami University (迈阿密大学), USA; Portland State University (波特兰州立大学), USA
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-53] hinking Machines: A Survey of LLM based Reasoning Strategies

链接: https://arxiv.org/abs/2503.10814
作者: Dibyanayan Bandyopadhyay,Soham Bhattacharjee,Asif Ekbal
机构: Department of Computer Science and Engineering, IIT Patna (印度理工学院帕特纳计算机科学与工程系); School of AI and Data Science, IIT Jodhpur (印度理工学院焦德普尔人工智能与数据科学学院)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-54] Data Caricatures: On the Representation of African American Language in Pretraining Corpora

链接: https://arxiv.org/abs/2503.10789
作者: Nicholas Deas,Blake Vente,Amith Ananthram,Jessica A. Grieser,Desmond Patton,Shana Kleiner,James Shepard,Kathleen McKeown
机构: Columbia University, Department of Computer Science (哥伦比亚大学，计算机科学系); University of Michigan, Department of Linguistics (密歇根大学，语言学系); University of Pennsylvania, School of Social Policy and Practice, Annenberg School for Communications (宾夕法尼亚大学，社会政策与实践学院，安纳伯格传播学院); University of Tennessee, Knoxville, Department of English (田纳西大学，英语系)
类目: Computation and Language (cs.CL)
备注: Preprint

点击查看摘要

[NLP-55] Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing

链接: https://arxiv.org/abs/2503.10742
作者: Yudong Liu,Jingwei Sun,Yueqian Lin,Jingyang Zhang,Ming Yin,Qinsi Wang,Jianyi Zhang,Hai Li,Yiran Chen
机构: Duke University (杜克大学)
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-56] DarkBench: Benchmarking Dark Patterns in Large Language Models ICLR2025

链接: https://arxiv.org/abs/2503.10728
作者: Esben Kran,Hieu Minh “Jord” Nguyen,Akash Kundu,Sami Jawhar,Jinsuk Park,Mateusz Maria Jurewicz
机构: Apart Research; METR; Independent
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注: Accepted as an Oral paper at ICLR 2025

点击查看摘要

[NLP-57] Word-level Annotation of GDPR Transparency Compliance in Privacy Policies using Large Language Models

链接: https://arxiv.org/abs/2503.10727
作者: Thomas Cory,Wolf Rieder,Julia Krämer,Philip Raschke,Patrick Herbke,Axel Küpper
机构: Technische Universität Berlin (柏林工业大学); Erasmus University Rotterdam (鹿特丹伊拉斯姆斯大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-58] RankPO: Preference Optimization for Job-Talent Matching

链接: https://arxiv.org/abs/2503.10723
作者: Yafei Zhang,Murray Wang,Yu Wang,Xiaohui Wang
机构: Laboratory for AI-Powered Financial Technologies (人工智能金融技术实验室), City University of Hong Kong (香港城市大学), Hong Kong S.A.R., China (中国香港)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG)
备注: 15 pages, 3 figures, 7 tables

点击查看摘要

[NLP-59] AttentionRAG : Attention-Guided Context Pruning in Retrieval-Augmented Generation

链接: https://arxiv.org/abs/2503.10720
作者: Yixiong Fang,Tianran Sun,Yuling Shi,Xiaodong Gu
机构: Shanghai Jiao Tong University (上海交通大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-60] ZeroMerge: Parameter-Free KV Cache Compression for Memory-Efficient Long-Context LLM s

链接: https://arxiv.org/abs/2503.10714
作者: Xin Liu,Pei Liu,Guoming Tang
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-61] CALLM : Context-Aware Emotion Analysis in Cancer Survivors Using LLM s and Retrieval-Augmented Mobile Diaries

链接: https://arxiv.org/abs/2503.10707
作者: Zhiyuan Wang,Katharine E. Daniel,Laura E. Barnes,Philip I. Chow
机构: Department of Systems and Info. Engineering (系统与信息工程系), University of Virginia (弗吉尼亚大学); Center for Behavioral Health and Tech (行为健康技术中心), University of Virginia (弗吉尼亚大学); Center for Behavioral Health and Technology (行为健康技术中心), University of Virginia (弗吉尼亚大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注: 10 pages, including 3 figures; appendix: 8 pages with 19 figures

点击查看摘要

[NLP-62] SciFi-Benchmark: How Would AI-Powered Robots Behave in Science Fiction Literature?

链接: https://arxiv.org/abs/2503.10706
作者: Pierre Sermanet,Anirudha Majumdar,Vikas Sindhwani
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC); Robotics (cs.RO)
备注:

点击查看摘要

[NLP-63] Harmonizing Large Language Models with Collaborative Behavioral Signals for Conversational Recommendation

链接: https://arxiv.org/abs/2503.10703
作者: Guanrong Li,Kuo Tian,Jinnan Qi,Qinghan Fu,Zhen Wu,Xinyu Dai
机构: 未知
类目: Computation and Language (cs.CL); Information Retrieval (cs.IR)
备注:

点击查看摘要

[NLP-64] ClaimTrust: Propagation Trust Scoring for RAG Systems

链接: https://arxiv.org/abs/2503.10702
作者: Hangkai Qian,Bo Li,Qichen Wang
机构: 未知
类目: Computation and Language (cs.CL); Information Retrieval (cs.IR)
备注: 6 pages, 2 figures, 1 table

点击查看摘要

[NLP-65] Ordered Semantically Diverse Sampling for Textual Data

链接: https://arxiv.org/abs/2503.10698
作者: Ashish Tiwari,Mukul Singh,Ananya Singha,Arjun Radhakrishna
机构: 未知
类目: Computation and Language (cs.CL); Information Retrieval (cs.IR)
备注:

点击查看摘要

[NLP-66] Introducing Verification Task of Set Consistency with Set-Consistency Energy Networks

链接: https://arxiv.org/abs/2503.10695
作者: Mooho Song,Jay-Yoon Lee
机构: Seoul National University (首尔国立大学)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-67] Medical Large Language Model Benchmarks Should Prioritize Construct Validity

链接: https://arxiv.org/abs/2503.10694
作者: Ahmed Alaa,Thomas Hartvigsen,Niloufar Golchini,Shiladitya Dutta,Frances Dean,Inioluwa Deborah Raji,Travis Zack
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-68] Battling Misinformation: An Empirical Study on Adversarial Factuality in Open-Source Large Language Models

链接: https://arxiv.org/abs/2503.10690
作者: Shahnewaz Karim Sakib,Anindya Bijoy Das,Shibbir Ahmed
机构: University of Tennessee at Chattanooga (田纳西大学查塔努加校区); The University of Akron (阿克伦大学); Texas State University (德克萨斯州立大学)
类目: Computation and Language (cs.CL); Cryptography and Security (cs.CR)
备注:

点击查看摘要

[NLP-69] Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents ICLR2025

链接: https://arxiv.org/abs/2503.10689
作者: Dongjun Lee,Juyong Lee,Kyuyoung Kim,Jihoon Tack,Jinwoo Shin,Yee Whye Teh,Kimin Lee
机构: 未知
类目: Computation and Language (cs.CL)
备注: Accepted to ICLR 2025

点击查看摘要

[NLP-70] CULEMO: Cultural Lenses on Emotion – Benchmarking LLM s for Cross-Cultural Emotion Understanding

链接: https://arxiv.org/abs/2503.10688
作者: Tadesse Destaw Belay,Ahmed Haj Ahmed,Alvin Grissom II,Iqra Ameer,Grigori Sidorov,Olga Kolesnikova,Seid Muhie Yimam
机构: Instituto Politécnico Nacional (墨西哥国家理工学院); Haverford College (哈弗福德学院); Wollo University (沃尔洛大学); Pennsylvania State University (宾夕法尼亚州立大学); University of Hamburg (汉堡大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-71] Understanding the Quality-Diversity Trade-off in Diffusion Language Models

链接: https://arxiv.org/abs/2503.10683
作者: Zak Buzzard
机构: University of Cambridge (剑桥大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 11 pages, 8 figures

点击查看摘要

[NLP-72] End-to-end Learning of Sparse Interventions on Activations to Steer Generation

链接: https://arxiv.org/abs/2503.10679
作者: Pau Rodriguez,Michal Klein,Eleonora Gualdoni,Arno Blaas,Luca Zappella,Marco Cuturi,Xavier Suau
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-73] A Survey on Knowledge-Oriented Retrieval-Augmented Generation

链接: https://arxiv.org/abs/2503.10677
作者: Mingyue Cheng,Yucong Luo,Jie Ouyang,Qi Liu,Huijie Liu,Li Li,Shuo Yu,Bohou Zhang,Jiawei Cao,Jie Ma,Daoyu Wang
机构: State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China (中国科学技术大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-74] Fine-Tuning LLM s for Report Summarization: Analysis on Supervised and Unsupervised Data

链接: https://arxiv.org/abs/2503.10676
作者: Swati Rallapalli,Shannon Gallagher,Andrew O. Mellinger,Jasmine Ratchford,Anusha Sinha,Tyler Brooks,William R. Nichols,Nick Winski,Bryan Brown
机构: Software Engineering Institute, Carnegie Mellon University (卡内基梅隆大学软件工程学院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-75] Beyond One-Size-Fits-All Summarization: Customizing Summaries for Diverse Users

链接: https://arxiv.org/abs/2503.10675
作者: Mehmet Samet Duran,Tevfik Aytekin
机构: Faculty of Engineering and Natural Sciences, Bahcesehir University (巴拉杰希尔大学工程与自然科学学院); Department of Computer Engineering, Bahcesehir University (巴拉杰希尔大学计算机工程系)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: This work has been submitted to the IEEE for possible publication

点击查看摘要

[NLP-76] Enhancing Retrieval for ESGLLM via ESG-CID – A Disclosure Content Index Finetuning Dataset for Mapping GRI and ESRS

链接: https://arxiv.org/abs/2503.10674
作者: Shafiuddin Rehan Ahmed,Ankit Parag Shah,Quan Hung Tran,Vivek Khetan,Sukryool Kang,Ankit Mehta,Yujia Bao,Wei Wei
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Long paper

点击查看摘要

[NLP-77] ZeroSumEval: An Extensible Framework For Scaling LLM Evaluation with Inter-Model Competition

链接: https://arxiv.org/abs/2503.10673
作者: Hisham A. Alyahya,Haidar Khan,Yazeed Alnumay,M Saiful Bari,Bülent Yener
机构: Saudi Data & AI Authority (SDAIA)(沙特数据与人工智能管理局); Meta(元宇宙平台公司); Cohere(未知中文); Rensselaer Polytechnic Institute (伦斯勒理工学院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-78] Identifying Non-Replicable Social Science Studies with Language Models

链接: https://arxiv.org/abs/2503.10671
作者: Denitsa Saynova,Kajsa Hansson,Bastiaan Bruinsma,Annika Fredén,Moa Johansson
机构: Chalmers University of Technology (查尔姆斯理工大学); University of Gothenburg (哥德堡大学); Lund University (隆德大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-79] UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality

链接: https://arxiv.org/abs/2503.10669
作者: Zelei Cheng,Xin-Qiang Cai,Yuting Tang,Pushi Zhang,Boming Yang,Xinyu Xing
机构: Northwestern University (西北大学); RIKEN-AIP (理化学研究所人工智能研究中心); The University of Tokyo (东京大学); Microsoft Research Asia (微软亚洲研究院); Northwestern University (西北大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Language Modeling, Machine Learning for NLP

点击查看摘要

[NLP-80] Identity Lock: Locking API Fine-tuned LLM s With Identity-based Wake Words

链接: https://arxiv.org/abs/2503.10668
作者: Hongyu Su,Yifeng Gao,Yifan Ding,Xingjun Ma
机构: Shanghai Key Lab of Intell. Info. Processing (上海智能信息处理重点实验室), School of CS (计算机科学学院), Fudan University (复旦大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-81] Green Prompting

链接: https://arxiv.org/abs/2503.10666
作者: Marta Adamska,Daria Smirnova,Hamid Nasiri,Zhengxin Yu,Peter Garraghan
机构: School of Computing and Communications, Lancaster University (计算与通讯学院，兰卡斯特大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 9 pages, 5 figures

点击查看摘要

[NLP-82] Small Vision-Language Models: A Survey on Compact Architectures and Techniques

链接: https://arxiv.org/abs/2503.10665
作者: Nitesh Patnaik,Navdeep Nayak,Himani Bansal Agrawal,Moinak Chinmoy Khamaru,Gourav Bal,Saishree Smaranika Panda,Rishi Raj,Vishal Meena,Kartheek Vadlamani
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)
备注:

点击查看摘要

[NLP-83] Semantic Wave Functions: Exploring Meaning in Large Language Models Through Quantum Formalism

链接: https://arxiv.org/abs/2503.10664
作者: Timo Aukusti Laine
机构: 未知
类目: Computation and Language (cs.CL); Machine Learning (cs.LG); Quantum Physics (quant-ph)
备注: 29 pages, 4 figures

点击查看摘要

[NLP-84] Evaluation of the Automated Labeling Method for Taxonomic Nomenclature Through Prompt-Optimized Large Language Model

链接: https://arxiv.org/abs/2503.10662
作者: Keito Inoshita,Kota Nojiri,Haruto Sugeno,Takumi Taga
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: This paper will be submitted to IEEE IAICT

点击查看摘要

[NLP-85] MARRO: Multi-headed Attention for Rhetorical Role Labeling in Legal Documents

链接: https://arxiv.org/abs/2503.10659
作者: Purbid Bambroo,Subinay Adhikary,Paheli Bhattacharya,Abhijnan Chakraborty,Saptarshi Ghosh,Kripabandhu Ghosh
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-86] LimTopic: LLM -based Topic Modeling and Text Summarization for Analyzing Scientific Articles limitations

链接: https://arxiv.org/abs/2503.10658
作者: Ibrahim Al Azhar,Venkata Devesh Reddy,Hamed Alhoori,Akhil Pandey Akella
机构: Northern Illinois University (北方伊利诺伊大学); Northwestern University (西北大学)
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: 12 pages, accepted at JCDL 2024 (The ACM/IEEE Joint Conference on Digital Libraries). This is a preprint version; the final version will be published in the ACM Digital Library

点击查看摘要

[NLP-87] RouterEval: A Comprehensive Benchmark for Routing LLM s to Explore Model-level Scaling Up in LLM s

链接: https://arxiv.org/abs/2503.10657
作者: Zhongzhan Huang,Guoming Ling,Vincent S. Liang,Yupei Lin,Yandong Chen,Shanshan Zhong,Hefeng Wu,Liang Lin
机构: Sun Yat-sen University (中山大学); Purdue University (普渡大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Preprint

点击查看摘要

[NLP-88] Language modelling techniques for analysing the impact of human genetic variation

链接: https://arxiv.org/abs/2503.10655
作者: Megha Hegde,Jean-Christophe Nebel,Farzana Rahman
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Biomolecules (q-bio.BM)
备注:

点击查看摘要

[NLP-89] Improving RAG Retrieval via Propositional Content Extraction: a Speech Act Theory Approach

链接: https://arxiv.org/abs/2503.10654
作者: João Alberto de Oliveira Lima
机构: University of Brasília (巴西利亚大学); Federal Senate of Brazil (巴西参议院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
备注: 19 pages, 4 figures

点击查看摘要

[NLP-90] Evaluating Local and Cloud-Based Large Language Models for Simulating Consumer Choices in Energy Stated Preference Surveys

链接: https://arxiv.org/abs/2503.10652
作者: Han Wang,Jacek Pawlak,Aruna Sivakumar
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-91] AI Enabled User-Specific Cyberbullying Severity Detection with Explainability

链接: https://arxiv.org/abs/2503.10650
作者: Tabia Tanzin Prama,Jannatul Ferdaws Amrin,Md. Mushfique Anwar,Iqbal H. Sarker
机构: 未知
类目: Machine Learning (cs.LG); Computation and Language (cs.CL); Computers and Society (cs.CY)
备注:

点击查看摘要

[NLP-92] Measuring Political Preferences in AI Systems: An Integrative Approach

链接: https://arxiv.org/abs/2503.10649
作者: David Rozado
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Measuring Political Preferences in AI Systems. Report. Available: this https URL

点击查看摘要

[NLP-93] Hate Speech and Sentiment of YouTube Video Comments From Public and Private Sources Covering the Israel-Palestine Conflict

链接: https://arxiv.org/abs/2503.10648
作者: Simon Hofmann,Christoph Sommermann,Mathias Kraus,Patrick Zschech,Julian Rosenberger
机构: 未知
类目: Computation and Language (cs.CL); Computers and Society (cs.CY); Machine Learning (cs.LG); Social and Information Networks (cs.SI)
备注: Presented at the 19th International Conference on Wirtschaftsinformatik (WI 2024). Available here: this https URL

点击查看摘要

[NLP-94] he Reliability of LLM s for Medical Diagnosis: An Examination of Consistency Manipulation and Contextual Awareness

链接: https://arxiv.org/abs/2503.10647
作者: Krishna Subedi
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC)
备注:

点击查看摘要

[NLP-95] Synthetic Categorical Restructuring large Or How AIs Gradually Extract Efficient Regularities from Their Experience of the World

链接: https://arxiv.org/abs/2503.10643
作者: Michael Pichat,William Pogrund,Paloma Pichat,Armanouche Gasparian,Samuel Demarchi,Martin Corbet,Alois Georgeon,Theo Dasilva,Michael Veillet-Guillem
机构: 未知
类目: Computation and Language (cs.CL); Neural and Evolutionary Computing (cs.NE); Neurons and Cognition (q-bio.NC)
备注:

点击查看摘要

[NLP-96] xt2Zinc: A Cross-Domain Dataset for Modeling Optimization and Satisfaction Problems in MiniZinc

链接: https://arxiv.org/abs/2503.10642
作者: Akash Singirikonda,Serdar Kadioglu,Karthik Uppuluri
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-97] Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

链接: https://arxiv.org/abs/2503.03601
作者: Kristian Kuznetsov,Laida Kushnareva,Polina Druzhinina,Anton Razzhigaev,Anastasia Voznyuk,Irina Piontkovskaya,Evgeny Burnaev,Serguei Barannikov
机构: 未知
类目: Computation and Language (cs.CL); Information Theory (cs.IT)
备注:

点击查看摘要

[NLP-98] Quantifying Logical Consistency in Transformers via Query-Key Alignment

链接: https://arxiv.org/abs/2502.17017
作者: Eduard Tulchinskii,Anastasia Voznyuk,Laida Kushnareva,Andrei Andriiainen,Irina Piontkovskaya,Evgeny Burnaev,Serguei Barannikov
机构: Skolkovo Institute of Science and Technology (斯科尔科沃科学技术研究院); AI Foundation and Algorithm Lab (AI基金会和算法实验室); Moscow Institute of Physics and Technology (莫斯科物理技术学院); CNRS, Université Paris Cité, France (法国国家科学研究中心, 巴黎城市大学); Artificial Intelligence Research Institute (AIRI) (人工智能研究所)
类目: Computation and Language (cs.CL); Information Theory (cs.IT); Machine Learning (cs.LG); Logic (math.LO)
备注:

点击查看摘要

[NLP-99] Robust AI-Generated Text Detection by Restricted Embeddings EMNLP2024

链接: https://arxiv.org/abs/2410.08113
作者: Kristian Kuznetsov,Eduard Tulchinskii,Laida Kushnareva,German Magai,Serguei Barannikov,Sergey Nikolenko,Irina Piontkovskaya
机构: AI Foundation and Algorithm Lab (俄罗斯); HSE University (俄罗斯); Noeon Research (日本); Skolkovo Institute of Science and Technology (俄罗斯); CNRS, Université Paris Cité (法国); ISP RAS Research Center for Trusted Artificial Intelligence, Moscow (俄罗斯); St. Petersburg Department of the Steklov Institute of Mathematics (俄罗斯)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Theory (cs.IT)
备注: Accepted to Findings of EMNLP 2024

点击查看摘要

[NLP-100] Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts

链接: https://arxiv.org/abs/2306.04723
作者: Eduard Tulchinskii,Kristian Kuznetsov,Laida Kushnareva,Daniil Cherniavskii,Serguei Barannikov,Irina Piontkovskaya,Sergey Nikolenko,Evgeny Burnaev
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Theory (cs.IT); Machine Learning (cs.LG); Algebraic Topology (math.AT)
备注:

点击查看摘要

计算机视觉

[CV-0] Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation

链接: https://arxiv.org/abs/2503.11652
作者: Hiroyasu Akada,Jian Wang,Vladislav Golyanik,Christian Theobalt
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-1] VGGT: Visual Geometry Grounded Transformer CVPR2025

链接: https://arxiv.org/abs/2503.11651
作者: Jianyuan Wang,Minghao Chen,Nikita Karaev,Andrea Vedaldi,Christian Rupprecht,David Novotny
机构: Visual Geometry Group, University of Oxford (牛津大学视觉几何组); Meta AI (Meta 人工智能实验室)
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-2] Centaur: Robust End-to-End Autonomous Driving with Test-Time Training

链接: https://arxiv.org/abs/2503.11650
作者: Chonghao Sima,Kashyap Chitta,Zhiding Yu,Shiyi Lan,Ping Luo,Andreas Geiger,Hongyang Li,Jose M. Alvarez
机构: The University of Hong Kong (香港大学); NVIDIA (英伟达); University of Tübingen (图宾根大学); Tübingen AI Center (图宾根人工智能中心)
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-3] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

链接: https://arxiv.org/abs/2503.11647
作者: Jianhong Bai,Menghan Xia,Xiao Fu,Xintao Wang,Lianrui Mu,Jinwen Cao,Zuozhu Liu,Haoji Hu,Xiang Bai,Pengfei Wan,Di Zhang
机构: Zhejiang University (浙江大学); Kuaishou Technology (快手科技); The Chinese University of Hong Kong (香港中文大学); Huazhong University of Science and Technology (华中科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-4] Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation

链接: https://arxiv.org/abs/2503.11633
作者: Hongyu Wen,Yiming Zuo,Venkat Subramanian,Patrick Chen,Jia Deng
机构: Department of Computer Science, Princeton University (计算机科学系, 普林斯顿大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-5] reeMeshGPT : Artistic Mesh Generation with Autoregressive Tree Sequencing CVPR2025

链接: https://arxiv.org/abs/2503.11629
作者: Stefan Lionar,Jiabin Liang,Gim Hee Lee
机构: Sea AI Lab; Garena; National University of Singapore (新加坡国立大学)
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注: CVPR 2025. Code: this https URL

点击查看摘要

[CV-6] Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages CVPR2025

链接: https://arxiv.org/abs/2503.11609
作者: Matteo Farina,Massimiliano Mancini,Giovanni Iacca,Elisa Ricci
机构: University of Trento (特伦托大学); Fondazione Bruno Kessler (布鲁诺·凯勒基金会)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Multimedia (cs.MM)
备注: Camera-ready version for CVPR 2025 (w/ SuppMat, 23 pages)

点击查看摘要

[CV-7] Advancing 3D Gaussian Splatting Editing with Complementary and Consensus Information

链接: https://arxiv.org/abs/2503.11601
作者: Xuanqi Zhang,Jieun Lee,Chris Joslin,Wonsook Lee
机构: University of Ottawa (渥太华大学); Hansung University (汉城大学); Carleton University (卡莱顿大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 7 pages, 9 figures

点击查看摘要

[CV-8] Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers

链接: https://arxiv.org/abs/2503.11579
作者: Weiming Ren,Wentao Ma,Huan Yang,Cong Wei,Ge Zhang,Wenhu Chen
机构: University of Waterloo (滑铁卢大学); University of Toronto (多伦多大学); 01.AI; Vector Institute (向量研究所); M-A-P
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project Page: this https URL

点击查看摘要

[CV-9] SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

链接: https://arxiv.org/abs/2503.11576
作者: Ahmed Nassar,Andres Marafioti,Matteo Omenetti,Maksym Lysak,Nikolaos Livathinos,Christoph Auer,Lucas Morin,Rafael Teixeira de Lima,Yusik Kim,A. Said Gurbuz,Michele Dolfi,Miquel Farré,Peter W. J. Staar
机构: IBM Research (IBM研究院); HuggingFace (HuggingFace)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 24 pages, 10 figures

点击查看摘要

[CV-10] RASA: Replace Anyone Say Anything – A Training-Free Framework for Audio-Driven and Universal Portrait Video Editing

链接: https://arxiv.org/abs/2503.11571
作者: Tianrui Pan,Lin Liu,Jie Liu,Xiaopeng Zhang,Jie Tang,Gangshan Wu,Qi Tian
机构: State Key Laboratory for Novel Software Technology, Nanjing University (南京大学国家重点实验室); Huawei Inc (华为)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Demo is available at this https URL

点击查看摘要

[CV-11] Disentangled Object-Centric Image Representation for Robotic Manipulation

链接: https://arxiv.org/abs/2503.11565
作者: David Emukpere,Romain Deffayet,Bingbing Wu,Romain Brégier,Michael Niemaz,Jean-Luc Meunier,Denys Proux,Jean-Michel Renders,Seungsu Kim
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-12] VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity

链接: https://arxiv.org/abs/2503.11557
作者: Jing Bi,Junjia Guo,Susan Liang,Guangyu Sun,Luchuan Song,Yunlong Tang,Jinxi He,Jiarui Wu,Ali Vosoughi,Chen Chen,Chenliang Xu
机构: University of Rochester (罗切斯特大学); University of Central Florida (中佛罗里达大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-13] Similarity-Aware Token Pruning: Your VLM but Faster

链接: https://arxiv.org/abs/2503.11549
作者: Ahmadreza Jeddi,Negin Baghbanzadeh,Elham Dolatabadi,Babak Taati
机构: University of Toronto (多伦多大学); Vector Institute (Vector研究所); York University, Canada (约克大学，加拿大); KITE Research Institute, UHN (KITE 研究所，UHN)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 15 pages, 8 figures, 8 tables

点击查看摘要

[CV-14] AugGen: Synthetic Augmentation Can Improve Discriminative Models

链接: https://arxiv.org/abs/2503.11544
作者: Parsa Rahimi,Damien Teney,Sebastien Marcel
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-15] FLASHμ: Fast Localizing And Sizing of Holographic Microparticles

链接: https://arxiv.org/abs/2503.11538
作者: Ayush Paliwal,Oliver Schlenczek,Birte Thiede,Manuel Santos Pereira,Katja Stieger,Eberhard Bodenschatz,Gholamhossein Bagheri,Alexander Ecker
机构: Max Planck Institute for Dynamics and Self-Organization (马克斯·普朗克动力学与自组织研究所, Germany); Institute of Computer Science and Campus Institute Data Science, University of Göttingen (哥廷根大学计算机科学研究所和校园数据科学研究所, Germany); Faculty of Physics, University of Göttingen (哥廷根大学物理系, Germany); Laboratory of Atomic and Solid State Physics, Cornell University (康奈尔大学原子和固态物理实验室, USA)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Atmospheric and Oceanic Physics (physics.ao-ph); Optics (physics.optics)
备注:

点击查看摘要

[CV-16] HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models

链接: https://arxiv.org/abs/2503.11513
作者: Ziqin Zhou,Yifan Yang,Yuqing Yang,Tianyu He,Houwen Peng,Kai Qiu,Qi Dai,Lili Qiu,Chong Luo,Lingqiao Liu
机构: The University of Adelaide (阿德莱德大学); Microsoft Research Asia (微软研究亚洲)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-17] Cloud2BIM: An open-source automatic pipeline for efficient conversion of large-scale point clouds into IFC format

链接: https://arxiv.org/abs/2503.11498
作者: Slávek Zbirovský,Václav Nežerka
机构: Faculty of Civil Engineering, Czech Technical University in Prague (捷克技术大学布拉格工学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Software Engineering (cs.SE)
备注: 42 pages, 18 figures

点击查看摘要

[CV-18] Cognitive Disentanglement for Referring Multi-Object Tracking

链接: https://arxiv.org/abs/2503.11496
作者: Shaofeng Liang,Runwei Guan,Wangwang Lian,Daizong Liu,Xiaolou Sun,Dongming Wu,Yutao Yue,Weiping Ding,Hui Xiong
机构: S.upc.edu.cn (中国石油大学（华东）); liverpool.ac.uk (利物浦大学); stu.pku.edu.cn (北京大学); seu.edu.cn (东南大学); ntu.edu.cn (南洋理工大学); ust.hk (香港科技大学); hkust-gz.edu.cn (香港科技大学广州校区); ust.hk (香港科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 24 pages, 9 figures

点击查看摘要

[CV-19] V-STaR: Benchmarking Video-LLM s on Video Spatio-Temporal Reasoning

链接: https://arxiv.org/abs/2503.11495
作者: Zixu Cheng,Jian Hu,Ziquan Liu,Chenyang Si,Wei Li,Shaogang Gong
机构: Institution1; Institution2
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: A benchmark for Video Spatio-Temporal Reasoning

点击查看摘要

[CV-20] 2I-FineEval: Fine-Grained Compositional Metric for Text-to-Image Evaluation ECCV2024

链接: https://arxiv.org/abs/2503.11481
作者: Seyed Mohammad Hadi Hosseini,Amir Mohammad Izadi,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)
备注: Accepted at ECCV 2024 Workshop EVAL-FoMo

点击查看摘要

[CV-21] Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios

链接: https://arxiv.org/abs/2503.11465
作者: Hang Shao,Lei Luo,Jianjun Qian,Mengkai Yan,Shuo Chen,Jian Yang
机构: PCA Lab, Nanjing University of Science and Technology (南理工); Nanjing University (南京大学); Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering (教育部高维信息智能感知重点实验室, 计算机科学与工程学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-22] COIN: Confidence Score-Guided Distillation for Annotation-Free Cell Segmentation

链接: https://arxiv.org/abs/2503.11439
作者: Sanghyun Jo,Seo Jin Lee,Seungwoo Lee,Seohyung Hong,Hyungseok Seo,Kyungsu Kim
机构: Unknown
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-23] ASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation

链接: https://arxiv.org/abs/2503.11423
作者: Hongxiang Zhao,Xingchen Liu,Mutian Xu,Yiming Hao,Weikai Chen,Xiaoguang Han
机构: SSE, CUHKSZ (南方科技大学); FNii, CUHKSZ (南方科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: Conference on Computer Vision and Pattern Recognition 2025

点击查看摘要

[CV-24] AQUA-SLAM: Tightly-Coupled Underwater Acoustic-Visual-Inertial SLAM with Sensor Calibration

链接: https://arxiv.org/abs/2503.11420
作者: Shida Xu,Kaicheng Zhang,Sen Wang
机构: Department of Electrical and Electronic Engineering & I-X, Imperial College London (帝国理工学院); School of Engineering and Physical Sciences, Heriot-Watt University (赫瑞-瓦特大学)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-25] MTV-Inpaint: Multi-Task Long Video Inpainting

链接: https://arxiv.org/abs/2503.11412
作者: Shiyuan Yang,Zheng Gu,Liang Hou,Xin Tao,Pengfei Wan,Xiaodong Chen,Jing Liao
机构: City University of Hong Kong (香港城市大学); Tianjin University (天津大学); Shenzhen University (深圳大学); Kuaishou Technology (快手科技); Xiaodong Chen (陈晓东) (天津大学); Jing Liao (廖静) (香港城市大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-26] LuSeg: Efficient Negative and Positive Obstacles Segmentation via Contrast-Driven Multi-Modal Feature Fusion on the Lunar

链接: https://arxiv.org/abs/2503.11409
作者: Shuaifeng Jiao,Zhiwen Zeng,Zhuoqun Su,Xieyuanli Chen,Zongtan Zhou,Huimin Lu
机构: College of Intelligence Science and Technology, National University of Defense Technology (国防科技大学智能科学与技术学院); National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology (国防科技大学装备状态感知与智能支持国家重点实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-27] owards A Correct Usage of Cryptography in Semantic Watermarks for Diffusion Models ICLR

链接: https://arxiv.org/abs/2503.11404
作者: Jonas Thietke,Andreas Müller,Denis Lukovnikov,Asja Fischer,Erwin Quiring
机构: Ruhr University Bochum (鲁尔大学波鸿)
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 3 figures, WMark@ICLR

点击查看摘要

[CV-28] A Framework for a Capability-driven Evaluation of Scenario Understanding for Multimodal Large Language Models in Autonomous Driving

链接: https://arxiv.org/abs/2503.11400
作者: Tin Stribor Sohn,Philipp Reis,Maximilian Dillitzer,Johannes Bach,Jason J. Corso,Eric Sax
机构: Dr. Ing. h.c. F. Porsche AG (保时捷股份有限公司); Forschungszentrum Informatik (信息技术研究中心); Hochschule Esslingen (埃斯林根应用技术大学); University of Michigan (密歇根大学); Voxel51; Karlsruher Institut für Technologie (卡尔斯鲁厄理工学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: Submitted to IEEE IAVVC 2025, Under Review

点击查看摘要

[CV-29] Watch and Learn: Leverag ing Expert Knowledge and Language for Surgical Video Understanding

链接: https://arxiv.org/abs/2503.11392
作者: David Gastager,Ghazal Ghazaei,Constantin Patsch
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 14 pages main manuscript with 3 figures; 6 pages supplementary material with 3 figures. To be presented at International Conference on Information Processing in Computer-Assisted Interventions (IPCAI 2025). To be published in International Journal of Computer Assisted Radiology and Surgery (IJCARS)

点击查看摘要

[CV-30] Deepfake Detection of Face Images based on a Convolutional Neural Network

链接: https://arxiv.org/abs/2503.11389
作者: Lukas Kroiß,Johannes Reschke
机构: Ostbayerische Technische Hochschule Regensburg (奥斯特拜罗伊特应用技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-31] BEVDiffLoc: End-to-End LiDAR Global Localization in BEV View based on Diffusion Model

链接: https://arxiv.org/abs/2503.11372
作者: Ziyue Wang,Chenghao Shi,Neng Wang,Qinghua Yu,Xieyuanli Chen,Huimin Lu
机构: College of Intelligence Science and Technology, National University of Defense Technology, China (智能科学与技术学院, 国防科技大学, 中国); National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology, China (装备状态感知与智能支持国家级重点实验室, 国防科技大学, 中国)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-32] EMoTive: Event-guided Trajectory Modeling for 3D Motion Estimation

链接: https://arxiv.org/abs/2503.11371
作者: Zengyu Wan,Wei Zhai,Yang Cao,Zhengjun Zha
机构: USTC (University of Science and Technology of China)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-33] PBR3DGen: A VLM-guided Mesh Generation with High-quality PBR Texture

链接: https://arxiv.org/abs/2503.11368
作者: Xiaokang Wei,Bowen Zhang,Xianghui Yang,Yuxuan Wang,Chunchao Guo,Xi Zhao,Yan Luximon
机构: The Hong Kong Polytechnic University (香港理工大学); Xi’an Jiaotong University (西安交通大学); Nanyang Technological University (南洋理工大学); Tencent Hunyuan (腾讯浑元)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Homepage: this https URL

点击查看摘要

[CV-34] PARIC: Probabilistic Attention Regularization for Language Guided Image Classification from Pre-trained Vison Language Models

链接: https://arxiv.org/abs/2503.11360
作者: Mayank Nautiyal,Stela Arranz Gheorghe,Kristiana Stefa,Li Ju,Ida-Maria Sintorn,Prashant Singh
机构: Department of Information Technology, Uppsala University (乌普萨拉大学), Uppsala, Sweden; IT University of Copenhagen (哥本哈根信息技术大学), Copenhagen, Denmark; Science for Life Laboratory (SciLifeLab), Uppsala University (乌普萨拉大学), Uppsala, Sweden
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-35] Enhancing Hand Palm Motion Gesture Recognition by Eliminating Reference Frame Bias via Frame-Invariant Similarity Measures

链接: https://arxiv.org/abs/2503.11352
作者: Arno Verduyn,Maxim Vochten,Joris De Schutter
机构: Department of Mechanical Engineering and Flanders Make at KU Leuven (KU Leuven 的机械工程系和 Flanders Make)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV); Human-Computer Interaction (cs.HC)
备注: 8 pages, 4 figures, this work has been submitted as a conference paper for consideration in the 2025 IEEE International Conference on Automation Science and Engineering (CASE), the content in this preprint is identical to the version submitted for peer review

点击查看摘要

[CV-36] EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splatting

链接: https://arxiv.org/abs/2503.11345
作者: Di Li,Jie Feng,Jiahao Chen,Weisheng Dong,Guanbin Li,Guangming Shi,Licheng Jiao
机构: Xidian University (西安电子科技大学); Sun Yat-sen University (中山大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-37] Road Rag e Reasoning with Vision-language Models (VLMs): Task Definition and Evaluation Dataset

链接: https://arxiv.org/abs/2503.11342
作者: Yibing Weng,Yu Gu,Fuji Ren
机构: School of Computer Science and Engineering, University of Electronic Science and Technology of China (电子科技大学)(Chengdu, China)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-38] Self-Supervised Pretraining for Fine-Grained Plankton Recognition

链接: https://arxiv.org/abs/2503.11341
作者: Joona Kareinen,Tuomas Eerola,Kaisa Kraft,Lasse Lensu,Sanna Suikkanen,Heikki Kälviäinen
机构: LUT University (拉普兰塔工业大学); Finnish Environment Institute (芬兰环境研究所)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-39] APLA: A Simple Adaptation Method for Vision Transformers

链接: https://arxiv.org/abs/2503.11335
作者: Moein Sorkhei,Emir Konuk,Kevin Smith,Christos Matsoukas
机构: KTH Royal Institute of Technology (皇家理工学院), Stockholm, Sweden; Science for Life Laboratory (SciLifeLab), Stockholm, Sweden
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-40] Cardiomyopathy Diagnosis Model from Endomyocardial Biopsy Specimens: Appropriate Feature Space and Class Boundary in Small Sample Size Data

链接: https://arxiv.org/abs/2503.11331
作者: Masaya Mori,Yuto Omae,Yutaka Koyama,Kazuyuki Hara,Jun Toyotani,Yasuo Okumura,Hiroyuki Hao
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-41] Colour Morphological Distance Ordering based on the Log-Exp-Supremum

链接: https://arxiv.org/abs/2503.11329
作者: Marvin Kahra,Michael Breuß
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 13 pages, 13 figures, submitted to SSVM 2025

点击查看摘要

[CV-42] ransiT: Transient Transformer for Non-line-of-sight Videography

链接: https://arxiv.org/abs/2503.11328
作者: Ruiqian Li,Siyuan Shen,Suan Xia,Ziheng Wang,Xingyue Peng,Chengxuan Song,Yingsheng Zhu,Tao Wu,Shiying Li,Jingyi Yu
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); Lingang Laboratory, Shanghai (临港实验室，上海); School of Physical Science and Technology, ShanghaiTech University (上海科技大学物理科学与技术学院); Shanghai Engineering Research Center of Intelligent Vision and Imaging (上海智能视觉与成像工程技术研究中心)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-43] Safe-VAR: Safe Visual Autoregressive Model for Text-to-Image Generative Watermarking

链接: https://arxiv.org/abs/2503.11324
作者: Ziyi Wang,Songbai Tan,Gang Xu,Xuerui Qiu,Hongbin Xu,Xin Meng,Ming Li,Fei Richard Yu
机构: Zhejiang University (浙江大学); Shenzhen University (深圳大学); South China University of Technology (华南理工大学); Institute of Automation, Chinese Academy of Sciences (中国科学院自动化研究所); Peking University (北京大学); Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) (广东人工智能与数字经济实验室 (深圳))
类目: Multimedia (cs.MM); Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-44] Leverag ing Diffusion Knowledge for Generative Image Compression with Fractal Frequency-Aware Band Learning

链接: https://arxiv.org/abs/2503.11321
作者: Lingyu Zhu,Xiangrui Zeng,Bolin Chen,Peilin Chen,Yung-Hui Li,Shiqi Wang
机构: City University of Hong Kong (香港城市大学); Hon Hai Research Institute (鸿海研究院)
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-45] Open-Set Plankton Recognition ECCV2024

链接: https://arxiv.org/abs/2503.11318
作者: Joona Kareinen,Annaliina Skyttä,Tuomas Eerola,Kaisa Kraft,Lasse Lensu,Sanna Suikkanen,Maiju Lehtiniemi,Heikki Kälviäinen
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: ECCV 2024, OOD-CV workshop paper

点击查看摘要

[CV-46] MMS-LLaMA: Efficient LLM -based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens

链接: https://arxiv.org/abs/2503.11315
作者: Jeong Hun Yeo,Hyeongseop Rha,Se Jin Park,Yong Man Ro
机构: Integrated Vision and Language Lab (综合视觉与语言实验室), KAIST (韩国科学技术院), South Korea (韩国)
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM); Sound (cs.SD); Audio and Speech Processing (eess.AS)
备注: The code and models are available this https URL

点击查看摘要

[CV-47] GMG: A Video Prediction Method Based on Global Focus and Motion Guided

链接: https://arxiv.org/abs/2503.11297
作者: Yuhao Du,Hui Liu,Haoxiang Peng,Xinyuan Chen,Chenrong Wu,Jiankai Zhang
机构: College of Atmospheric Sciences, Lanzhou University (兰州大学); College of Computer and Mathematics, Central South University of Forestry and Technology (中南林业科技大学); Center for Language and Information Processing, University of Munich (LMU) (慕尼黑大学); Department of Computer Science, University of Manchester (曼彻斯特大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-48] EmoAgent : Multi-Agent Collaboration of Plan Edit and Critic for Affective Image Manipulation

链接: https://arxiv.org/abs/2503.11290
作者: Qi Mao,Haobo Hu,Yujie He,Difei Gao,Haokun Chen,Libiao Jin
机构: MIPG, Communication University of China (传媒大学媒体物理与智能传播院); Show Lab, National University of Singapore (新加坡国立大学展示实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-49] Prof. Robot: Differentiable Robot Rendering Without Static and Self-Collisions

链接: https://arxiv.org/abs/2503.11269
作者: Quanyuan Ruan,Jiabao Lei,Wenhao Yuan,Yanglin Zhang,Dekun Lu,Guiliang Liu,Kui Jia
机构: South China University of Technology (华南理工大学); School of Data Science, The Chinese University of Hong Kong, Shenzhen (香港中文大学（深圳）数据科学学院)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-50] CyclePose – Leverag ing Cycle-Consistency for Annotation-Free Nuclei Segmentation in Fluorescence Microscopy MICCAI2025

链接: https://arxiv.org/abs/2503.11266
作者: Jonas Utz,Stefan Vocht,Anne Tjorven Buessen,Dennis Possart,Fabian Wagner,Mareike Thies,Mingxuan Gu,Stefan Uderhardt,Katharina Breininger
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: under review for MICCAI 2025

点击查看摘要

[CV-51] DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Models

链接: https://arxiv.org/abs/2503.11265
作者: Xirui Zhou,Lianlei Shan,Xiaolin Gui
机构: Xi’an Jiaotong University (西安交通大学); University of Chinese Academy of Sciences (中国科学院大学); 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-52] Noise Synthesis for Low-Light Image Denoising with Diffusion Models

链接: https://arxiv.org/abs/2503.11262
作者: Liying Lu,Raphaël Achddou,Sabine Süsstrunk
机构: IVRL (Image and Visual Representation Lab), EPFL
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-53] Breaking Shallow Limits: Task-Driven Pixel Fusion for Gap-free RGBT Tracking

链接: https://arxiv.org/abs/2503.11247
作者: Andong Lu,Yuanzhi Guo,Wanyu Wang,Chenglong Li,Jin Tang,Bin Luo
机构: School of Computer Science and Technology, Anhui University (安徽大学计算机科学与技术学院); School of Artificial Intelligence, Anhui University (安徽大学人工智能学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: In peer review

点击查看摘要

[CV-54] L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery

链接: https://arxiv.org/abs/2503.11245
作者: Ziwei Shi,Xiaoran Zhang,Yan Xia,Yu Zang,Siqi Shen,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; Technical University of Munich (慕尼黑工业大学), Germany; Munich Center for Machine Learning (慕尼黑机器学习中心), Germany
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-55] Compound Expression Recognition via Large Vision-Language Models

链接: https://arxiv.org/abs/2503.11241
作者: Jun Yu,Xilong Lu
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); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-56] owards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards CVPR2025

链接: https://arxiv.org/abs/2503.11240
作者: Zijing Hu,Fengda Zhang,Long Chen,Kun Kuang,Jiahui Li,Kaifeng Gao,Jun Xiao,Xin Wang,Wenwu Zhu
机构: Zhejiang University (浙江大学); Nanyang Technological University (南洋理工大学); The Hong Kong University of Science and Technology (香港科技大学); Tsinghua University (清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Accepted to CVPR 2025

点击查看摘要

[CV-57] Non Line-of-Sight Optical Wireless Communication using Neuromorphic Cameras

链接: https://arxiv.org/abs/2503.11226
作者: Abbaas Alif Mohamed Nishar,Alireza Marefat,Ashwin Ashok
机构: Georgia State University (乔治亚州立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Emerging Technologies (cs.ET); Information Theory (cs.IT); Networking and Internet Architecture (cs.NI)
备注: Accepted to be Presented at THE 22ND INTERNATIONAL CONFERENCE ON EMBEDDED WIRELESS SYSTEMS AND NETWORKS

点击查看摘要

[CV-58] oward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption CVPR2025

链接: https://arxiv.org/abs/2503.11221
作者: Du Chen,Tianhe Wu,Kede Ma,Lei Zhang
机构: The Hong Kong Polytechnic University (香港理工大学); City University of Hong Kong (香港城市大学); OPPO Research Institute (OPPO 研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025

点击查看摘要

[CV-59] MEET: A Million-Scale Dataset for Fine-Grained Geospatial Scene Classification with Zoom-Free Remote Sensing Imagery

链接: https://arxiv.org/abs/2503.11219
作者: Yansheng Li,Yuning Wu,Gong Cheng,Chao Tao,Bo Dang,Yu Wang,Jiahao Zhang,Chuge Zhang,Yiting Liu,Xu Tang,Jiayi Ma,Yongjun Zhang
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-60] owards General Multimodal Visual Tracking

链接: https://arxiv.org/abs/2503.11218
作者: Andong Lu,Mai Wen,Jinhu Wang,Yuanzhi Guo,Chenglong Li,Jin Tang,Bin Luo
机构: School of Computer Science and Technology, Anhui University (安徽大学计算机科学与技术学院); School of Artificial Intelligence, Anhui University (安徽大学人工智能学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: In peer review

点击查看摘要

[CV-61] Simulating Dual-Pixel Images From Ray Tracing For Depth Estimation

链接: https://arxiv.org/abs/2503.11213
作者: Fengchen He,Dayang Zhao,Hao Xu,Tingwei Quan,Shaoqun Zeng
机构: School of Optical and Electronic Information, Huazhong University of Science and Technology (华中科技大学光电信息学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-62] LLaVA-MLB: Mitigating and Leverag ing Attention Bias for Training-Free Video LLM s

链接: https://arxiv.org/abs/2503.11205
作者: Leqi Shen,Tao He,Guoqiang Gong,Fan Yang,Yifeng Zhang,Pengzhang Liu,Sicheng Zhao,Guiguang Ding
机构: School of Software, Tsinghua University (清华大学软件学院); BNRist, Tsinghua University (清华大学智能技术与系统国家重点实验室); JD.com (京东); GRG Banking Equipment Co., Ltd. (广电银通金融电子科技有限公司); South China University of Technology (华南理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-63] NF-SLAM: Effective Normalizing Flow-supported Neural Field representations for object-level visual SLAM in automotive applications IROS2024

链接: https://arxiv.org/abs/2503.11199
作者: Li Cui,Yang Ding,Richard Hartley,Zirui Xie,Laurent Kneip,Zhenghua Yu
机构: Motovis Intelligent Technologies (Motovis 智能科技); Australian National University (澳大利亚国立大学); ShanghaiTech University (上海科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages, 5 figures, IROS 2024

点击查看摘要

[CV-64] Provenance Detection for AI-Generated Images: Combining Perceptual Hashing Homomorphic Encryption and AI Detection Models

链接: https://arxiv.org/abs/2503.11195
作者: Shree Singhi,Aayan Yadav,Aayush Gupta,Shariar Ebrahimi,Parisa Hassanizadeh
机构: Zellic(泽利克); MIT, ZK Email(麻省理工学院, ZK 邮箱); Newcastle University(纽卡斯尔大学); Polish Academy of Science(波兰科学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-65] Online Test-time Adaptation for 3D Human Pose Estimation: A Practical Perspective with Estimated 2D Poses

链接: https://arxiv.org/abs/2503.11194
作者: Qiuxia Lin,Kerui Gu,Linlin Yang,Angela Yao
机构: Department of Computer Science, National University of Singapore (新加坡国立大学); State Key Laboratory of Media Convergence and Communication, CUC (媒体融合与传播国家重点实验室（中国传媒大学）); School of Information and Communication Engineering, CUC (中国传媒大学信息与通信工程学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-66] FastVID: Dynamic Density Pruning for Fast Video Large Language Models

链接: https://arxiv.org/abs/2503.11187
作者: Leqi Shen,Guoqiang Gong,Tao He,Yifeng Zhang,Pengzhang Liu,Sicheng Zhao,Guiguang Ding
机构: School of Software, Tsinghua University (清华大学软件学院); BNRist, Tsinghua University (清华大学智能技术与系统国家重点实验室); JD.com; GRG Banking Equipment Co., Ltd. (广电银通金融电子科技有限公司); South China University of Technology (华南理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-67] Multimodal-Aware Fusion Network for Referring Remote Sensing Image Segmentation

链接: https://arxiv.org/abs/2503.11183
作者: Leideng Shi,Juan Zhang
机构: School of Electronic and Electrical Engineering, Shanghai University of Engineering Science (上海工程技术大学电子电气工程学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 5 pages, 5 figures, accepted in IEEE Geoscience and Remote Sensing Letters (GRSL)

点击查看摘要

[CV-68] Multi-Stage Generative Upscaler: Reconstructing Football Broadcast Images via Diffusion Models

链接: https://arxiv.org/abs/2503.11181
作者: Luca Martini,Daniele Zolezzi,Saverio Iacono,Gianni Viardo Vercelli
机构: University of Genoa (Università degli Studi di Genova)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-69] Zero-TIG: Temporal Consistency-Aware Zero-Shot Illumination-Guided Low-light Video Enhancement

链接: https://arxiv.org/abs/2503.11175
作者: Yini Li,Nantheera Anantrasirichai
机构: Visual Information Laboratory, University of Bristol (视觉信息实验室, 布里斯托大学); Visual Information Laboratory, University of Bristol (视觉信息实验室, 布里斯托大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-70] Uncertainty-Aware Normal-Guided Gaussian Splatting for Surface Reconstruction from Sparse Image Sequences

链接: https://arxiv.org/abs/2503.11172
作者: Zhen Tan,Xieyuanli Chen,Jinpu Zhang,Lei Feng,Dewen Hu
机构: National University of Defense Technology (国防科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 12 pages, 8 figures

点击查看摘要

[CV-71] Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction

链接: https://arxiv.org/abs/2503.11167
作者: Haonan Wang,Qixiang Zhang,Lehan Wang,Xuanqi Huang,Xiaomeng Li
机构: The Hong Kong University of Science and Technology (香港科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-72] A Benchmarking Study of Vision-based Robotic Grasping Algorithms

链接: https://arxiv.org/abs/2503.11163
作者: Bharath K Rameshbabu,Sumukh S Balakrishna,Brian Flynn,Vinarak Kapoor,Adam Norton,Holly Yanco,Berk Calli
机构: Worcester Polytechnic Institute (伍斯特理工学院); University of Massachusetts Lowell (马萨诸塞大学洛厄尔分校)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注: Submitted to The IEEE Robotics and Automation Magazine

点击查看摘要

[CV-73] Stabilizing Quantization-Aware Training by Implicit-Regularization on Hessian Matrix

链接: https://arxiv.org/abs/2503.11159
作者: Junbiao Pang,Tianyang Cai
机构: Beijing University Of Technology (北京工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages, 5 figures

点击查看摘要

[CV-74] GaussianIP: Identity-Preserving Realistic 3D Human Generation via Human-Centric Diffusion Prior CVPR2025

链接: https://arxiv.org/abs/2503.11143
作者: Zichen Tang,Yuan Yao,Miaomiao Cui,Liefeng Bo,Hongyu Yang
机构: School of Artificial Intelligence, Beihang University (北航人工智能学院), Beijing, China; Shanghai Artificial Intelligence Laboratory (上海人工智能实验室), Shanghai, China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025

点击查看摘要

[CV-75] Minding Fuzzy Regions: A Data-driven Alternating Learning Paradigm for Stable Lesion Segmentation CVPR2025

链接: https://arxiv.org/abs/2503.11140
作者: Lexin Fang,Yunyang Xu,Xiang Ma,Xuemei Li,Caiming Zhang
机构: School of Software, Shandong University (山东大学软件学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 11 figures, accepted by CVPR 2025

点击查看摘要

[CV-76] SpaceSeg: A High-Precision Intelligent Perception Segmentation Method for Multi-Spacecraft On-Orbit Targets

链接: https://arxiv.org/abs/2503.11133
作者: Hao Liu,Pengyu Guo,Siyuan Yang,Zeqing Jiang,Qinglei Hu,Dongyu Li
机构: Hangzhou International Innovation Institute, Beihang University (北京航空航天大学); School of Cyber Science and Technology, Beihang University (北京航空航天大学); College of Computing and Data Science, Nanyang Technological University (南洋理工大学); Ant Group (蚂蚁集团); School of Automation Science and Electrical Engineering, Beihang University (北京航空航天大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-77] Direction-Aware Diagonal Autoregressive Image Generation

链接: https://arxiv.org/abs/2503.11129
作者: Yijia Xu,Jianzhong Ju,Jian Luan,Jinshi Cui
机构: School of Intelligence Science and Technology, Peking University (北京大学智能科学与技术学院); Xiaomi Inc. (小米公司)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-78] DriveGEN: Generalized and Robust 3D Detection in Driving via Controllable Text-to-Image Diffusion Generation CVPR2025

链接: https://arxiv.org/abs/2503.11122
作者: Hongbin Lin,Zilu Guo,Yifan Zhang,Shuaicheng Niu,Yafeng Li,Ruimao Zhang,Shuguang Cui,Zhen Li
机构: FNii-Shenzhen (FNii 深圳); SSE, CUHK-Shenzhen (香港中文大学深圳分校); National University of Singapore (新加坡国立大学); Nanyang Technological University (南洋理工大学); Baoji University of Arts and Sciences (宝鸡文理学院); Sun Yat-sen University (中山大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025

点击查看摘要

[CV-79] A Multi-Objective Evaluation Framework for Analyzing Utility-Fairness Trade-Offs in Machine Learning Systems

链接: https://arxiv.org/abs/2503.11120
作者: Gökhan Özbulak,Oscar Jimenez-del-Toro,Maíra Fatoretto,Lilian Berton,André Anjos
机构: École Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院); Idiap Research Institute (马蒂尼), Switzerland(瑞士); Federal University of São Paulo (UNIFESP)(圣保罗联邦大学), Brazil(巴西)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: 11 pages, 13 figures

点击查看摘要

[CV-80] Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering

链接: https://arxiv.org/abs/2503.11117
作者: Kaixuan Jiang,Yang Liu,Weixing Chen,Jingzhou Luo,Ziliang Chen,Ling Pan,Guanbin Li,Liang Lin
机构: Sun Yat-sen University (中山大学); Peng Cheng Laboratory (鹏城实验室); Hong Kong University of Science and Technology (香港科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-81] Solution for 8th Competition on Affective Behavior Analysis in-the-wild

链接: https://arxiv.org/abs/2503.11115
作者: Jun Yu,Yunxiang Zhang,Xilong Lu,Yang Zheng,Yongqi Wang,Lingsi Zhu
机构: University of Science and Technolog of China (中国科学技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-82] Quantifying Interpretability in CLIP Models with Concept Consistency

链接: https://arxiv.org/abs/2503.11103
作者: Avinash Madasu,Vasudev Lal,Phillip Howard
机构: Intel Labs (英特尔实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-83] A Survey on Self-supervised Contrastive Learning for Multimodal Text-Image Analysis

链接: https://arxiv.org/abs/2503.11101
作者: Asifullah Khan,Laiba Asmatullah,Anza Malik,Shahzaib Khan,Hamna Asif
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-84] A Novel Decomposed Feature-Oriented Framework for Open-Set Semantic Segmentation on LiDAR Data ICRA

链接: https://arxiv.org/abs/2503.11097
作者: Wenbang Deng,Xieyuanli Chen,Qinghua Yu,Yunze He,Junhao Xiao,Huimin Lu
机构: College of Intelligence Science and Technology, National University of Defense Technology, China (国防科技大学智能科学与技术学院, 中国); Hunan University (湖南大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: This paper has been accepted by 2025 ICRA

点击查看摘要

[CV-85] Augmenting Image Annotation: A Human-LMM Collaborative Framework for Efficient Object Selection and Label Generation ICLR2025

链接: https://arxiv.org/abs/2503.11096
作者: He Zhang,Xinyi Fu,John M. Carroll
机构: College of Information Sciences and Technology, Pennsylvania State University (宾夕法尼亚州立大学); The Future Laboratory, Tsinghua University (清华大学); College of Information Sciences and Technology, Pennsylvania State University (宾夕法尼亚州立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注: This paper will appear at ICLR 2025 Workshop on Bidirectional Human-AI Alignment

点击查看摘要

[CV-86] Open3DVQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space

链接: https://arxiv.org/abs/2503.11094
作者: Weichen Zhan,Zile Zhou,Zhiheng Zheng,Chen Gao,Jinqiang Cui,Yong Li,Xinlei Chen,Xiao-Ping Zhang
机构: Tsinghua University (清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-87] OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning

链接: https://arxiv.org/abs/2503.11093
作者: Yuan Liu,Saihui Hou,Saijie Hou,Jiabao Du,Shibei Meng,Yongzhen Huang
机构: School of Artificial Intelligence, Beijing Normal University (北京师范大学人工智能学院); School of Artificial Intelligence, Beijing University of Posts and Telecommunications (北京邮电大学人工智能学院); WATRIX.AI (华钛智行)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-88] Aerial Vision-and-Language Navigation with Grid-based View Selection and Map Construction

链接: https://arxiv.org/abs/2503.11091
作者: Ganlong Zhao,Guanbin Li,Jia Pan,Yizhou Yu
机构: The University of Hong Kong (香港大学); Sun Yat-sen University (中山大学); Guangdong Key Laboratory of Big Data Analysis and Processing (广东省大数据分析与处理重点实验室); Peng Cheng Laboratory (鹏城实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Under Submission

点击查看摘要

[CV-89] EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks

链接: https://arxiv.org/abs/2503.11089
作者: Yi Zhang,Qiang Zhang,Xiaozhu Ju,Zhaoyang Liu,Jilei Mao,Jingkai Sun,Jintao Wu,Shixiong Gao,Shihan Cai,Zhiyuan Qin,Linkai Liang,Jiaxu Wang,Yiqun Duan,Jiahang Cao,Renjing Xu,Jian Tang
机构: Beijing Innovation Center of Humanoid Robotics (北京仿人机器人创新中心); Hong Kong University of Science and Technology (Guangzhou) (香港科技大学（广州）); Hong Kong University of Science and Technology (香港科技大学); University of Technology Sydney (悉尼科技大学)
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: technical report

点击查看摘要

[CV-90] Multi-View Industrial Anomaly Detection with Epipolar Constrained Cross-View Fusion

链接: https://arxiv.org/abs/2503.11088
作者: Yifan Liu,Xun Xu,Shijie Li,Jingyi Liao,Xulei Yang
机构: Institute for Infocomm Research (I2R), A*STAR, Singapore; 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-91] MoMa-Kitchen: A 100K Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation

链接: https://arxiv.org/abs/2503.11081
作者: Pingrui Zhang,Xianqiang Gao,Yuhan Wu,Kehui Liu,Dong Wang,Zhigang Wang,Bin Zhao,Yan Ding,Xuelong Li
机构: Shanghai AI Laboratory (上海人工智能实验室); University of Science and Technology of China (中国科学技术大学); Northwestern Polytechnical University (西北工业大学); TeleAI, China Telecom Corp Ltd (中国电信研究院)
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-92] Understanding Flatness in Generative Models: Its Role and Benefits

链接: https://arxiv.org/abs/2503.11078
作者: Taehwan Lee,Kyeongkook Seo,Jaejun Yoo,Sung Whan Yoon
机构: Graduate School of Artificial Intelligence, Ulsan National Institute of Science and Technology (UNIST); Department of Electrical Engineering, Ulsan National Institute of Science and Technology (UNIST)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-93] Perceive Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models

链接: https://arxiv.org/abs/2503.11073
作者: Hongyang Wei,Shuaizheng Liu,Chun Yuan,Lei Zhang
机构: Tsinghua Shenzhen International Graduate School, Tsinghua University (清华大学深圳国际研究生院，清华大学); The Hong Kong Polytechnic University (香港理工大学); OPPO Research Institute (OPPO 研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-94] Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models CVPR2025

链接: https://arxiv.org/abs/2503.11071
作者: Zhenguang Liu,Chao Shuai,Shaojing Fan,Ziping Dong,Jinwu Hu,Zhongjie Ba,Kui Ren
机构: Zhejiang University (浙江大学); National University of Singapore (新加坡国立大学); South China University of Technology (华南理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Received by CVPR 2025 (10 pages, 11 figures)

点击查看摘要

[CV-95] Falcon: A Remote Sensing Vision-Language Foundation Model

链接: https://arxiv.org/abs/2503.11070
作者: Kelu Yao,Nuo Xu,Rong Yang,Yingying Xu,Zhuoyan Gao,Titinunt Kitrungrotsakul,Yi Ren,Pu Zhang,Jin Wang,Ning Wei,Chao Li
机构: Research Center for Space Computing System, ZhejiangLab (浙江实验室), Hangzhou, China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Under Review

点击查看摘要

[CV-96] Active Learning from Scene Embeddings for End-to-End Autonomous Driving

链接: https://arxiv.org/abs/2503.11062
作者: Wenhao Jiang,Duo Li,Menghan Hu,Chao Ma,Ke Wang,Zhipeng Zhang
机构: East China Normal University (华东师范大学); KargoBot (行深智能科技有限公司); Shanghai Jiao Tong University (上海交通大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages, 5 figures

点击查看摘要

[CV-97] BannerAg ency: Advertising Banner Design with Multimodal LLM Agents

链接: https://arxiv.org/abs/2503.11060
作者: Heng Wang,Yotaro Shimose,Shingo Takamatsu
机构: Sony Group Corporation (索尼集团公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-98] Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization

链接: https://arxiv.org/abs/2503.11056
作者: Kyle Sargent,Kyle Hsu,Justin Johnson,Li Fei-Fei,Jiajun Wu
机构: Stanford University (斯坦福大学); University of Michigan (密歇根大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 18 pages, 13 figures

点击查看摘要

[CV-99] LUSD: Localized Update Score Distillation for Text-Guided Image Editing

链接: https://arxiv.org/abs/2503.11054
作者: Worameth Chinchuthakun,Tossaporn Saengja,Nontawat Tritrong,Pitchaporn Rewatbowornwong,Pramook Khungurn,Supasorn Suwajanakorn
机构: 未知
类目: Graphics (cs.GR); 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-100] owards Privacy-preserved Pre-training of Remote Sensing Foundation Models with Federated Mutual-guidance Learning

链接: https://arxiv.org/abs/2503.11051
作者: Jieyi Tan,Chengwei Zhang,Bo Dang,Yansheng Li
机构: Wuhan University (武汉大学); University of Cambridge (剑桥大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 13 pages, 5 figures, 7 tables

点击查看摘要

[CV-101] PSF-4D: A Progressive Sampling Framework for View Consistent 4D Editing

链接: https://arxiv.org/abs/2503.11044
作者: Hasan Iqbal,Nazmul Karim,Umar Khalid,Azib Farooq,Zichun Zhong,Jing Hua,Chen Chen
机构: Wayne State University (韦恩州立大学); University of Central Florida (中佛罗里达大学); Miami University (迈阿密大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages, 7 figures

点击查看摘要

[CV-102] ACMo: Attribute Controllable Motion Generation

链接: https://arxiv.org/abs/2503.11038
作者: Mingjie Wei,Xuemei Xie,Guangming Shi
机构: Xidian University (西安电子科技大学); Peng Cheng Laboratory (鹏城实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-103] Weakly Supervised Contrastive Adversarial Training for Learning Robust Features from Semi-supervised Data CVPR2025

链接: https://arxiv.org/abs/2503.11032
作者: Lilin Zhang,Chengpei Wu,Ning Yang
机构: School of Computer Science, Sichuan University (四川大学), Chengdu, China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: This paper has been accepted by CVPR 2025

点击查看摘要

[CV-104] FMNet: Frequency-Assisted Mamba-Like Linear Attention Network for Camouflaged Object Detection

链接: https://arxiv.org/abs/2503.11030
作者: Ming Deng,Sijin Sun,Zihao Li,Xiaochuan Hu,Xing Wu
机构: Shanghai University; Agency for Science, Technology and Research (新加坡科技研究局); University of Electronic Science and Technology of China (电子科技大学); 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-105] EmoDiffusion: Enhancing Emotional 3D Facial Animation with Latent Diffusion Models

链接: https://arxiv.org/abs/2503.11028
作者: Yixuan Zhang,Qing Chang,Yuxi Wang,Guang Chen,Zhaoxiang Zhang,Junran Peng
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-106] Fast and Robust Localization for Humanoid Soccer Robot via Iterative Landmark Matching

链接: https://arxiv.org/abs/2503.11020
作者: Ruochen Hou,Mingzhang Zhu,Hyunwoo Nam,Gabriel I. Fernandez,Dennis W. Hong
机构: Robotics and Mechanisms Laboratory (RoMeLa), Department of Mechanical and Aerospace Engineering, University of California, Los Angeles, CA 90095, USA.
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-107] Deep Incomplete Multi-view Clustering with Distribution Dual-Consistency Recovery Guidance

链接: https://arxiv.org/abs/2503.11017
作者: Jiaqi Jin,Siwei Wang,Zhibin Dong,Xihong Yang,Xinwang Liu,En Zhu,Kunlun He
机构: School of Computer, National University of Defense Technology (国防科技大学), Changsha, China; Intelligent Game and Decision Lab, Academy of Military Sciences (军事科学院), Beijing, China; Medical Big Data Research Center, Chinese PLA General Hospital (中国人民解放军总医院), Beijing, China
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-108] Comparative Analysis of Advanced AI-based Object Detection Models for Pavement Marking Quality Assessment during Daytime

链接: https://arxiv.org/abs/2503.11008
作者: Gian Antariksa,Rohir Chakraborty,Shriyank Somvanshi,Subasish Das,Mohammad Jalayer,Deep Rameshkumar Patel,David Mills
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 6 pages, 3 figures, accepted at IEEE CAI 2025

点击查看摘要

[CV-109] Observation-Graph Interaction and Key-Detail Guidance for Vision and Language Navigation

链接: https://arxiv.org/abs/2503.11006
作者: Yifan Xie,Binkai Ou,Fei Ma,Yaohua Liu
机构: Xi’an Jiaotong University (西安交通大学); Guangdong Institute of Intelligence Science and Technology (广东智能科学与技术研究院); BoardWare Information System Company Ltd; Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) (广东人工智能与数字经济实验室（深圳）)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 8 pages, 4 figures

点击查看摘要

[CV-110] Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detection ICLR2025

链接: https://arxiv.org/abs/2503.11005
作者: Chuhan Zhang,Chaoyang Zhu,Pingcheng Dong,Long Chen,Dong Zhang
机构: The Hong Kong University of Science and Technology (香港科技大学); AI Chip Center for Emerging Smart Systems (ACCESS)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 5 figures, Published as a conference paper at ICLR 2025

点击查看摘要

[CV-111] VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention AAAI2025

链接: https://arxiv.org/abs/2503.11004
作者: Jiangning Wei,Lixiong Qin,Bo Yu,Tianjian Zou,Chuhan Yan,Dandan Xiao,Yang Yu,Lan Yang,Ke Li,Jun Liu
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-112] Rethinking Rotation-Invariant Recognition of Fine-grained Shapes from the Perspective of Contour Points

链接: https://arxiv.org/abs/2503.10992
作者: Yanjie Xu,Handing Xu,Tianmu Wang,Yaguan Li,Yunzhi Chen,Zhenguo Nie
机构: Department of Mechanical Engineering, Tsinghua University, Beijing, 100084, China (清华大学机械工程系, 北京, 100084, 中国); State Key Laboratory of Tribology in Advanced Equipment, Tsinghua University, Beijing, 100084, China (摩擦学国家重点实验室(先进成形制造教育部重点实验室), 清华大学, 北京, 100084, 中国); College of Mechanical Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China (太原理工大学机械工程学院, 太原, 山西, 030024, 中国)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: This work has been submitted to the IEEE for possible publication

点击查看摘要

[CV-113] Image-Goal Navigation Using Refined Feature Guidance and Scene Graph Enhancement

链接: https://arxiv.org/abs/2503.10986
作者: Zhicheng Feng,Xieyuanli Chen,Chenghao Shi,Lun Luo,Zhichao Chen,Yun-Hui Liu,Huimin Lu
机构: College of Intelligence Science and Technology, National University of Defense Technology, China(国防科技大学智能科学与技术学院，中国); National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology, China(国防科技大学装备状态感知与智能支持国家重点实验室，中国); Zhejiang University, China(浙江大学，中国); Jiangxi University of Science and Technology, China(江西理工大学，中国); T Stone Robotics Institute and Department of Mechanical and Automation Engineering, the Chinese University of Hong Kong, China(香港中文大学石天机器人研究所和机械与自动化工程系，中国)
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-114] Enhanced Multi-View Pedestrian Detection Using Probabilistic Occupancy Volume

链接: https://arxiv.org/abs/2503.10982
作者: Reef Alturki,Adrian Hilton,Jean-Yves Guillemaut
机构: Centre for Vision, Speech and Signal Processing, University of Surrey (萨里大学视觉、语音和信号处理中心)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-115] Unlocking Open-Set Language Accessibility in Vision Models

链接: https://arxiv.org/abs/2503.10981
作者: Fawaz Sammani,Jonas Fischer,Nikos Deligiannis
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-116] OuroMamba: A Data-Free Quantization Framework for Vision Mamba Models

链接: https://arxiv.org/abs/2503.10959
作者: Akshat Ramachandran,Mingyu Lee,Huan Xu,Souvik Kundu,Tushar Krishna
机构: Georgia Institute of Technology (乔治亚理工学院); Intel Labs (英特尔实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-117] Automated Tomato Maturity Estimation Using an Optimized Residual Model with Pruning and Quantization Techniques

链接: https://arxiv.org/abs/2503.10940
作者: Muhammad Waseem,Chung-Hsuan Huang,Muhammad Muzzammil Sajjad,Laraib Haider Naqvi,Yaqoob Majeed,Tanzeel Ur Rehman,Tayyaba Nadeem
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-118] ChatGPT Encounters Morphing Attack Detection: Zero-Shot MAD with Multi-Modal Large Language Models and General Vision Models

链接: https://arxiv.org/abs/2503.10937
作者: Haoyu Zhang,Raghavendra Ramachandra,Kiran Raja,Christoph Busch
机构: Norwegian University of Science and Technology (NTNU)(挪威科技大学); Darmstadt University of Applied Sciences (HDA)(达姆施塔特应用技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-119] Multi-Domain Biometric Recognition using Body Embeddings

链接: https://arxiv.org/abs/2503.10931
作者: Anirudh Nanduri,Siyuan Huang,Rama Chellappa
机构: University of Maryland (马里兰大学), College Park; Johns Hopkins University (约翰斯·霍普金斯大学), Baltimore
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-120] PolyRoof: Precision Roof Polygonization in Urban Residential Building with Graph Neural Networks

链接: https://arxiv.org/abs/2503.10913
作者: Chaikal Amrullah,Daniel Panangian,Ksenia Bittner
机构: Remote Sensing Technology Institute (IMF); German Aerospace Center (DLR)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to Joint Urban Remote Sensing Event (JURSE) 2025

点击查看摘要

[CV-121] JPEG Compliant Compression for Both Human and Machine A Report

链接: https://arxiv.org/abs/2503.10912
作者: Linfeng Ye
机构: University of Waterloo (滑铁卢大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 9 pages, 6 figures

点击查看摘要

[CV-122] Learning to Inference Adaptively for Multimodal Large Language Models

链接: https://arxiv.org/abs/2503.10905
作者: Zhuoyan Xu,Khoi Duc Nguyen,Preeti Mukherjee,Saurabh Bagchi,Somali Chaterji,Yingyu Liang,Yin Li
机构: University of Wisconsin-Madison (威斯康星大学麦迪逊分校); Purdue University (普渡大学); The University of Hong Kong (香港大学)
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-123] Memory-Efficient 3D High-Resolution Medical Image Synthesis Using CRF-Guided GANs ALT ICPR2024

链接: https://arxiv.org/abs/2503.10899
作者: Mahshid Shiri,Alessandro Bruno,Daniele Loiacono
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to Artificial Intelligence for Healthcare Applications, 3rd International Workshop ICPR 2024

点击查看摘要

[CV-124] rajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSM CVPR2025

链接: https://arxiv.org/abs/2503.10898
作者: Yizhou Huang,Yihua Cheng,Kezhi Wang
机构: Brunel University of London; University of Birmingham
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025

点击查看摘要

[CV-125] axonomic Reasoning for Rare Arthropods: Combining Dense Image Captioning and RAG for Interpretable Classification

链接: https://arxiv.org/abs/2503.10886
作者: Nathaniel Lesperance,Sujeevan Ratnasingham,Graham W. Taylor
机构: University of Guelph; Vector Institute for AI; Centre for Biodiversity Genomics
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG); Populations and Evolution (q-bio.PE)
备注: 12 pages, 3 figures

点击查看摘要

[CV-126] Convolutional Rectangular Attention Module

链接: https://arxiv.org/abs/2503.10875
作者: Hai-Vy Nguyen,Fabrice Gamboa,Sixin Zhang,Reda Chhaibi,Serge Gratton,Thierry Giaccone
机构: Ampere Software Technology (安培软件科技); Institut de mathématiques de Toulouse (图卢兹数学研究所); Institut de Recherche en Informatique de Toulouse (图卢兹信息学研究所); Laboratoire Jean Alexandre Dieudonné, Université Côte d’Azur (让-亚历山大-迪厄多内实验室，尼斯海岸大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Machine Learning (stat.ML)
备注:

点击查看摘要

[CV-127] AIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Models IJCAI-25

链接: https://arxiv.org/abs/2503.10872
作者: Xiangyu Yin,Yi Qi,Jinwei Hu,Zhen Chen,Yi Dong,Xingyu Zhao,Xiaowei Huang,Wenjie Ruan
机构: University of Liverpool (利物浦大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Under review of IJCAI-25

点击查看摘要

[CV-128] RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priors

链接: https://arxiv.org/abs/2503.10860
作者: Avinash Paliwal,Xilong Zhou,Wei Ye,Jinhui Xiong,Rakesh Ranjan,Nima Khademi Kalantari
机构: Texas A&M University (德克萨斯农工大学); Meta Reality Labs (Meta 实景实验室); Max Planck Institute for Informatics (马克斯·普朗克信息学研究所)
类目: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR)
备注: Project page: this https URL , Code: this https URL

点击查看摘要

[CV-129] Dual Codebook VQ: Enhanced Image Reconstruction with Reduced Codebook Size

链接: https://arxiv.org/abs/2503.10832
作者: Parisa Boodaghi Malidarreh,Jillur Rahman Saurav,Thuong Le Hoai Pham,Amir Hajighasemi,Anahita Samadi,Saurabh Shrinivas Maydeo,Mohammad Sadegh Nasr,Jacob M. Luber
机构: Department of Computer Science, The University of Texas at Arlington (德克萨斯大学阿灵顿分校计算机科学系)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 15 pages, including main text and supplementary data

点击查看摘要

[CV-130] Large-scale Pre-training for Grounded Video Caption Generation

链接: https://arxiv.org/abs/2503.10781
作者: Evangelos Kazakos,Cordelia Schmid,Josef Sivic
机构: Czech Institute of Informatics, Robotics and Cybernetics at the Czech Technical University in Prague (捷克技术大学布拉格分校的捷克信息系统、机器人和控制研究中心); Inria (Inria), École normale supérieure (法国高等师范学院), CNRS (法国国家科学研究中心), PSL Research University (巴黎文理研究大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: arXiv admin note: text overlap with arXiv:2411.07584

点击查看摘要

[CV-131] he Power of One: A Single Example is All it Takes for Segmentation in VLMs

链接: https://arxiv.org/abs/2503.10779
作者: Mir Rayat Imtiaz Hossain,Mennatullah Siam,Leonid Sigal,James J. Little
机构: University of British Columbia (英属哥伦比亚大学); Vector Institute for AI (向量人工智能研究所); Canada CIFAR AI Chair (加拿大 CIFAR 人工智能主席)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-132] HeightFormer: Learning Height Prediction in Voxel Features for Roadside Vision Centric 3D Object Detection via Transformer

链接: https://arxiv.org/abs/2503.10777
作者: Zhang Zhang,Chao Sun,Chao Yue,Da Wen,Yujie Chen,Tianze Wang,Jianghao Leng
机构: Beijing Institute of Technology (北京理工大学); ETH Zurich (瑞士联邦理工学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-133] FlowTok: Flowing Seamlessly Across Text and Image Tokens

链接: https://arxiv.org/abs/2503.10772
作者: Ju He,Qihang Yu,Qihao Liu,Liang-Chieh Chen
机构: ByteDance Seed (字节跳动种子团队); Johns Hopkins University (约翰斯·霍普金斯大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page at this https URL

点击查看摘要

[CV-134] Clothes-Changing Person Re-identification Based On Skeleton Dynamics

链接: https://arxiv.org/abs/2503.10759
作者: Asaf Joseph,Shmuel Peleg
机构: The Hebrew University of Jerusalem(耶路撒冷希伯来大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-135] Unifying 2D and 3D Vision-Language Understanding

【速读】：该论文致力于解决3D视觉-语言学习领域因大规模3D数据集匮乏所面临的挑战。解决方案的关键在于提出UniVLG，一种统一的2D与3D视觉-语言理解架构，通过从预训练的2D模型初始化大多数模型权重，并在2D和3D视觉-语言数据上进行联合训练，有效弥合了现有以2D为中心的模型与具身系统中丰富的3D感官数据之间的差距。论文创新性地引入了跨2D和3D模态共享的语言条件掩码解码器，以更有效地在RGB和RGB-D图像中定位对象，同时通过2D到3D升维策略进一步缩小2D与3D模态间的域差异，从而显著提升了多任务下的性能表现，并实现了无需依赖3D网格重建或真实物体提议的更贴近实际的具身对齐评估标准。

链接: https://arxiv.org/abs/2503.10745
作者: Ayush Jain,Alexander Swerdlow,Yuzhou Wang,Sergio Arnaud,Ada Martin,Alexander Sax,Franziska Meier,Katerina Fragkiadaki
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Robotics (cs.RO)
备注: The first two authors contributed equally

点击查看摘要

Abstract:Progress in 3D vision-language learning has been hindered by the scarcity of large-scale 3D datasets. We introduce UniVLG, a unified architecture for 2D and 3D vision-language understanding that bridges the gap between existing 2D-centric models and the rich 3D sensory data available in embodied systems. Our approach initializes most model weights from pre-trained 2D models and trains on both 2D and 3D vision-language data. We propose a novel language-conditioned mask decoder shared across 2D and 3D modalities to ground objects effectively in both RGB and RGB-D images, outperforming box-based approaches. To further reduce the domain gap between 2D and 3D, we incorporate 2D-to-3D lifting strategies, enabling UniVLG to utilize 2D data to enhance 3D performance. With these innovations, our model achieves state-of-the-art performance across multiple 3D vision-language grounding tasks, demonstrating the potential of transferring advances from 2D vision-language learning to the data-constrained 3D domain. Furthermore, co-training on both 2D and 3D data enhances performance across modalities without sacrificing 2D capabilities. By removing the reliance on 3D mesh reconstruction and ground-truth object proposals, UniVLG sets a new standard for realistic, embodied-aligned evaluation. Code and additional visualizations are available at \hrefthis https URLthis http URL .
zh

[CV-136] Subnet-Aware Dynamic Supernet Training for Neural Architecture Search CVPR2025

链接: https://arxiv.org/abs/2503.10740
作者: Jeimin Jeon,Youngmin Oh,Junghyup Lee,Donghyeon Baek,Dohyung Kim,Chanho Eom,Bumsub Ham
机构: Yonsei University (延世大学); Articron Inc.; Samsung Research; Samsung Advanced Institute of Technology (三星高级技术研究院); Chung-Ang University (中央大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to CVPR 2025

点击查看摘要

[CV-137] Visual Polarization Measurement Using Counterfactual Image Generation

链接: https://arxiv.org/abs/2503.10738
作者: Mohammad Mosaffa,Omid Rafieian,Hema Yoganarasimhan
机构: Cornell University (康奈尔大学); University of Washington (华盛顿大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-138] Sparse Dictionary Learning for Image Recovery by Iterative Shrinkage

链接: https://arxiv.org/abs/2503.10732
作者: Shima Shabani,Mohammadsadegh Khoshghiaferezaee,Michael Breuß
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 19 pages, 5 Figures, IntelliSys 2025

点击查看摘要

[CV-139] Leverag ing Vision-Language Embeddings for Zero-Shot Learning in Histopathology Images

链接: https://arxiv.org/abs/2503.10731
作者: Md Mamunur Rahaman,Ewan K. A. Millar,Erik Meijering
机构: School of Computer Science and Engineering (计算机科学与工程学院), University of New South Wales (新南威尔士大学), Sydney, NSW 2052, Australia; Department of Anatomical Pathology (解剖病理学系), NSW Health Pathology, St. George Hospital, NSW 2217, Australia
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-140] 3D Extended Object Tracking based on Extruded B-Spline Side View Profiles

链接: https://arxiv.org/abs/2503.10730
作者: Longfei Han,Klaus Kefferpütz,Jürgen Beyerer
机构: Application Center »Connected Mobility and Infrastructure«, Fraunhofer IVI (弗劳恩霍夫交通安全创新中心); Technische Hochschule Ingolstadt (英戈尔施塔特应用技术大学); Karlsruhe Institute of Technology (KIT) (卡尔斯鲁厄理工学院); Fraunhofer IOSB (弗劳恩霍夫信息安全与通信技术研究所)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: 8 pages, 7 figures, submitted to FUSION 2025

点击查看摘要

[CV-141] Long-Video Audio Synthesis with Multi-Agent Collaboration

【速读】：该论文致力于解决长视频到音频合成（video-to-audio synthesis）在长篇内容（如电影）中面临的动态语义变化、时间错位以及缺乏专用数据集等挑战。现有方法虽在短片中表现良好，但在长场景中因片段化合成与跨场景一致性不足而表现欠佳。论文提出了一种名为LVAS-Agent的新多智能体框架，通过角色专业化协作模拟专业配音流程。其关键创新包括用于场景/剧本精炼的讨论-修正机制以及用于时序-语义对齐的生成-检索循环。此外，为了系统评估，论文还引入了包含207个专业策划长视频的首个基准数据集LVAS-Bench。实验表明，该方法在视听对齐方面优于基线方法。

链接: https://arxiv.org/abs/2503.10719
作者: Yehang Zhang,Xinli Xu,Xiaojie Xu,Li Liu,Yingcong Chen
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

Abstract:Video-to-audio synthesis, which generates synchronized audio for visual content, critically enhances viewer immersion and narrative coherence in film and interactive media. However, video-to-audio dubbing for long-form content remains an unsolved challenge due to dynamic semantic shifts, temporal misalignment, and the absence of dedicated datasets. While existing methods excel in short videos, they falter in long scenarios (e.g., movies) due to fragmented synthesis and inadequate cross-scene consistency. We propose LVAS-Agent, a novel multi-agent framework that emulates professional dubbing workflows through collaborative role specialization. Our approach decomposes long-video synthesis into four steps including scene segmentation, script generation, sound design and audio synthesis. Central innovations include a discussion-correction mechanism for scene/script refinement and a generation-retrieval loop for temporal-semantic alignment. To enable systematic evaluation, we introduce LVAS-Bench, the first benchmark with 207 professionally curated long videos spanning diverse scenarios. Experiments demonstrate superior audio-visual alignment over baseline methods.
zh

[CV-142] am NYCU at Defactify4: Robust Detection and Source Identification of AI-Generated Images Using CNN and CLIP-Based Models

链接: https://arxiv.org/abs/2503.10718
作者: Tsan-Tsung Yang,I-Wei Chen,Kuan-Ting Chen,Shang-Hsuan Chiang,Wen-Chih Peng
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-143] HiCMamba: Enhancing Hi-C Resolution and Identifying 3D Genome Structures with State Space Modeling

链接: https://arxiv.org/abs/2503.10713
作者: Minghao Yang,Zhi-An Huang,Zhihang Zheng,Yuqiao Liu,Shichen Zhang,Pengfei Zhang,Hui Xiong,Shaojun Tang
机构: Hong Kong University of Science and Technology (Guangzhou)(香港科技大学（广州）); City University of Hong Kong (Dongguan)(香港城市大学（东莞))
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-144] Enhanced Continual Learning of Vision-Language Models with Model Fusion

链接: https://arxiv.org/abs/2503.10705
作者: Haoyuan Gao,Zicong Zhang,Yuqi Wei,Linglan Zhao,Guilin Li,Yexin Li,Linghe Kong,Weiran Huang
机构: Shanghai Jiao Tong University (上海交通大学); Shanghai Innovation Institute (上海创新研究院); State Key Laboratory of General Artificial Intelligence, BIGAI (通用人工智能国家重点实验室, BIGAI); Tencent (腾讯)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: arXiv admin note: text overlap with arXiv:2303.10070 by other authors

点击查看摘要

[CV-145] Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework

链接: https://arxiv.org/abs/2503.10704
作者: Jing Wang,Fengzhuo Zhang,Xiaoli Li,Vincent Y. F. Tan,Tianyu Pang,Chao Du,Aixin Sun,Zhuoran Yang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注:

点击查看摘要

[CV-146] Video Individual Counting for Moving Drones

链接: https://arxiv.org/abs/2503.10701
作者: Yaowu Fan,Jia Wan,Tao Han,Antoni B. Chan,Andy J. Ma
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-147] A-V2A: Textually Assisted Video-to-Audio Generation

链接: https://arxiv.org/abs/2503.10700
作者: Yuhuan You,Xihong Wu,Tianshu Qu
机构: State Key Laboratory of General Artificial Intelligence (国家重点实验室)(北京大学); School of Intelligence Science and Technology (智能科学与技术学院)(北京大学), Peking University (北京大学), Beijing, China
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注:

点击查看摘要

[CV-148] st-Time Discovery via Hashing Memory

链接: https://arxiv.org/abs/2503.10699
作者: Fan Lyu,Tianle Liu,Zhang Zhang,Fuyuan Hu,Liang Wang
机构: New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences (新自动化研究所模式识别国家重点实验室); School of Electric & Information Engineering, Suzhou University of Science and Technology (苏州科技大学电气与电子信息工程学院)
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-149] Zero-Shot Subject-Centric Generation for Creative Application Using Entropy Fusion

链接: https://arxiv.org/abs/2503.10697
作者: Kaifeng Zou,Xiaoyi Feng,Peng Wang,Tao Huang,Zizhou Huang,Zhang Haihang,Yuntao Zou,Dagang Li
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV)
备注: 8 pages, 8 figure

点击查看摘要

[CV-150] Neighboring Autoregressive Modeling for Efficient Visual Generation

链接: https://arxiv.org/abs/2503.10696
作者: Yefei He,Yuanyu He,Shaoxuan He,Feng Chen,Hong Zhou,Kaipeng Zhang,Bohan Zhuang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注: 16 pages

点击查看摘要

[CV-151] Knowledge Consultation for Semi-Supervised Semantic Segmentation

链接: https://arxiv.org/abs/2503.10693
作者: Thuan Than,Nhat-Anh Nguyen-Dang,Dung Nguyen,Salwa K. Al Khatib,Ahmed Elhagry,Hai Phan,Yihui He,Zhiqiang Shen,Marios Savvides,Dang Huynh
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-152] Exploring the best way for UAV visual localization under Low-altitude Multi-view Observation Condition: a Benchmark

链接: https://arxiv.org/abs/2503.10692
作者: Yibin Ye,Xichao Teng,Shuo Chen,Zhang Li,Leqi Liu,Qifeng Yu,Tao Tan
机构: National University of Defense Technology (国防科技大学), Macao Polytechnic University (澳门城市大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-153] Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluation

链接: https://arxiv.org/abs/2503.10691
作者: Qiji Zhou,Yifan Gong,Guangsheng Bao,Hongjie Qiu,Jinqiang Li,Xiangrong Zhu,Huajian Zhang,Yue Zhang
机构: School of Engineering, Westlake University (西湖大学工程学院); College of Computer Science and Technology, Hangzhou Dianzi University (杭州电子科技大学计算机科学与技术学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-154] Context-guided Responsible Data Augmentation with Diffusion Models ICLR

链接: https://arxiv.org/abs/2503.10687
作者: Khawar Islam,Naveed Akhtar
机构: School of Computing and Information Systems, The University of Melbourne (墨尔本大学计算机与信息系统学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: ICLRw

点击查看摘要

[CV-155] MaskAttn-UNet: A Mask Attention-Driven Framework for Universal Low-Resolution Image Segmentation ICCV2025

链接: https://arxiv.org/abs/2503.10686
作者: Anzhe Cheng,Chenzhong Yin,Yu Chang,Heng Ping,Shixuan Li,Shahin Nazarian,Paul Bogdan
机构: University of Southern California (南加州大学); The University of British Columbia (不列颠哥伦比亚大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Image and Video Processing (eess.IV)
备注: ICCV 2025 Submission

点击查看摘要

[CV-156] VFM-UDA: Improving Network Architectures and Data Strategies for Unsupervised Domain Adaptive Semantic Segmentation

链接: https://arxiv.org/abs/2503.10685
作者: Brunó B. Englert,Gijs Dubbelman
机构: Eindhoven University of Technology (埃因霍温理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-157] Open-World Skill Discovery from Unsegmented Demonstrations

链接: https://arxiv.org/abs/2503.10684
作者: Jingwen Deng,Zihao Wang,Shaofei Cai,Anji Liu,Yitao Liang
机构: Peking University (北京大学); University of California, Los Angeles (加州大学洛杉矶分校)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-158] VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion

链接: https://arxiv.org/abs/2503.10678
作者: Lehan Yang,Jincen Song,Tianlong Wang,Daiqing Qi,Weili Shi,Yuheng Liu,Sheng Li
机构: University of Virginia; Columbia University; Texas A&M University
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-159] CeTAD: Towards Certified Toxicity-Aware Distance in Vision Language Models ICML2025

链接: https://arxiv.org/abs/2503.10661
作者: Xiangyu Yin,Jiaxu Liu,Zhen Chen,Jinwei Hu,Yi Dong,Xiaowei Huang,Wenjie Ruan
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Under review of ICML 2025

点击查看摘要

[CV-160] xt-to-3D Generation using Jensen-Shannon Score Distillation

链接: https://arxiv.org/abs/2503.10660
作者: Khoi Do,Binh-Son Hua
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-161] Video Anomaly Detection with Structured Keywords

链接: https://arxiv.org/abs/2503.10653
作者: Thomas Foltz
机构: The Pennsylvania State University (宾夕法尼亚州立大学)
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-162] Physics-Aware Human-Object Rendering from Sparse Views via 3D Gaussian Splatting

链接: https://arxiv.org/abs/2503.09640
作者: Weiquan Wang,Jun Xiao,Yueting Zhuang,Long Chen
机构: Zhejiang University (浙江大学); Hong Kong University of Science and Technology (香港科技大学)
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-163] Pathology Image Compression with Pre-trained Autoencoders

链接: https://arxiv.org/abs/2503.11591
作者: Srikar Yellapragada,Alexandros Graikos,Kostas Triaridis,Zilinghan Li,Tarak Nath Nandi,Ravi K Madduri,Prateek Prasanna,Joel Saltz,Dimitris Samaras
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-164] Alzheimers Disease Classification Using Retinal OCT: TransnetOCT and Swin Transformer Models

链接: https://arxiv.org/abs/2503.11511
作者: Siva Manohar Reddy Kesu,Neelam Sinha,Hariharan Ramasangu,Thomas Gregor Issac
机构: AIT Resource Group Inc (AIT 资源集团有限公司); Centre for Brain Research (脑研究中心), Indian Institute of Science (印度科学研究所); Relecura. Inc. (Relecura有限公司); Centre for Brain Research (脑研究中心), Indian Institute of Science (印度科学研究所)
类目: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: 18 pages, 25 figures

点击查看摘要

[CV-165] FG-DFPN: Flow Guided Deformable Frame Prediction Network

链接: https://arxiv.org/abs/2503.11343
作者: M. Akın Yılmaz,Ahmet Bilican,A. Murat Tekalp
机构: Codeway AI Research (Codeway AI 研究); Koç University (科奇大学)
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注: Submitted to 33th European Signal Processing Conference (EUSIPCO) 2025

点击查看摘要

[CV-166] Advancements in Real-Time Oncology Diagnosis: Harnessing AI and Image Fusion Techniques

链接: https://arxiv.org/abs/2503.11332
作者: Leila Bagheriye,Johan Kwisthout
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注: This paper is under review

点击查看摘要

[CV-167] Deep Lossless Image Compression via Masked Sampling and Coarse-to-Fine Auto-Regression

链接: https://arxiv.org/abs/2503.11231
作者: Tiantian Li,Qunbing Xia,Yue Li,Ruixiao Guo,Gaobo Yang
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages

点击查看摘要

[CV-168] MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation

链接: https://arxiv.org/abs/2503.11026
作者: Sungwoo Cho,Jeongsoo Choi,Sungnyun Kim,Se-Young Yun
机构: KAIST AI (KAIST AI); KAIST EE (KAIST EE)
类目: Audio and Speech Processing (eess.AS); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Multimedia (cs.MM)
备注: Preliminary work

点击查看摘要

[CV-169] DNA Origami Nanostructures Observed in Transmission Electron Microscopy Images can be Characterized through Convolutional Neural Networks

链接: https://arxiv.org/abs/2503.10950
作者: Xingfei Wei,Qiankun Mo,Chi Chen,Mark Bathe,Rigoberto Hernandez
机构: Department of Chemistry, Johns Hopkins University, Baltimore, Maryland 21218, USA; Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States; Department of Chemistry, Johns Hopkins University, Baltimore, Maryland 21218, USA
类目: Chemical Physics (physics.chem-ph); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-170] Deep Learning-Based Automated Workflow for Accurate Segmentation and Measurement of Abdominal Organs in CT Scans

链接: https://arxiv.org/abs/2503.10717
作者: Praveen Shastry,Ashok Sharma,Kavya Mohan,Naveen Kumarasami,Anandakumar D,Mounigasri M,Keerthana R,Kishore Prasath Venkatesh,Bargava Subramanian,Kalyan Sivasailam
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: 13 pages , 3 figures

点击查看摘要

[CV-171] Optimal Transport for Brain-Image Alignment: Unveiling Redundancy and Synergy in Neural Information Processing

链接: https://arxiv.org/abs/2503.10663
作者: Yang Xiao,Wang Lu,Jie Ji,Ruimeng Ye,Gen Li,Xiaolong Ma,Bo Hui
机构: University of Tulsa (塔尔萨大学); Tsinghua University (清华大学); Clemson University (克莱姆森大学)
类目: Neurons and Cognition (q-bio.NC); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 14pages

点击查看摘要

人工智能

[AI-0] ASMA-Tune: Unlocking LLM s Assembly Code Comprehension via Structural-Semantic Instruction Tuning

链接: https://arxiv.org/abs/2503.11617
作者: Xinyi Wang,Jiashui Wang,Peng Chen,Jinbo Su,Yanming Liu,Long Liu,Yangdong Wang,Qiyuan Chen,Kai Yun,Chunfu Jia
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
*备注: 19 pages, multiple figures

点击查看摘要

[AI-1] Synthesizing Access Control Policies using Large Language Models ICSE2025

链接: https://arxiv.org/abs/2503.11573
作者: Adarsh Vatsa,Pratyush Patel,William Eiers
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
*备注: to be published in the NLBSE Workshop at ICSE 2025

点击查看摘要

[AI-2] Implicit Bias-Like Patterns in Reasoning Models

链接: https://arxiv.org/abs/2503.11572
作者: Messi H.J. Lee,Calvin K. Lai
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-3] Designing Neural Synthesizers for Low Latency Interaction

链接: https://arxiv.org/abs/2503.11562
作者: Franco Caspe,Jordie Shier,Mark Sandler,Charalampos Saitis,Andrew McPherson
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS)
*备注: See website at this http URL - 13 pages, 5 figures, accepted to the Journal of the Audio Engineering Society

点击查看摘要

[AI-4] Potential of large language model-powered nudges for promoting daily water and energy conservation

链接: https://arxiv.org/abs/2503.11531
作者: Zonghan Li,Song Tong,Yi Liu,Kaiping Peng,Chunyan Wang
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-5] Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attacks

链接: https://arxiv.org/abs/2503.11514
作者: Pengxin Guo,Runxi Wang,Shuang Zeng,Jinjing Zhu,Haoning Jiang,Yanran Wang,Yuyin Zhou,Feifei Wang,Hui Xiong,Liangqiong Qu
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-6] Unicorn: A Universal and Collaborative Reinforcement Learning Approach Towards Generalizable Network-Wide Traffic Signal Control

链接: https://arxiv.org/abs/2503.11488
作者: Yifeng Zhang,Yilin Liu,Ping Gong,Peizhuo Li,Mingfeng Fan,Guillaume Sartoretti
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO)
*备注:

点击查看摘要

[AI-7] Heterogeneous Causal Discovery of Repeated Undesirable Health Outcomes

链接: https://arxiv.org/abs/2503.11477
作者: Shishir Adhikari,Guido Muscioni,Mark Shapiro,Plamen Petrov,Elena Zheleva
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-8] Research Vision: Multi-Agent Path Planning for Cops And Robbers Via Reactive Synthesis

链接: https://arxiv.org/abs/2503.11475
作者: William Fishell,Andoni Rodriguez,Mark Santolucito
类目: Logic in Computer Science (cs.LO); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-9] Integrating LLM s in Gamified Systems

链接: https://arxiv.org/abs/2503.11458
作者: Carlos J. Costa
类目: Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
*备注: 9 pages, 2 figures, 1 table

点击查看摘要

[AI-10] Preference Elicitation for Multi-objective Combinatorial Optimization with Active Learning and Maximum Likelihood Estimation

链接: https://arxiv.org/abs/2503.11435
作者: Marianne Defresne,Jayanta Mandi,Tias Guns
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: 9 pages, 2 figures

点击查看摘要

[AI-11] Adaptive Torque Control of Exoskeletons under Spasticity Conditions via Reinforcement Learning

链接: https://arxiv.org/abs/2503.11433
作者: Andrés Chavarrías,David Rodriguez-Cianca,Pablo Lanillos
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Systems and Control (eess.SY)
*备注: Accepted for publication in IEEE 19th International Conference on Rehabilitation Robotics (ICORR2025)

点击查看摘要

[AI-12] Combining Causal Models for More Accurate Abstractions of Neural Networks

链接: https://arxiv.org/abs/2503.11429
作者: Theodora-Mara Pîslar,Sara Magliacane,Atticus Geiger
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-13] From Generative AI to Innovative AI: An Evolutionary Roadmap

链接: https://arxiv.org/abs/2503.11419
作者: Seyed Mahmoud Sajjadi Mohammadabadi
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-14] A Neural Network Architecture Based on Attention Gate Mechanism for 3D Magnetotelluric Forward Modeling

链接: https://arxiv.org/abs/2503.11408
作者: Xin Zhong,Weiwei Ling,Kejia Pan,Pinxia Wu,Jiajing Zhang,Zhiliang Zhan,Wenbo Xiao
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 12 pages, 16 figures

点击查看摘要

[AI-15] Hierarchical Information-Guided Spatio-Temporal Mamba for Stock Time Series Forecasting

链接: https://arxiv.org/abs/2503.11387
作者: Wenbo Yan,Shurui Wang,Ying Tan
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-16] An experimental approach on Few Shot Class Incremental Learning

链接: https://arxiv.org/abs/2503.11349
作者: Marinela Adam
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-17] Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model

链接: https://arxiv.org/abs/2503.11339
作者: Moritz A. Zanger,Pascal R. Van der Vaart,Wendelin Böhmer,Matthijs T.J. Spaan
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
*备注:

点击查看摘要

[AI-18] Financial Fraud Detection with Entropy Computing

链接: https://arxiv.org/abs/2503.11273
作者: Babak Emami,Wesley Dyk,David Haycraft,Carrie Spear,Lac Nguyen,Nicholas Chancellor
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Optics (physics.optics); Quantum Physics (quant-ph)
*备注: 15 pages including references and appendix, 6 figures

点击查看摘要

[AI-19] Spherical Tree-Sliced Wasserstein Distance

链接: https://arxiv.org/abs/2503.11249
作者: Hoang V. Tran,Thanh T. Chu,Khoi N.M. Nguyen,Trang Pham,Tam Le,Tan M. Nguyen
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-20] GKG-LLM : A Unified Framework for Generalized Knowledge Graph Construction

链接: https://arxiv.org/abs/2503.11227
作者: Jian Zhang,Bifan Wei,Shihao Qi,haiping Zhu,Jun Liu,Qika Lin
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-21] Can Large Reasoning Models do Analogical Reasoning under Perceptual Uncertainty?

链接: https://arxiv.org/abs/2503.11207
作者: Giacomo Camposampiero,Michael Hersche,Roger Wattenhofer,Abu Sebastian,Abbas Rahimi
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-22] Align in Depth: Defending Jailbreak Attacks via Progressive Answer Detoxification

链接: https://arxiv.org/abs/2503.11185
作者: Yingjie Zhang,Tong Liu,Zhe Zhao,Guozhu Meng,Kai Chen
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-23] Unifying Perplexing Behaviors in Modified BP Attributions through Alignment Perspective

链接: https://arxiv.org/abs/2503.11160
作者: Guanhua Zheng,Jitao Sang,Changsheng Xu
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 11 pages, 9 figures

点击查看摘要

[AI-24] Dont Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning

链接: https://arxiv.org/abs/2503.11127
作者: Matthew Khoriaty(1),Andrii Shportko(1),Gustavo Mercier(1),Zach Wood-Doughty(1) ((1) Northwestern University)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 6 pages, 6 figures

点击查看摘要

[AI-25] A Survey of Cross-domain Graph Learning: Progress and Future Directions

链接: https://arxiv.org/abs/2503.11086
作者: Haihong Zhao,Chenyi Zi,Aochuan Chen,Jia Li
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-26] API Agents vs. GUI Agents : Divergence and Convergence

链接: https://arxiv.org/abs/2503.11069
作者: Chaoyun Zhang,Shilin He,Liqun Li,Si Qin,Yu Kang,Qingwei Lin,Dongmei Zhang
类目: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
*备注:

点击查看摘要

[AI-27] Low-cost Real-world Implementation of the Swing-up Pendulum for Deep Reinforcement Learning Experiments

链接: https://arxiv.org/abs/2503.11065
作者: Peter Böhm,Pauline Pounds,Archie C. Chapman
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO); Systems and Control (eess.SY)
*备注: Australasian Conference on Robotics and Automation (ACRA) 2022

点击查看摘要

[AI-28] raining Directional Locomotion for Quadrupedal Low-Cost Robotic Systems via Deep Reinforcement Learning

链接: https://arxiv.org/abs/2503.11059
作者: Peter Böhm,Archie C. Chapman,Pauline Pounds
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注: Australasian Conference on Robotics and Automation (ACRA) 2022

点击查看摘要

[AI-29] Distance-Based Tree-Sliced Wasserstein Distance

链接: https://arxiv.org/abs/2503.11050
作者: Hoang V. Tran,Khoi N.M. Nguyen,Trang Pham,Thanh T. Chu,Tam Le,Tan M. Nguyen
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-30] Measuring Similarity in Causal Graphs: A Framework for Semantic and Structural Analysis

链接: https://arxiv.org/abs/2503.11046
作者: Ning-Yuan Georgia Liu,Flower Yang,Mohammad S. Jalali
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 27 pages

点击查看摘要

[AI-31] Resource Constrained Pathfinding with A* and Negative Weights

链接: https://arxiv.org/abs/2503.11037
作者: Saman Ahmadi,Andrea Raith,Mahdi Jalili
类目: Artificial Intelligence (cs.AI)
*备注: 9 pages 2 figures 2 tables

点击查看摘要

[AI-32] From Abstraction to Reality: DARPAs Vision for Robust Sim-to-Real Autonomy

链接: https://arxiv.org/abs/2503.11007
作者: Erfaun Noorani,Zachary Serlin,Ben Price,Alvaro Velasquez
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA); Systems and Control (eess.SY)
*备注:

点击查看摘要

[AI-33] xAgent : An AI Agent for Therapeutic Reasoning Across a Universe of Tools

链接: https://arxiv.org/abs/2503.10970
作者: Shanghua Gao,Richard Zhu,Zhenglun Kong,Ayush Noori,Xiaorui Su,Curtis Ginder,Theodoros Tsiligkaridis,Marinka Zitnik
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: Project page: this https URL TxAgent code: this https URL ToolUniverse code: this https URL

点击查看摘要

[AI-34] Predicting Stock Movement with BERTweet and Transformers

链接: https://arxiv.org/abs/2503.10957
作者: Michael Charles Albada,Mojolaoluwa Joshua Sonola
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE)
*备注: 9 pages, 4 figures, 2 tables

点击查看摘要

[AI-35] Empirical Computation

链接: https://arxiv.org/abs/2503.10954
作者: Eric Tang,Marcel Böhme
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
*备注: Open challenges in the analysis of properties and limits of empirical computation

点击查看摘要

[AI-36] Safe Continual Domain Adaptation after Sim2Real Transfer of Reinforcement Learning Policies in Robotics

链接: https://arxiv.org/abs/2503.10949
作者: Josip Josifovski,Shangding Gu,Mohammadhossein Malmir,Haoliang Huang,Sayantan Auddy,Nicolás Navarro-Guerrero,Costas Spanos,Alois Knoll
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注: 8 pages, 5 figures, under review

点击查看摘要

[AI-37] (varepsilon δ) Considered Harmful: Best Practices for Reporting Differential Privacy Guarantees

链接: https://arxiv.org/abs/2503.10945
作者: Juan Felipe Gomez,Bogdan Kulynych,Georgios Kaissis,Jamie Hayes,Borja Balle,Antti Honkela
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Machine Learning (stat.ML)
*备注:

点击查看摘要

[AI-38] Graph-Grounded LLM s: Leverag LLM s: Leveraging Graphical Function Calling to Minimize LLM Hallucinations

链接: https://arxiv.org/abs/2503.10941
作者: Piyush Gupta,Sangjae Bae,David Isele
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Robotics (cs.RO)
*备注:

点击查看摘要

[AI-39] Predicting Clinical Outcomes with Waveform LSTMs

链接: https://arxiv.org/abs/2503.10925
作者: Michael Albada
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 7 pages,. arXiv admin note: text overlap with arXiv:1803.06589 by other authors

点击查看摘要

[AI-40] Resource Heterogeneity-Aware and Utilization-Enhanced Scheduling for Deep Learning Clusters

链接: https://arxiv.org/abs/2503.10918
作者: Abeda Sultana,Nabin Pakka,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: 14 pages, 12 figures, IEEE Transactions on Computers

点击查看摘要

[AI-41] Ecological Neural Architecture Search

链接: https://arxiv.org/abs/2503.10908
作者: Benjamin David Winter,William J. Teahan
类目: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI)
*备注: 5 pages, 4 figures

点击查看摘要

[AI-42] H2-MARL: Multi-Agent Reinforcement Learning for Pareto Optimality in Hospital Capacity Strain and Human Mobility during Epidemic

链接: https://arxiv.org/abs/2503.10907
作者: Xueting Luo,Hao Deng,Jihong Yang,Yao Shen,Huanhuan Guo,Zhiyuan Sun,Mingqing Liu,Jiming Wei,Shengjie Zhao
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
*备注:

点击查看摘要

[AI-43] ask-Specific Activation Functions for Neuroevolution using Grammatical Evolution

链接: https://arxiv.org/abs/2503.10879
作者: Benjamin David Winter,William John Teahan
类目: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI)
*备注: 8 pages, 4 figures, IEEE

点击查看摘要

[AI-44] Evaluating a Novel Neuroevolution and Neural Architecture Search System

链接: https://arxiv.org/abs/2503.10869
作者: Benjamin David Winter,William John Teahan
类目: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI)
*备注: 10 pages, 5 figures, IEEE

点击查看摘要

[AI-45] Rotated Bitboards in FUSc# and Reinforcement Learning in Computer Chess and Beyond

链接: https://arxiv.org/abs/2503.10822
作者: Johannes Buchner
类目: Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
*备注: 23 pages

点击查看摘要

[AI-46] Byzantine-Resilient Federated Learning via Distributed Optimization

链接: https://arxiv.org/abs/2503.10792
作者: Yufei Xia,Wenrui Yu,Qiongxiu Li
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-47] Vulnerability Detection: From Formal Verification to Large Language Models and Hybrid Approaches: A Comprehensive Overview

链接: https://arxiv.org/abs/2503.10784
作者: Norbert Tihanyi,Tamas Bisztray,Mohamed Amine Ferrag,Bilel Cherif,Richard A. Dubniczky,Ridhi Jain,Lucas C. Cordeiro
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-48] Predicting Treatment Response in Body Dysmorphic Disorder with Interpretable Machine Learning

链接: https://arxiv.org/abs/2503.10741
作者: Omar Costilla-Reyes,Morgan Talbot
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-49] Commenting Higher-level Code Unit: Full Code Reduced Code or Hierarchical Code Summarization

链接: https://arxiv.org/abs/2503.10737
作者: Weisong Sun,Yiran Zhang,Jie Zhu,Zhihui Wang,Chunrong Fang,Yonglong Zhang,Yebo Feng,Jiangping Huang,Xingya Wang,Zhi Jin,Yang Liu
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-50] OCPM2: Extending the Process Mining Methodology for Object-Centric Event Data Extraction

链接: https://arxiv.org/abs/2503.10735
作者: Najmeh Miri,Shahrzad Khayatbashi,Jelena Zdravkovic,Amin Jalali
类目: Databases (cs.DB); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-51] Samoyeds: Accelerating MoE Models with Structured Sparsity Leverag ing Sparse Tensor Cores

链接: https://arxiv.org/abs/2503.10725
作者: Chenpeng Wu,Qiqi Gu,Heng Shi,Jianguo Yao,Haibing Guan
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Operating Systems (cs.OS)
*备注:

点击查看摘要

[AI-52] acticExpert: Spatial-Temporal Graph Language Model for Basketball Tactics

链接: https://arxiv.org/abs/2503.10722
作者: Xu Lingrui,Liu Mandi,Zhang Lei
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-53] From Understanding to Excelling: Template-Free Algorithm Design through Structural-Functional Co-Evolution

链接: https://arxiv.org/abs/2503.10721
作者: Zhe Zhao,Haibin Wen,Pengkun Wang,Ye Wei,Zaixi Zhang,Xi Lin,Fei Liu,Bo An,Hui Xiong,Yang Wang,Qingfu Zhang
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-54] Estimating Control Barriers from Offline Data ICRA2025

链接: https://arxiv.org/abs/2503.10641
作者: Hongzhan Yu,Seth Farrell,Ryo Yoshimitsu,Zhizhen Qin,Henrik I. Christensen,Sicun Gao
类目: ystems and Control (eess.SY); Artificial Intelligence (cs.AI); Robotics (cs.RO)
*备注: This paper has been accepted to ICRA 2025

点击查看摘要

[AI-55] IMPACT: Intelligent Motion Planning with Acceptable Contact Trajectories via Vision-Language Models

链接: https://arxiv.org/abs/2503.10110
作者: Yiyang Ling,Karan Owalekar,Oluwatobiloba Adesanya,Erdem Bıyık,Daniel Seita
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-56] 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); Symbolic Computation (cs.SC); Systems and Control (eess.SY)
*备注:

点击查看摘要

[AI-57] Disentanglement Learning via Topology

链接: https://arxiv.org/abs/2308.12696
作者: Nikita Balabin,Daria Voronkova,Ilya Trofimov,Evgeny Burnaev,Serguei Barannikov
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Information Theory (cs.IT); Differential Geometry (math.DG)
*备注:

点击查看摘要

[AI-58] Device-Robust Acoustic Scene Classification via Impulse Response Augmentation

链接: https://arxiv.org/abs/2305.07499
作者: Tobias Morocutti,Florian Schmid,Khaled Koutini,Gerhard Widmer
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS)
*备注: In Proceedings of the 31st European Signal Processing Conference, EUSIPCO 2023. Source Code available at: this https URL

点击查看摘要

[AI-59] Enhancing Deep Learning Based Structured Illumination Microscopy Reconstruction with Light Field Awareness

链接: https://arxiv.org/abs/2503.11640
作者: Long-Kun Shan,Ze-Hao Wang,Tong-Tian Weng,Xiang-Dong Chen,Fang-Wen Sun
类目: Optics (physics.optics); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-60] Learning to reset in target search problems

链接: https://arxiv.org/abs/2503.11330
作者: Gorka Muñoz-Gil,Hans J. Briegel,Michele Caraglio
类目: atistical Mechanics (cond-mat.stat-mech); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Biological Physics (physics.bio-ph); Computational Physics (physics.comp-ph)
*备注:

点击查看摘要

[AI-61] AI and Deep Learning for Automated Segmentation and Quantitative Measurement of Spinal Structures in MRI

链接: https://arxiv.org/abs/2503.11281
作者: Praveen Shastry,Bhawana Sonawane,Kavya Mohan,Naveen Kumarasami,Anandakumar D,Keerthana R,Mounigasri M,Kaviya SP,Kishore Prasath Venkatesh,Bargava Subramanian,Kalyan Sivasailam
类目: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI)
*备注: 16 pages, 2 figures

点击查看摘要

[AI-62] Fourier Neural Operator based surrogates for CO_2 storag e in realistic geologies

链接: https://arxiv.org/abs/2503.11031
作者: Anirban Chandra,Marius Koch,Suraj Pawar,Aniruddha Panda,Kamyar Azizzadenesheli,Jeroen Snippe,Faruk O. Alpak,Farah Hariri,Clement Etienam,Pandu Devarakota,Anima Anandkumar,Detlef Hohl
类目: Computational Physics (physics.comp-ph); Artificial Intelligence (cs.AI); Geophysics (physics.geo-ph)
*备注:

点击查看摘要

[AI-63] he Problem of the Priors or Posteriors?

链接: https://arxiv.org/abs/2503.10984
作者: Hanti Lin
类目: Other Statistics (stat.OT); Artificial Intelligence (cs.AI); Probability (math.PR)
*备注:

点击查看摘要

机器学习

[LG-0] Are Deep Speech Denoising Models Robust to Adversarial Noise?

链接: https://arxiv.org/abs/2503.11627
作者: Will Schwarzer,Philip S. Thomas,Andrea Fanelli,Xiaoyu Liu
类目: ound (cs.SD); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS)
*备注: 13 pages, 5 figures

点击查看摘要

[LG-1] From Denoising Score Matching to Langevin Sampling: A Fine-Grained Error Analysis in the Gaussian Setting

链接: https://arxiv.org/abs/2503.11615
作者: Samuel Hurault,Matthieu Terris,Thomas Moreau,Gabriel Peyré
类目: Machine Learning (cs.LG); Optimization and Control (math.OC)
*备注: 38 pages

点击查看摘要

[LG-2] Enhanced Soups for Graph Neural Networks

链接: https://arxiv.org/abs/2503.11612
作者: Joseph Zuber,Aishwarya Sarkar,Joseph Jennings,Ali Jannesari
类目: Machine Learning (cs.LG)
*备注: 10 pages, 4 figures, 3 tables, accepted to GrAPL 2025 (colocated with IPDPS 2025)

点击查看摘要

[LG-3] Bottom-up Iterative Anomalous Diffusion Detector (BI-ADD)

链接: https://arxiv.org/abs/2503.11529
作者: Junwoo Park,Nataliya Sokolovska,Clément Cabriel,Ignacio Izeddin,Judith Miné-Hattab
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-4] A Review of DeepSeek Models Key Innovative Techniques

链接: https://arxiv.org/abs/2503.11486
作者: Chengen Wang,Murat Kantarcioglu
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-5] A Real-World Energy Management Dataset from a Smart Company Building for Optimization and Machine Learning

链接: https://arxiv.org/abs/2503.11469
作者: Jens Engel,Andrea Castellani,Patricia Wollstadt,Felix Lanfermann,Thomas Schmitt,Sebastian Schmitt,Lydia Fischer,Steffen Limmer,David Luttropp,Florian Jomrich,René Unger,Tobias Rodemann
类目: ystems and Control (eess.SY); Machine Learning (cs.LG)
*备注: 22 pages, 9 figures. Preprint submitted to Scientific Data

点击查看摘要

[LG-6] Dynamic Obstacle Avoidance with Bounded Rationality Adversarial Reinforcement Learning

链接: https://arxiv.org/abs/2503.11467
作者: Jose-Luis Holgado-Alvarez,Aryaman Reddi,Carlo D’Eramo
类目: Robotics (cs.RO); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-7] In Shift and In Variance: Assessing the Robustness of HAR Deep Learning Models against Variability

链接: https://arxiv.org/abs/2503.11466
作者: Azhar Ali Khaked,Nobuyuki Oishi,Daniel Roggen,Paula Lago
类目: Human-Computer Interaction (cs.HC); Machine Learning (cs.LG); Signal Processing (eess.SP)
*备注:

点击查看摘要

[LG-8] Make Optimization Once and for All with Fine-grained Guidance

链接: https://arxiv.org/abs/2503.11462
作者: Mingjia Shi,Ruihan Lin,Xuxi Chen,Yuhao Zhou,Zezhen Ding,Pingzhi Li,Tong Wang,Kai Wang,Zhangyang Wang,Jiheng Zhang,Tianlong Chen
类目: Machine Learning (cs.LG)
*备注: Preprint

点击查看摘要

[LG-9] Deep Learning Agents Trained For Avoidance Behave Like Hawks And Doves

链接: https://arxiv.org/abs/2503.11452
作者: Aryaman Reddi,Glenn Vinnicombe
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-10] D3: Diversity Difficulty and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning

链接: https://arxiv.org/abs/2503.11441
作者: Jia Zhang,Chen-Xi Zhang,Yao Liu,Yi-Xuan Jin,Xiao-Wen Yang,Bo Zheng,Yi Liu,Lan-Zhe Guo
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-11] FlowKac: An Efficient Neural Fokker-Planck solver using Temporal Normalizing flows and the Feynman Kac-Formula

链接: https://arxiv.org/abs/2503.11427
作者: Naoufal El Bekri,Lucas Drumetz,Franck Vermet
类目: Machine Learning (cs.LG); Dynamical Systems (math.DS); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-12] Classifying Long-tailed and Label-noise Data via Disentangling and Unlearning

链接: https://arxiv.org/abs/2503.11414
作者: Chen Shu,Mengke Li,Yiqun Zhang,Yang Lu,Bo Han,Yiu-ming Cheung,Hanzi Wang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-13] Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models

链接: https://arxiv.org/abs/2503.11411
作者: Xu Liu,Taha Aksu,Juncheng Liu,Qingsong Wen,Yuxuan Liang,Caiming Xiong,Silvio Savarese,Doyen Sahoo,Junnan Li,Chenghao Liu
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-14] Exploring Performance-Complexity Trade-Offs in Sound Event Detection

链接: https://arxiv.org/abs/2503.11373
作者: Tobias Morocutti,Florian Schmid,Jonathan Greif,Francesco Foscarin,Gerhard Widmer
类目: ound (cs.SD); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS)
*备注:

点击查看摘要

[LG-15] Creating a Good Teacher for Knowledge Distillation in Acoustic Scene Classification

链接: https://arxiv.org/abs/2503.11363
作者: Tobias Morocutti,Florian Schmid,Khaled Koutini,Gerhard Widmer
类目: ound (cs.SD); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS)
*备注:

点击查看摘要

[LG-16] Latent Space Representation of Electricity Market Curves for Improved Prediction Efficiency

链接: https://arxiv.org/abs/2503.11294
作者: Martin Výboh,Zuzana Chladná,Gabriela Grmanová,Mária Lucká
类目: Machine Learning (cs.LG)
*备注: Submitted to Applied Soft Computing

点击查看摘要

[LG-17] Brain Effective Connectivity Estimation via Fourier Spatiotemporal Attention

链接: https://arxiv.org/abs/2503.11283
作者: Wen Xiong,Jinduo Liu,Junzhong Ji,Fenglong Ma
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-18] OPTIMUS: Predicting Multivariate Outcomes in Alzheimers Disease Using Multi-modal Data amidst Missing Values

链接: https://arxiv.org/abs/2503.11282
作者: Christelle Schneuwly Diaz,Duy-Thanh Vu,Julien Bodelet,Duy-Cat Can,Guillaume Blanc,Haiting Jiang,Lin Yao,Guiseppe Pantaleo,ADNI,Oliver Y. Chén
类目: Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC)
*备注:

点击查看摘要

[LG-19] Permutation Equivariant Neural Networks for Symmetric Tensors

链接: https://arxiv.org/abs/2503.11276
作者: Edward Pearce-Crump
类目: Machine Learning (cs.LG); Combinatorics (math.CO); Representation Theory (math.RT); Machine Learning (stat.ML)
*备注: 22 pages

点击查看摘要

[LG-20] Federated Koopman-Reservoir Learning for Large-Scale Multivariate Time-Series Anomaly Detection SDM2025

链接: https://arxiv.org/abs/2503.11255
作者: Long Tan Le,Tung-Anh Nguyen,Han Shu,Suranga Seneviratne,Choong Seon Hong,Nguyen H. Tran
类目: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注: Accepted at SDM 2025

点击查看摘要

[LG-21] Cost-effective Deep Learning Infrastructure with NVIDIA GPU

链接: https://arxiv.org/abs/2503.11246
作者: Aatiz Ghimire,Shahnawaz Alam,Siman Giri,Madhav Prasad Ghimire
类目: Distributed, Parallel, and Cluster Computing (cs.DC); Hardware Architecture (cs.AR); Machine Learning (cs.LG); Software Engineering (cs.SE); Systems and Control (eess.SY)
*备注: 10 Pages,6 Figures, this paper was presented in National Data and Computing Conference 2024 and will be published into KUSET Journal by Kathmandu University

点击查看摘要

[LG-22] LLM Perf: GPU Performance Modeling meets Large Language Models

链接: https://arxiv.org/abs/2503.11244
作者: Khoi N.M. Nguyen,Hoang Duy Nguyen Do,Huyen Thao Le,Thanh Tuan Dao
类目: Performance (cs.PF); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-23] Addressing Information Loss and Interaction Collapse: A Dual Enhanced Attention Framework for Feature Interaction

链接: https://arxiv.org/abs/2503.11233
作者: Yi Xu,Zhiyuan Lu,Xiaochen Li,Jinxin Hu,Hong Wen,Zulong Chen,Yu Zhang,Jing Zhang
类目: Information Retrieval (cs.IR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-24] Optimal Transport and Adaptive Thresholding for Universal Domain Adaptation on Time Series

链接: https://arxiv.org/abs/2503.11217
作者: Romain Mussard,Fannia Pacheco,Maxime Berar,Gilles Gasso,Paul Honeine
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-25] Spatio-Temporal Graph Structure Learning for Earthquake Detection

链接: https://arxiv.org/abs/2503.11215
作者: Suchanun Piriyasatit,Ercan Engin Kuruoglu,Mehmet Sinan Ozeren
类目: Machine Learning (cs.LG)
*备注: 7 pages

点击查看摘要

[LG-26] Enabling Weak Client Participation via On-device Knowledge Distillation in Heterogenous Federated Learning

链接: https://arxiv.org/abs/2503.11151
作者: Jihyun Lim,Junhyuk Jo,Tuo Zhang,Salman Avestimehr,Sunwoo Lee
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-27] Asynchronous Sharpness-Aware Minimization For Fast and Accurate Deep Learning

链接: https://arxiv.org/abs/2503.11147
作者: Junhyuk Jo,Jihyun Lim,Sunwoo Lee
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-28] Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning

链接: https://arxiv.org/abs/2503.11146
作者: Jisoo Kim,Sungmin Kang,Sunwoo Lee
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-29] MUSS: Multilevel Subset Selection for Relevance and Diversity

链接: https://arxiv.org/abs/2503.11126
作者: Vu Nguyen,Andrey Kan
类目: Machine Learning (cs.LG)
*备注: 24 pages

点击查看摘要

[LG-30] Context-Aware Rule Mining Using a Dynamic Transformer-Based Framework

链接: https://arxiv.org/abs/2503.11125
作者: Jie Liu,Yiwei Zhang,Yuan Sheng,Yujia Lou,Haige Wang,Bohuan Yang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-31] Approximating the Total Variation Distance between Gaussians AISTATS2025

链接: https://arxiv.org/abs/2503.11099
作者: Arnab Bhattacharyya,Weiming Feng,Piyush Srivastava
类目: Data Structures and Algorithms (cs.DS); Machine Learning (cs.LG); Probability (math.PR)
*备注: Accepted by AISTATS 2025

点击查看摘要

[LG-32] Further Exploration of Precise Binding Energies from Physics Informed Machine Learning and the Development a Practical Ensemble Model

链接: https://arxiv.org/abs/2503.11066
作者: I. Bentley,J. Tedder,M. Gebran,A. Paul
类目: Machine Learning (cs.LG); Nuclear Theory (nucl-th)
*备注: Submitted to PRC for review

点击查看摘要

[LG-33] Generative Modelling for Mathematical Discovery

链接: https://arxiv.org/abs/2503.11061
作者: Jordan S. Ellenberg,Cristofero S. Fraser-Taliente,Thomas R. Harvey,Karan Srivastava,Andrew V. Sutherland
类目: Machine Learning (cs.LG); Combinatorics (math.CO)
*备注: 22 pages, 14 figures

点击查看摘要

[LG-34] InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences

链接: https://arxiv.org/abs/2503.11043
作者: Hongkai Zheng,Wenda Chu,Bingliang Zhang,Zihui Wu,Austin Wang,Berthy T. Feng,Caifeng Zou,Yu Sun,Nikola Kovachki,Zachary E. Ross,Katherine L. Bouman,Yisong Yue
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-35] Neural Tangent Kernel of Neural Networks with Loss Informed by Differential Operators

链接: https://arxiv.org/abs/2503.11029
作者: Weiye Gan,Yicheng Li,Qian Lin,Zuoqiang Shi
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-36] Residual Policy Gradient: A Reward View of KL-regularized Objective

链接: https://arxiv.org/abs/2503.11019
作者: Pengcheng Wang,Xinghao Zhu,Yuxin Chen,Chenfeng Xu,Masayoshi Tomizuka,Chenran Li
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-37] Crash Severity Analysis of Child Bicyclists using Arm-Net and MambaNet

链接: https://arxiv.org/abs/2503.11003
作者: Shriyank Somvanshi,Rohit Chakraborty,Subasish Das,Anandi K Dutta
类目: Machine Learning (cs.LG)
*备注: 4 pages, 6 figures, accepted at IEEE CAI 2025

点击查看摘要

[LG-38] Riemannian Geometric-based Meta Learning

链接: https://arxiv.org/abs/2503.10993
作者: JuneYoung Park,YuMi Lee,Tae-Joon Kim,Jang-Hwan Choi
类目: Machine Learning (cs.LG)
*备注: 9 pages

点击查看摘要

[LG-39] Statistical Impossibility and Possibility of Aligning LLM s with Human Preferences: From Condorcet Paradox to Nash Equilibrium

链接: https://arxiv.org/abs/2503.10990
作者: Kaizhao Liu,Qi Long,Zhekun Shi,Weijie J. Su,Jiancong Xiao
类目: Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG); Theoretical Economics (econ.TH); Statistics Theory (math.ST); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-40] From Dionysius Emerges Apollo – Learning Patterns and Abstractions from Perceptual Sequences

链接: https://arxiv.org/abs/2503.10973
作者: Shuchen Wu
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-41] FedOSAA: Improving Federated Learning with One-Step Anderson Acceleration

链接: https://arxiv.org/abs/2503.10961
作者: Xue Feng(University of California, Davis),M. Paul Laiu(Oak Ridge National Laboratory),Thomas Strohmer(University of California, Davis)
类目: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注:

点击查看摘要

[LG-42] Phishsense-1B: A Technical Perspective on an AI-Powered Phishing Detection Model

链接: https://arxiv.org/abs/2503.10944
作者: SE Blake
类目: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
*备注: Phishing Detection Model this https URL

点击查看摘要

[LG-43] owards Efficient Large Scale Spatial-Temporal Time Series Forecasting via Improved Inverted Transformers

链接: https://arxiv.org/abs/2503.10858
作者: Jiarui Sun,Chin-Chia Michael Yeh,Yujie Fan,Xin Dai,Xiran Fan,Zhimeng Jiang,Uday Singh Saini,Vivian Lai,Junpeng Wang,Huiyuan Chen,Zhongfang Zhuang,Yan Zheng,Girish Chowdhary
类目: Machine Learning (cs.LG)
*备注: 10 pages

点击查看摘要

[LG-44] Panopticon: Advancing Any-Sensor Foundation Models for Earth Observation

链接: https://arxiv.org/abs/2503.10845
作者: Leonard Waldmann,Ando Shah,Yi Wang,Nils Lehmann,Adam J. Stewart,Zhitong Xiong,Xiao Xiang Zhu,Stefan Bauer,John Chuang
类目: Machine Learning (cs.LG)
*备注: First two authors contributed equally. Code is available at: this https URL

点击查看摘要

[LG-45] Attacking Multimodal OS Agents with Malicious Image Patches

链接: https://arxiv.org/abs/2503.10809
作者: Lukas Aichberger,Alasdair Paren,Yarin Gal,Philip Torr,Adel Bibi
类目: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-46] Fixed-Point RNNs: From Diagonal to Dense in a Few Iterations

链接: https://arxiv.org/abs/2503.10799
作者: Sajad Movahedi,Felix Sarnthein,Nicola Muca Cirone,Antonio Orvieto
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-47] Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation CVPR2025

链接: https://arxiv.org/abs/2503.10743
作者: Qi Lv,Hao Li,Xiang Deng,Rui Shao,Yinchuan Li,Jianye Hao,Longxiang Gao,Michael Yu Wang,Liqiang Nie
类目: Robotics (cs.RO); Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: Accepted by CVPR 2025

点击查看摘要

[LG-48] AU: Modeling Temporal Consistency Through Temporal Attentive U-Net for PPG Peak Detection

链接: https://arxiv.org/abs/2503.10733
作者: Chunsheng Zuo,Yu Zhao,Juntao Ye
类目: Machine Learning (cs.LG); Signal Processing (eess.SP)
*备注: 27 pages, submitted to a journal

点击查看摘要

[LG-49] Numerical and statistical analysis of NeuralODE with Runge-Kutta time integration

链接: https://arxiv.org/abs/2503.10729
作者: Emily C. Ehrhardt,Hanno Gottschalk,Tobias J. Riedlinger
类目: Machine Learning (cs.LG); Classical Analysis and ODEs (math.CA); Numerical Analysis (math.NA); Probability (math.PR)
*备注: 29 pages

点击查看摘要

[LG-50] Prototype-Guided Cross-Modal Knowledge Enhancement for Adaptive Survival Prediction

链接: https://arxiv.org/abs/2503.10726
作者: Fengchun Liu,Linghan Cai,Zhikang Wang,Zhiyuan Fan,Jin-gang Yu,Hao Chen,Yongbing Zhang
类目: Machine Learning (cs.LG); Image and Video Processing (eess.IV)
*备注:

点击查看摘要

[LG-51] Real-time Pollutant Identification through Optical PM Micro-Sensor

链接: https://arxiv.org/abs/2503.10724
作者: Elie Azeraf,Audrey Wagner,Emilie Bialic,Samia Mellah,Ludovic Lelandais
类目: Machine Learning (cs.LG); Signal Processing (eess.SP)
*备注: 11 pages, 4 figures

点击查看摘要

[LG-52] NeuMC – a package for neural sampling for lattice field theories

链接: https://arxiv.org/abs/2503.11482
作者: Piotr Bialas,Piotr Korcyl,Tomasz Stebel,Dawid Zapolski
类目: High Energy Physics - Lattice (hep-lat); Machine Learning (cs.LG)
*备注: 42 pages, 15 figures, for associated code repository, see this https URL

点击查看摘要

[LG-53] Integrating Dynamical Systems Modeling with Spatiotemporal scRNA-seq Data Analysis

链接: https://arxiv.org/abs/2503.11347
作者: Zhenyi Zhang,Yuhao Sun,Qiangwei Peng,Tiejun Li,Peijie Zhou
类目: Quantitative Methods (q-bio.QM); Machine Learning (cs.LG); Biological Physics (physics.bio-ph)
*备注:

点击查看摘要

[LG-54] Lightweight Learning for Grant-Free Activity Detection in Cell-Free Massive MIMO Networks

链接: https://arxiv.org/abs/2503.11305
作者: Ali Elkeshawy,Haifa Fares,Amor Nafkha
类目: ignal Processing (eess.SP); Machine Learning (cs.LG)
*备注: arXiv admin note: text overlap with arXiv:2406.07160

点击查看摘要

[LG-55] When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective

链接: https://arxiv.org/abs/2503.11272
作者: Alireza Mousavi-Hosseini,Clayton Sanford,Denny Wu,Murat A. Erdogdu
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: 43 pages, 2 figures

点击查看摘要

[LG-56] CRPS-Based Targeted Sequential Design with Application in Chemical Space

链接: https://arxiv.org/abs/2503.11250
作者: Lea Friedli,Athénaïs Gautier,Anna Broccard,David Ginsbourger
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Applications (stat.AP); Computation (stat.CO)
*备注:

点击查看摘要

[LG-57] Clustering Items through Bandit Feedback: Finding the Right Feature out of Many

链接: https://arxiv.org/abs/2503.11209
作者: Maximilian Graf,Victor Thuot(MISTEA),Nicolas Verzelen(MISTEA)
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-58] Physics-constrained DeepONet for Surrogate CFD models: a curved backward-facing step case

链接: https://arxiv.org/abs/2503.11196
作者: Anas Jnini,Harshinee Goordoyal,Sujal Dave,Flavio Vella,Katharine H. Fraser,Artem Korobenko
类目: Fluid Dynamics (physics.flu-dyn); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-59] MobiVital: Self-supervised Time-series Quality Estimation for Contactless Respiration Monitoring Using UWB Radar

链接: https://arxiv.org/abs/2503.11064
作者: Ziqi Wang,Derek Hua,Wenjun Jiang,Tianwei Xing,Xun Chen,Mani Srivastava
类目: ignal Processing (eess.SP); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-60] Mamba time series forecasting with uncertainty propagation

链接: https://arxiv.org/abs/2503.10873
作者: Pedro Pessoa,Paul Campitelli,Douglas P. Shepherd,S. Banu Ozkan,Steve Pressé
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Chaotic Dynamics (nlin.CD)
*备注:

点击查看摘要

[LG-61] Efficient Reachability Analysis for Convolutional Neural Networks Using Hybrid Zonotopes

链接: https://arxiv.org/abs/2503.10840
作者: Yuhao Zhang,Xiangru Xu
类目: Optimization and Control (math.OC); Machine Learning (cs.LG); Systems and Control (eess.SY)
*备注: Accepted by 2025 American Control Conference (ACC). 8 pages, 1 figure

点击查看摘要

[LG-62] Lessons from the trenches on evaluating machine-learning systems in materials science

链接: https://arxiv.org/abs/2503.10837
作者: Nawaf Alampara,Mara Schilling-Wilhelmi,Kevin Maik Jablonka
类目: Materials Science (cond-mat.mtrl-sci); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-63] Exploiting Concavity Information in Gaussian Process Contextual Bandit Optimization

链接: https://arxiv.org/abs/2503.10836
作者: Kevin Li,Eric Laber
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-64] On the Identifiability of Causal Abstractions AISTATS2025

链接: https://arxiv.org/abs/2503.10834
作者: Xiusi Li,Sékou-Oumar Kaba,Siamak Ravanbakhsh
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: 15 pages, 4 figures, published in AISTATS 2025

点击查看摘要

[LG-65] Learn then Decide: A Learning Approach for Designing Data Marketplaces

链接: https://arxiv.org/abs/2503.10773
作者: Yingqi Gao,Jin Zhou,Hua Zhou,Yong Chen,Xiaowu Dai
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-66] Exploration of Hepatitis B Virus Infection Dynamics through Virology-Informed Neural Network: A Novel Artificial Intelligence Approach

链接: https://arxiv.org/abs/2503.10708
作者: Bikram Das,Rupchand Sutradhar,D C Dalal
类目: Quantitative Methods (q-bio.QM); Machine Learning (cs.LG)
*备注:

点击查看摘要

信息检索

[IR-0] Variational Bayesian Personalized Ranking

链接: https://arxiv.org/abs/2503.11067
作者: Bin Liu,Xiaohong Liu,Qin Luo,Ziqiao Shang,Jielei Chu,Lin Ma,Zhaoyu Li,Fei Teng,Guangtao Zhai,Tianrui Li
类目: Information Retrieval (cs.IR)
*备注: 15 pages

点击查看摘要

附件下载

点击下载今日全部论文列表

Arxiv今日论文 | 2025-03-17

目录

概览 (2025-03-17)

自然语言处理

计算机视觉

人工智能

机器学习

信息检索

附件下载