Arxiv今日论文 | 2025-04-22

本篇博文主要内容为 2025-04-22 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/2504.15280
作者: Chun-Hsiao Yeh,Chenyu Wang,Shengbang Tong,Ta-Ying Cheng,Rouyu Wang,Tianzhe Chu,Yuexiang Zhai,Yubei Chen,Shenghua Gao,Yi Ma
机构: UC Berkeley (加州大学伯克利分校); TranscEngram; NYU (纽约大学); University of Oxford (牛津大学); UC Davis (加州大学戴维斯分校); HKU (香港大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注: Project page: this https URL

点击查看摘要

[NLP-1] An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes

链接: https://arxiv.org/abs/2504.15270
作者: Ji Qi,Yuan Yao,Yushi Bai,Bin Xu,Juanzi Li,Zhiyuan Liu,Tat-Seng Chua
机构: Tsinghua University (清华大学); National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-2] Roll the dice look before you leap: Going beyond the creative limits of next-token prediction

链接: https://arxiv.org/abs/2504.15266
作者: Vaishnavh Nagarajan,Chen Henry Wu,Charles Ding,Aditi Raghunathan
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 37 pages

点击查看摘要

[NLP-3] CRUST-Bench: A Comprehensive Benchmark for C-to-safe-Rust Transpilation

链接: https://arxiv.org/abs/2504.15254
作者: Anirudh Khatry,Robert Zhang,Jia Pan,Ziteng Wang,Qiaochu Chen,Greg Durrett,Isil Dillig
机构: The University of Texas at Austin; New York University
类目: oftware Engineering (cs.SE); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-4] Evaluating Judges as Evaluators: The JETTS Benchmark of LLM -as-Judges as Test-Time Scaling Evaluators

链接: https://arxiv.org/abs/2504.15253
作者: Yilun Zhou,Austin Xu,Peifeng Wang,Caiming Xiong,Shafiq Joty
机构: 未知
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: The first two authors contributed equally. The codebase is at this https URL

点击查看摘要

[NLP-5] MR. Guard: Multilingual Reasoning Guardrail using Curriculum Learning

链接: https://arxiv.org/abs/2504.15241
作者: Yahan Yang,Soham Dan,Shuo Li,Dan Roth,Insup Lee
机构: University of Pennsylvania (宾夕法尼亚大学); Microsoft (微软)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-6] Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions

链接: https://arxiv.org/abs/2504.15236
作者: Saffron Huang,Esin Durmus,Miles McCain,Kunal Handa,Alex Tamkin,Jerry Hong,Michael Stern,Arushi Somani,Xiuruo Zhang,Deep Ganguli
机构: Anthropic
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG)
备注: 44 pages

点击查看摘要

[NLP-7] Fully Bayesian Approaches to Topics over Time

链接: https://arxiv.org/abs/2504.15220
作者: Julián Cendrero,Julio Gonzalo,Ivar Zapata
机构: 未知
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: 25 pages

点击查看摘要

[NLP-8] EvalAgent : Discovering Implicit Evaluation Criteria from the Web

链接: https://arxiv.org/abs/2504.15219
作者: Manya Wadhwa,Zayne Sprague,Chaitanya Malaviya,Philippe Laban,Junyi Jessy Li,Greg Durrett
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-9] Support Evaluation for the TREC 2024 RAG Track: Comparing Human versus LLM Judges SIGIR2025

链接: https://arxiv.org/abs/2504.15205
作者: Nandan Thakur,Ronak Pradeep,Shivani Upadhyay,Daniel Campos,Nick Craswell,Jimmy Lin
机构: University of Waterloo (滑铁卢大学); Snowflake; Microsoft
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
备注: Accepted at SIGIR 2025 (short)

点击查看摘要

[NLP-10] On true empty category

链接: https://arxiv.org/abs/2504.15168
作者: Qilin Tian
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-11] he Synthetic Imputation Approach: Generating Optimal Synthetic Texts For Underrepresented Categories In Supervised Classification Tasks

链接: https://arxiv.org/abs/2504.15160
作者: Joan C. Timoneda
机构: Purdue University (普渡大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-12] KGMEL: Knowledge Graph-Enhanced Multimodal Entity Linking SIGIR2025

链接: https://arxiv.org/abs/2504.15135
作者: Juyeon Kim,Geon Lee,Taeuk Kim,Kijung Shin
机构: KAIST(韩国科学技术院)(首尔, 大韩民国); Hanyang University(汉阳大学)(首尔, 大韩民国); KAIST(韩国科学技术院)(首尔, 大韩民国); KAIST(韩国科学技术院)(首尔, 大韩民国)
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: SIGIR 2025 (Short)

点击查看摘要

[NLP-13] EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models

链接: https://arxiv.org/abs/2504.15133
作者: Ziwen Xu,Shuxun Wang,Kewei Xu,Haoming Xu,Mengru Wang,Xinle Deng,Yunzhi Yao,Guozhou Zheng,Huajun Chen,Ningyu Zhang
机构: Zhejiang University (浙江大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
备注: Work in progress. Demo: this https URL code: this https URL

点击查看摘要

[NLP-14] Kuwain 1.5B: An Arabic SLM via Language Injection

链接: https://arxiv.org/abs/2504.15120
作者: Khalil Hennara,Sara Chrouf,Mohamed Motaism Hamed,Zeina Aldallal,Omar Hadid,Safwan AlModhayan
机构: misraj.ai(米斯拉杰人工智能研究所)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-15] Rethinking the Potential of Multimodality in Collaborative Problem Solving Diagnosis with Large Language Models

链接: https://arxiv.org/abs/2504.15093
作者: K. Wong,B. Wu,S. Bulathwela,M. Cukurova
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Accepted for 26th International Conference on Artificial Intelligence in Education (AIED 2025), 22 - 26 July 2025, Palermo, Italy. 17 pages, 1 figure

点击查看摘要

[NLP-16] Rhythm of Opinion: A Hawkes-Graph Framework for Dynamic Propagation Analysis

链接: https://arxiv.org/abs/2504.15072
作者: Yulong Li,Zhixiang Lu,Feilong Tang,Simin Lai,Ming Hu,Yuxuan Zhang,Haochen Xue,Zhaodong Wu,Imran Razzak,Qingxia Li,Jionglong Su
机构: School of Artificial Intelligence and Advanced Computing, Xi’an Jiaotong-Liverpool University (西安交通大学利物浦大学人工智能与先进计算学院); Mohamed bin Zayed University of Artificial Intelligence (穆罕默德·本·扎耶德人工智能大学); Monash University (蒙纳士大学); Fisk University (菲斯克大学)
类目: ocial and Information Networks (cs.SI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-17] he Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language Models SIGIR2025 DATE

链接: https://arxiv.org/abs/2504.15068
作者: Ronak Pradeep,Nandan Thakur,Shivani Upadhyay,Daniel Campos,Nick Craswell,Jimmy Lin
机构: University of Waterloo (滑铁卢大学); Snowflake (Snowflake); Microsoft (微软); University of Waterloo (滑铁卢大学)
类目: Information Retrieval (cs.IR); Computation and Language (cs.CL)
备注: To appear in SIGIR 2025. Significant updates and revisions to arXiv:2411.09607

点击查看摘要

[NLP-18] sting LLM s Capabilities in Annotating Translations Based on an Error Typology Designed for LSP Translation: First Experiments with ChatGPT

链接: https://arxiv.org/abs/2504.15052
作者: Joachim Minder,Guillaume Wisniewski,Natalie Kübler
机构: Université Paris Cité (巴黎城市大学); CNRS (法国国家科学研究中心)
类目: Computation and Language (cs.CL); Audio and Speech Processing (eess.AS)
备注: Accepted for publication in the proceedings of MT Summit 2025

点击查看摘要

[NLP-19] RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search

链接: https://arxiv.org/abs/2504.15047
作者: Quy-Anh Dang,Chris Ngo,Truong-Son Hy
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-20] DistilQwen 2.5: Industrial Practices of Training Distilled Open Lightweight Language Models

链接: https://arxiv.org/abs/2504.15027
作者: Chengyu Wang,Junbing Yan,Yuanhao Yue,Jun Huang
机构: Alibaba Cloud Computing (阿里云)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-21] LLM s as Data Annotators: How Close Are We to Human Performance

链接: https://arxiv.org/abs/2504.15022
作者: Muhammad Uzair Ul Haq,Davide Rigoni,Alessandro Sperduti
机构: 未知
类目: Computation and Language (cs.CL)
备注: 27 pages, 4 figures

点击查看摘要

[NLP-22] Stay Hungry Stay Foolish: On the Extended Reading Articles Generation with LLM s AAAI2025

链接: https://arxiv.org/abs/2504.15013
作者: Yow-Fu Liou,Yu-Chien Tang,An-Zi Yen
机构: National Yang Ming Chiao Tung University (国立阳明交通大学)
类目: Computation and Language (cs.CL)
备注: Accepted by iRAISE@AAAI2025

点击查看摘要

[NLP-23] Efficient Pretraining Length Scaling

链接: https://arxiv.org/abs/2504.14992
作者: Bohong Wu,Shen Yan,Sijun Zhang,Jianqiao Lu,Yutao Zeng,Ya Wang,Xun Zhou
机构: ByteDance (字节跳动)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-24] Evaluating LLM s on Chinese Topic Constructions: A Research Proposal Inspired by Tian et al. (2024)

链接: https://arxiv.org/abs/2504.14969
作者: Xiaodong Yang
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-25] Speaker Fuzzy Fingerprints: Benchmarking Text-Based Identification in Multiparty Dialogues

链接: https://arxiv.org/abs/2504.14963
作者: Rui Ribeiro,Luísa Coheur,Joao P. Carvalho
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
备注: Paper accepted at the FUZZY IEEE 2025 conference

点击查看摘要

[NLP-26] Learning to Reason under Off-Policy Guidance

链接: https://arxiv.org/abs/2504.14945
作者: Jianhao Yan,Yafu Li,Zican Hu,Zhi Wang,Ganqu Cui,Xiaoye Qu,Yu Cheng,Yue Zhang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Work in progress

点击查看摘要

[NLP-27] EducationQ: Evaluating LLM s Teaching Capabilities Through Multi-Agent Dialogue Framework

链接: https://arxiv.org/abs/2504.14928
作者: Yao Shi,Rongkeng Liang,Yong Xu
机构: South China University of Technology (华南理工大学); Education Innovation Research Institute of Guangdong (广东教育创新研究院)
类目: Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Computation and Language (cs.CL); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC)
备注:

点击查看摘要

[NLP-28] CRAVE: A Conflicting Reasoning Approach for Explainable Claim Verification Using LLM s

链接: https://arxiv.org/abs/2504.14905
作者: Yingming Zheng,Xiaoliang Liu,Peng Wu,Li Pan
机构: School of Computer Science, Shanghai Jiao Tong University (上海交通大学计算机学院), Shanghai, China; Shanghai KEY Laboratory of Integrated Administration Technologies for Information Security (上海市信息安全综合管理技术重点实验室), Shanghai, China; School of Politics, National Defense University (国防大学政治学院), Shanghai, China
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-29] VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform

链接: https://arxiv.org/abs/2504.14904
作者: Xingyu Lu,Tianke Zhang,Chang Meng,Xiaobei Wang,Jinpeng Wang,YiFan Zhang,Shisong Tang,Changyi Liu,Haojie Ding,Kaiyu Jiang,Kaiyu Tang,Bin Wen,Hai-Tao Zheng,Fan Yang,Tingting Gao,Di Zhang,Kun Gai
机构: 未知
类目: ocial and Information Networks (cs.SI); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multimedia (cs.MM)
备注: 20 pages, 6 figures

点击查看摘要

[NLP-30] Retrieval Augmented Generation Evaluation in the Era of Large Language Models : A Comprehensive Survey

链接: https://arxiv.org/abs/2504.14891
作者: Aoran Gan,Hao Yu,Kai Zhang,Qi Liu,Wenyu Yan,Zhenya Huang,Shiwei Tong,Guoping Hu
机构: State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China (中国科学技术大学); McGill University (麦吉尔大学); Tencent Company (腾讯); Artificial Intelligence Research Institute, iFLYTEK Co., Ltd (科大讯飞人工智能研究院)
类目: Computation and Language (cs.CL)
备注: 18 pages, 5 figures

点击查看摘要

[NLP-31] Natural Fingerprints of Large Language Models

链接: https://arxiv.org/abs/2504.14871
作者: Teppei Suzuki,Ryokan Ri,Sho Takase
机构: SB Intuitions (SB Intuitions)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-32] OTC: Optimal Tool Calls via Reinforcement Learning

链接: https://arxiv.org/abs/2504.14870
作者: Hongru Wang,Cheng Qian,Wanjun Zhong,Xiusi Chen,Jiahao Qiu,Shijue Huang,Bowen Jin,Mengdi Wang,Kam-Fai Wong,Heng Ji
机构: The Chinese University of Hong Kong (香港中文大学); University of Illinois Urbana-Champaign (伊利诺伊大学香槟分校); Princeton University (普林斯顿大学); Sun Yat-sen University (中山大学); Hong Kong University of Science and Technology (香港科技大学)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-33] AlignRAG : An Adaptable Framework for Resolving Misalignments in Retrieval-Aware Reasoning of RAG

链接: https://arxiv.org/abs/2504.14858
作者: Jiaqi Wei,Hao Zhou,Xiang Zhang,Di Zhang,Zijie Qiu,Wei Wei,Jinzhe Li,Wanli Ouyang,Siqi Sun
机构: Zhejiang University (浙江大学); Shanghai Artificial Intelligence Laboratory (上海人工智能实验室); South China University of Technology (华南理工大学); University of British Columbia (不列颠哥伦比亚大学); Fudan University (复旦大学); University of Hong Kong (香港大学)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-34] ransparentize the Internal and External Knowledge Utilization in LLM s with Trustworthy Citation

链接: https://arxiv.org/abs/2504.14856
作者: Jiajun Shen,Tong Zhou,Yubo Chen,Delai Qiu,Shengping Liu,Kang Liu,Jun Zhao
机构: The Key Laboratory of Cognition and Decision Intelligence for Complex Systems (认知与决策智能重点实验室), Institute of Automation, Chinese Academy of Sciences (中国科学院自动化研究所); School of Artificial Intelligence, University of Chinese Academy of Sciences (中国科学院大学人工智能学院); Unisound Al Technology Co,Ltd (未正确解析公司名); Shanghai Artificial Intelligence Laboratory (上海人工智能实验室)
类目: Computation and Language (cs.CL)
备注: 19 pages, 14 figures

点击查看摘要

[NLP-35] Completing A Systematic Review in Hours instead of Months with Interactive AI Agents

链接: https://arxiv.org/abs/2504.14822
作者: Rui Qiu,Shijie Chen,Yu Su,Po-Yin Yen,Han-Wei Shen
机构: The Ohio State University (俄亥俄州立大学); Washington University School of Medicine (华盛顿大学医学院)
类目: Human-Computer Interaction (cs.HC); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-36] On Self-improving Token Embeddings

链接: https://arxiv.org/abs/2504.14808
作者: Mario M. Kubek,Shiraj Pokharel,Thomas Böhme,Emma L. McDaniel,Herwig Unger,Armin R. Mikler
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG)
备注: 18 pages, 4 figures, 3 tables, accepted at the 2025 25th International Conference on Innovations for Community Services (I4CS), June 11 - 13, Munich, Germany, 2025

点击查看摘要

[NLP-37] Automatic Evaluation Metrics for Document-level Translation: Overview Challenges and Trends

链接: https://arxiv.org/abs/2504.14804
作者: Jiaxin GUO,Xiaoyu Chen,Zhiqiang Rao,Jinlong Yang,Zongyao Li,Hengchao Shang,Daimeng Wei,Hao Yang
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-38] PLANET: A Collection of Benchmarks for Evaluating LLM s Planning Capabilities

链接: https://arxiv.org/abs/2504.14773
作者: Haoming Li,Zhaoliang Chen,Jonathan Zhang,Fei Liu
机构: Computer Science Department, Emory University (埃默里大学计算机科学系)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
备注: 10 pages

点击查看摘要

[NLP-39] Knowledge Distillation and Dataset Distillation of Large Language Models : Emerging Trends Challenges and Future Directions

链接: https://arxiv.org/abs/2504.14772
作者: Luyang Fang,Xiaowei Yu,Jiazhang Cai,Yongkai Chen,Shushan Wu,Zhengliang Liu,Zhenyuan Yang,Haoran Lu,Xilin Gong,Yufang Liu,Terry Ma,Wei Ruan,Ali Abbasi,Jing Zhang,Tao Wang,Ehsan Latif,Wei Liu,Wei Zhang,Soheil Kolouri,Xiaoming Zhai,Dajiang Zhu,Wenxuan Zhong,Tianming Liu,Ping Ma
机构: Department of Statistics, University of Georgia, GA, USA (统计系，佐治亚大学，美国佐治亚州); Department of Computer Science and Engineering, The University of Texas at Arlington, TX, USA (计算机科学与工程系，德克萨斯大学阿灵顿分校，美国德克萨斯州); School of Computing, University of Georgia, GA, USA (计算学院，佐治亚大学，美国佐治亚州); Department of Computer Science, Vanderbilt University, TN, USA (计算机科学系，范德比尔特大学，美国田纳西州); School of Computer Science, Carnegie Mellon University, PA, USA (卡内基梅隆大学计算机科学学院，美国宾夕法尼亚州); Department of Radiation Oncology, Mayo Clinic Arizona, AZ, USA (放射肿瘤科，梅奥诊所亚利桑那州分部，美国亚利桑那州); School of Computer and Cyber Sciences, Augusta University, GA, USA (计算机与网络科学学院，奥古斯塔大学，美国佐治亚州); AI4STEM Education Center, University of Georgia, GA, USA (AI4STEM教育中心，佐治亚大学，美国佐治亚州); Department of Computer Science and Engineering, The University of Texas at Arlington, TX, USA (计算机科学与工程系，德克萨斯大学阿灵顿分校，美国德克萨斯州)
类目: Computation and Language (cs.CL); Machine Learning (cs.LG); Machine Learning (stat.ML)
备注:

点击查看摘要

[NLP-40] Disentangling Linguistic Features with Dimension-Wise Analysis of Vector Embeddings

链接: https://arxiv.org/abs/2504.14766
作者: Saniya Karwa,Navpreet Singh
机构: Massachusetts Institute of Technology (麻省理工学院)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-41] PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines NAACL2025

链接: https://arxiv.org/abs/2504.14738
作者: Reya Vir,Shreya Shankar,Harrison Chase,Will Fu-Hinthorn,Aditya Parameswaran
机构: UC Berkeley (加州大学伯克利分校); LangChain; UC Berkeley (加州大学伯克利分校)
类目: Computation and Language (cs.CL)
备注: Accepted to NAACL 2025 Main Conference

点击查看摘要

[NLP-42] Evaluating BERTopic on Open-Ended Data: A Case Study with Belgian Dutch Daily Narratives

链接: https://arxiv.org/abs/2504.14707
作者: Ratna Kandala,Katie Hoemann
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-43] OmniV-Med: Scaling Medical Vision-Language Model for Universal Visual Understanding

链接: https://arxiv.org/abs/2504.14692
作者: Songtao Jiang,Yuan Wang,Sibo Song,Yan Zhang,Zijie Meng,Bohan Lei,Jian Wu,Jimeng Sun,Zuozhu Liu
机构: Zhejiang University (浙江大学); Alibaba Group (阿里巴巴集团); UIUC (伊利诺伊大学香槟分校)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-44] FarsEval-PKBETS: A new diverse benchmark for evaluating Persian large language models

链接: https://arxiv.org/abs/2504.14690
作者: Mehrnoush Shamsfard,Zahra Saaberi,Mostafa Karimi manesh,Seyed Mohammad Hossein Hashemi,Zahra Vatankhah,Motahareh Ramezani,Niki Pourazin,Tara Zare,Maryam Azimi,Sarina Chitsaz,Sama Khoraminejad,Morteza Mahdavi Mortazavi,Mohammad Mahdi Chizari,Sahar Maleki,Seyed Soroush Majd,Mostafa Masumi,Sayed Ali Musavi Khoeini,Amir Mohseni,Sogol Alipour
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 24 pages, 3 figures, 3 tables

点击查看摘要

[NLP-45] rans-Zero: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data

链接: https://arxiv.org/abs/2504.14669
作者: Wei Zou,Sen Yang,Yu Bao,Shujian Huang,Jiajun Chen,Shanbo Cheng
机构: National Key Laboratory for Novel Software Technology, Nanjing University (国家软件新技术重点实验室，南京大学); ByteDance Research (字节跳动研究部)
类目: Computation and Language (cs.CL)
备注: 11 pages, 4 figures

点击查看摘要

[NLP-46] A Case Study Exploring the Current Landscape of Synthetic Medical Record Generation with Commercial LLM s ALT

链接: https://arxiv.org/abs/2504.14657
作者: Yihan Lin,Zhirong Bella Yu,Simon Lee
机构: Department of Computer Science (计算机科学系), University of California, Los Angeles (加州大学洛杉矶分校); Bioinformatics IDP (生物信息学 IDP), University of California, Los Angeles (加州大学洛杉矶分校); Department of Computational Medicine (计算医学系), University of California, Los Angeles (加州大学洛杉矶分校)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Accepted at the Conference of Health, Inference, Learning (CHIL 2025) in Berkeley, CA. To appear in PMLR later in 2025

点击查看摘要

[NLP-47] LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLM s

链接: https://arxiv.org/abs/2504.14655
作者: Yunhui Xia,Wei Shen,Yan Wang,Jason Klein Liu,Huifeng Sun,Siyue Wu,Jian Hu,Xiaolong Xu
机构: 未知
类目: Machine Learning (cs.LG); Computation and Language (cs.CL); Software Engineering (cs.SE)
备注:

点击查看摘要

[NLP-48] Risk Assessment Framework for Code LLM s via Leverag ing Internal States

链接: https://arxiv.org/abs/2504.14640
作者: Yuheng Huang,Lei Ma,Keizaburo Nishikino,Takumi Akazaki
机构: The University of Tokyo (东京大学); University of Alberta (阿尔伯塔大学); Fujitsu Limited (富士通有限公司); Fujitsu Limited (富士通有限公司)
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: To appear in the 33rd ACM International Conference on the Foundations of Software Engineering (FSE Companion’25 Industry Track), June 23-28, 2025, Trondheim, Norway. This work was supported by Fujitsu Limited

点击查看摘要

[NLP-49] Harnessing Generative LLM s for Enhanced Financial Event Entity Extraction Performance

链接: https://arxiv.org/abs/2504.14633
作者: Soo-joon Choi,Ji-jun Park
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-50] Automatic Text Summarization (ATS) for Research Documents in Sorani Kurdish

链接: https://arxiv.org/abs/2504.14630
作者: Rondik Hadi Abdulrahman,Hossein Hassani
机构: 未知
类目: Computation and Language (cs.CL)
备注: 18 pages, 11 figures, 8 tables

点击查看摘要

[NLP-51] A Hierarchical Framework for Measuring Scientific Paper Innovation via Large Language Models

链接: https://arxiv.org/abs/2504.14620
作者: Hongming Tan,Shaoxiong Zhan,Fengwei Jia,Hai-Tao Zheng,Wai Kin Chan
机构: Shenzhen International Graduate School, Tsinghua University (清华大学深圳国际研究生院); Pengcheng Laboratory (鹏城实验室), Shenzhen, China
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-52] ranslation Analytics for Freelancers: I. Introduction Data Preparation Baseline Evaluations

链接: https://arxiv.org/abs/2504.14619
作者: Yuri Balashov,Alex Balashov,Shiho Fukuda Koski
机构: University of Georgia (乔治亚大学); Evariste Systems, LLC (伊瓦里斯特系统有限责任公司); SFK Language Solutions (SFK语言解决方案)
类目: Computation and Language (cs.CL)
备注: 28 pages, 4 figures. Accepted at the MT Summit, University of Geneva, June 2025

点击查看摘要

[NLP-53] a1: Steep Test-time Scaling Law via Environment Augmented Generation

链接: https://arxiv.org/abs/2504.14597
作者: Lingrui Mei,Shenghua Liu,Yiwei Wang,Baolong Bi,Yuyao Ge,Jun Wan,Yurong Wu,Xueqi Cheng
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-54] HealthGenie: Empowering Users with Healthy Dietary Guidance through Knowledge Graph and Large Language Models

链接: https://arxiv.org/abs/2504.14594
作者: Fan Gao,Xinjie Zhao,Ding Xia,Zhongyi Zhou,Rui Yang,Jinghui Lu,Hang Jiang,Chanjun Park,Irene Li
机构: The University of Tokyo(Tokyo Japan); Duke-NUS Medical School(Singapore Singapore); Smartor Inc.(Shanghai China); MIT Media Lab(Cambridge Massachusetts USA); Korea University(Seoul South Korea); The University of Tokyo(Tokyo Japan); The University of Tokyo(Tokyo Japan)
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-55] BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation

链接: https://arxiv.org/abs/2504.14538
作者: Yiting Ran,Xintao Wang,Tian Qiu,Jiaqing Liang,Yanghua Xiao,Deqing Yang
机构: Fudan University (复旦大学)
类目: Computation and Language (cs.CL)
备注: 19 pages, 4 figures

点击查看摘要

[NLP-56] Causality for Natural Language Processing

链接: https://arxiv.org/abs/2504.14530
作者: Zhijing Jin
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG)
备注: PhD Thesis 2024

点击查看摘要

[NLP-57] Are Vision LLM s Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding

链接: https://arxiv.org/abs/2504.14526
作者: Tong Zeng,Longfeng Wu,Liang Shi,Dawei Zhou,Feng Guo
机构: Department of Computer Science, Virginia Tech (弗吉尼亚理工大学); Virginia Tech Transportation Institute, Virginia Tech (弗吉尼亚理工大学交通研究所, 弗吉尼亚理工大学); Department of Statistics, Virginia Tech (弗吉尼亚理工大学统计系)
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-58] Meta-Thinking in LLM s via Multi-Agent Reinforcement Learning: A Survey

链接: https://arxiv.org/abs/2504.14520
作者: Ahsan Bilal,Muhammad Ahmed Mohsin,Muhammad Umer,Muhammad Awais Khan Bangash,Muhammad Ali Jamshed
机构: University of Oklahoma (俄克拉荷马大学), Norman, OK, 73072, USA; Stanford University (斯坦福大学), Stanford, CA, 94305, USA; School of Electrical and Computer Engineering, Oklahoma State University (电气与计算机工程学院，俄克拉荷马州立大学), Stillwater, OK, 74075 USA; University of Glasgow (格拉斯哥大学), G12 8QQ, Glasgow, UK
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Submitted to IEEE Transactions on Artificial Intelligence

点击查看摘要

[NLP-59] Functional Abstraction of Knowledge Recall in Large Language Models

链接: https://arxiv.org/abs/2504.14496
作者: Zijian Wang,Chang Xu
机构: School of Computer Science, The University of Sydney (悉尼大学计算机学院)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-60] FairSteer: Inference Time Debiasing for LLM s with Dynamic Activation Steering

链接: https://arxiv.org/abs/2504.14492
作者: Yichen Li,Zhiting Fan,Ruizhe Chen,Xiaotang Gai,Luqi Gong,Yan Zhang,Zuozhu Liu
机构: Zhejiang University (浙江大学); Research Center for Space Computing System, Zhejiang Lab (浙江实验室空间计算系统研究中心)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-61] DialogueAgents : A Hybrid Agent -Based Speech Synthesis Framework for Multi-Party Dialogue ICME2025

链接: https://arxiv.org/abs/2504.14482
作者: Xiang Li,Duyi Pan,Hongru Xiao,Jiale Han,Jing Tang,Jiabao Ma,Wei Wang,Bo Cheng
机构: State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications (北京邮电大学); Department of Computer Science and Engineering, Hong Kong University of Science and Technology (香港科技大学) (Guangzhou); Hong Kong University of Science and Technology (香港科技大学)
类目: Computation and Language (cs.CL); Sound (cs.SD)
备注: Accepted by ICME 2025. Dataset and code are publicly available: [ this https URL ]( this https URL )

点击查看摘要

[NLP-62] sEEG-based Encoding for Sentence Retrieval: A Contrastive Learning Approach to Brain-Language Alignment CVPR2025

链接: https://arxiv.org/abs/2504.14468
作者: Yijun Liu
机构: Ming Hsieh Department of Electrical and Computer Engineering (明氏电气与计算机工程系); University of Southern California (南加州大学)
类目: Computation and Language (cs.CL); Machine Learning (cs.LG); Signal Processing (eess.SP); Neurons and Cognition (q-bio.NC)
备注: Accepted for poster presentation at the CVPR 2025 Workshop on Multimodal Foundation Models (MMFM3)

点击查看摘要

[NLP-63] CoLoTa: A Dataset for Entity-based Commonsense Reasoning over Long-Tail Knowledge

链接: https://arxiv.org/abs/2504.14462
作者: Armin Toroghi,Willis Guo,Scott Sanner
机构: University of Toronto (多伦多大学); Carnegie Mellon University (卡内基梅隆大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-64] ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data

链接: https://arxiv.org/abs/2504.14452
作者: Tong Chen,Faeze Brahman,Jiacheng Liu,Niloofar Mireshghallah,Weijia Shi,Pang Wei Koh,Luke Zettlemoyer,Hannaneh Hajishirzi
机构: University of Washington (华盛顿大学); Allen Institute for Artificial Intelligence (艾伦人工智能研究所)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-65] LoRe: Personalizing LLM s via Low-Rank Reward Modeling

链接: https://arxiv.org/abs/2504.14439
作者: Avinandan Bose,Zhihan Xiong,Yuejie Chi,Simon Shaolei Du,Lin Xiao,Maryam Fazel
机构: University of Washington (华盛顿大学)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-66] Diverse Prompts: Illuminating the Prompt Space of Large Language Models with MAP-Elites CEC2025

链接: https://arxiv.org/abs/2504.14367
作者: Gabriel Machado Santos,Rita Maria da Silva Julia,Marcelo Zanchetta do Nascimento
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 8 pages Accepted for publication in IEEE CEC 2025

点击查看摘要

[NLP-67] Empirical Evaluation of Knowledge Distillation from Transformers to Subquadratic Language Models

链接: https://arxiv.org/abs/2504.14366
作者: Patrick Haller,Jonas Golde,Alan Akbik
机构: Humboldt-Universität zu Berlin (柏林洪堡大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-68] Improving RL Exploration for LLM Reasoning through Retrospective Replay

链接: https://arxiv.org/abs/2504.14363
作者: Shihan Dou,Muling Wu,Jingwen Xu,Rui Zheng,Tao Gui,Qi Zhang,Xuanjing Huang
机构: 未知
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注: 13 pages, 3 figures

点击查看摘要

[NLP-69] Integrating Single-Cell Foundation Models with Graph Neural Networks for Drug Response Prediction

链接: https://arxiv.org/abs/2504.14361
作者: Till Rossner,Ziteng Li,Jonas Balke,Nikoo Salehfard,Tom Seifert,Ming Tang
机构: L3S Research Center (L3S 研究中心), Germany; Leibniz University Hannover (汉诺威莱布尼茨大学), Germany
类目: Machine Learning (cs.LG); Computation and Language (cs.CL); Quantitative Methods (q-bio.QM)
备注: 8 pages, 6 figures

点击查看摘要

[NLP-70] A Multimodal Recaptioning Framework to Account for Perceptual Diversity in Multilingual Vision-Language Modeling

链接: https://arxiv.org/abs/2504.14359
作者: Kyle Buettner,Jacob Emmerson,Adriana Kovashka
机构: Intelligent Systems Program (智能系统项目), University of Pittsburgh (匹兹堡大学); Department of Computer Science (计算机科学系), University of Pittsburgh (匹兹堡大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-71] Multimodal Coreference Resolution for Chinese Social Media Dialogues: Dataset and Benchmark Approach

链接: https://arxiv.org/abs/2504.14321
作者: Xingyu Li,Chen Gong,Guohong Fu
机构: Institute of Artificial Intelligence, Soochow University (苏州大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-72] Probing the Subtle Ideological Manipulation of Large Language Models

链接: https://arxiv.org/abs/2504.14287
作者: Demetris Paschalides,George Pallis,Marios D. Dikaiakos
机构: 未知
类目: Computation and Language (cs.CL); Computers and Society (cs.CY)
备注:

点击查看摘要

[NLP-73] Cross-attention for State-based model RWKV-7

链接: https://arxiv.org/abs/2504.14260
作者: Liu Xiao,Li Zhiyuan,Lin Yueyu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-74] owards Explainable Fake Image Detection with Multi-Modal Large Language Models

链接: https://arxiv.org/abs/2504.14245
作者: Yikun Ji,Yan Hong,Jiahui Zhan,Haoxing Chen,jun lan,Huijia Zhu,Weiqiang Wang,Liqing Zhang,Jianfu Zhang
机构: Shanghai Jiao Tong University(上海交通大学); Ant Group(蚂蚁集团)
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-75] InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reason ers

链接: https://arxiv.org/abs/2504.14239
作者: Yuhang Liu,Pengxiang Li,Congkai Xie,Xavier Hu,Xiaotian Han,Shengyu Zhang,Hongxia Yang,Fei Wu
机构: Zhejiang University (浙江大学); Dalian University of Technology (大连理工大学); Reallm Labs; Zhejiang University (浙江大学); The Hong Kong Polytechnic University (香港理工大学); Zhejiang University (浙江大学)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 10 pages, 3 figures, work in progress

点击查看摘要

[NLP-76] Assessing AI-Generated Questions Alignment with Cognitive Frameworks in Educational Assessment CCS

链接: https://arxiv.org/abs/2504.14232
作者: Antoun Yaacoub,Jérôme Da-Rugna,Zainab Assaghir
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: This paper was presented in the 17th Int. Conf. on Computer Science and Information Technology (ICCSIT 2024), Dubai, United Arab Emirates, 2024, Oct. 23-25. IT’s now in production to be published in the International Journal of Computer Theory and Engineering

点击查看摘要

[NLP-77] Know Me Respond to Me: Benchmarking LLM s for Dynamic User Profiling and Personalized Responses at Scale

链接: https://arxiv.org/abs/2504.14225
作者: Bowen Jiang,Zhuoqun Hao,Young-Min Cho,Bryan Li,Yuan Yuan,Sihao Chen,Lyle Ungar,Camillo J. Taylor,Dan Roth
机构: University of Pennsylvania (宾夕法尼亚大学); Microsoft (微软)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-78] SimplifyMyText: An LLM -Based System for Inclusive Plain Language Text Simplification ECIR2025

链接: https://arxiv.org/abs/2504.14223
作者: Michael Färber,Parisa Aghdam,Kyuri Im,Mario Tawfelis,Hardik Ghoshal
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注: accepted at ECIR 2025

点击查看摘要

[NLP-79] Understanding the Repeat Curse in Large Language Models from a Feature Perspective ACL2025

链接: https://arxiv.org/abs/2504.14218
作者: Junchi Yao,Shu Yang,Jianhua Xu,Lijie Hu,Mengdi Li,Di Wang
机构: Provable Responsible AI and Data Analytics (PRADA) Lab (可证明负责任的人工智能与数据分析实验室); King Abdullah University of Science and Technology (沙特国王科技大学); University of Electronic Science and Technology of China (电子科技大学)
类目: Computation and Language (cs.CL)
备注: Submitted to ACL 2025

点击查看摘要

[NLP-80] Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification

链接: https://arxiv.org/abs/2504.14212
作者: Takuma Udagawa,Yang Zhao,Hiroshi Kanayama,Bishwaranjan Bhattacharjee
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-81] EIoU-EMC: A Novel Loss for Domain-specific Nested Entity Recognition SIGIR’2025

链接: https://arxiv.org/abs/2504.14203
作者: Jian Zhang,Tianqing Zhang,Qi Li,Hongwei Wang
机构: 未知
类目: Computation and Language (cs.CL); Information Retrieval (cs.IR)
备注: Accepted by SIGIR’2025

点击查看摘要

[NLP-82] Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models

链接: https://arxiv.org/abs/2504.14194
作者: Xinlin Zhuang,Jiahui Peng,Ren Ma,Yinfan Wang,Tianyi Bai,Xingjian Wei,Jiantao Qiu,Chi Zhang,Ying Qian,Conghui He
机构: 未知
类目: Computation and Language (cs.CL)
备注: Under review

点击查看摘要

[NLP-83] AI Idea Bench 2025: AI Research Idea Generation Benchmark

链接: https://arxiv.org/abs/2504.14191
作者: Yansheng Qiu,Haoquan Zhang,Zhaopan Xu,Ming Li,Diping Song,Zheng Wang,Kaipeng Zhang
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-84] Direct Advantage Regression: Aligning LLM s with Online AI Reward

链接: https://arxiv.org/abs/2504.14177
作者: Li He,He Zhao,Stephen Wan,Dadong Wang,Lina Yao,Tongliang Liu
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC)
备注:

点击查看摘要

[NLP-85] Hypothetical Documents or Knowledge Leakage? Rethinking LLM -based Query Expansion

链接: https://arxiv.org/abs/2504.14175
作者: Yejun Yoon,Jaeyoon Jung,Seunghyun Yoon,Kunwoo Park
机构: 未知
类目: Computation and Language (cs.CL); Information Retrieval (cs.IR)
备注: preprint

点击查看摘要

[NLP-86] Self-Correction Makes LLM s Better Parsers

链接: https://arxiv.org/abs/2504.14165
作者: Ziyan Zhang,Yang Hou,Chen Gong,Zhenghua Li
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-87] SConU: Selective Conformal Uncertainty in Large Language Models

链接: https://arxiv.org/abs/2504.14154
作者: Zhiyuan Wang,Qingni Wang,Yue Zhang,Tianlong Chen,Xiaofeng Zhu,Xiaoshuang Shi,Kaidi Xu
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML)
备注:

点击查看摘要

[NLP-88] Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations

链接: https://arxiv.org/abs/2504.14150
作者: Katie Matton,Robert Osazuwa Ness,John Guttag,Emre Kıcıman
机构: MIT; Microsoft Research (微软研究)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML)
备注: 61 pages, 14 figures, 36 tables

点击查看摘要

[NLP-89] HF4Rec: Human-Like Feedback-Driven Optimization Framework for Explainable Recommendation

链接: https://arxiv.org/abs/2504.14147
作者: Jiakai Tang,Jingsen Zhang,Zihang Tian,Xueyang Feng,Lei Wang,Xu Chen
机构: 未知
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-90] ALES: Text Adventure Learning Environment Suite

链接: https://arxiv.org/abs/2504.14128
作者: Christopher Zhang Cui,Xingdi Yuan,Zhang Xiao,Prithviraj Ammanabrolu,Marc-Alexandre Côté
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-91] Large Language Model Enhanced Particle Swarm Optimization for Hyperparameter Tuning for Deep Learning Models

链接: https://arxiv.org/abs/2504.14126
作者: Saad Hameed,Basheer Qolomany,Samir Brahim Belhaouari,Mohamed Abdallah,Junaid Qadir,Ala Al-Fuqaha
机构: Division of Information and Computing Technology, College of Science and Engineering, Hamad Bin Khalifa University (哈姆德本哈利法大学), Doha, 5825 Qatar; Department of Medicine, College of Medicine, Howard University (霍华德大学), Washington, D.C. 20059 USA; Department of Computer Science and Engineering, Qatar University (卡塔尔大学), Doha, 5825 Qatar
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-92] Bayesian Principles Improve Prompt Learning In Vision-Language Models AISTATS2025

链接: https://arxiv.org/abs/2504.14123
作者: Mingyu Kim,Jongwoo Ko,Mijung Park
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
备注: AISTATS2025

点击查看摘要

[NLP-93] PEFT A2Z: Parameter-Efficient Fine-Tuning Survey for Large Language and Vision Models

链接: https://arxiv.org/abs/2504.14117
作者: Nusrat Jahan Prottasha,Upama Roy Chowdhury,Shetu Mohanto,Tasfia Nuzhat,Abdullah As Sami,Md Shamol Ali,Md Shohanur Islam Sobuj,Hafijur Raman,Md Kowsher,Ozlem Ozmen Garibay
机构: University of Central Florida (中佛罗里达大学), USA; Khulna University of Engineering & Technology (库尔纳工程与技术大学), Bangladesh; Delineate Inc. (Delineate公司), USA; Universiti Tenaga Nasional (国家能源大学), Malaysia; University of South Florida (南佛罗里达大学), USA; Daffodil International University (达芙妮国际大学), Bangladesh; Anymate Me (Anymate Me), Germany
类目: Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
备注: PEFT Survey paper

点击查看摘要

[NLP-94] Linking forward-pass dynamics in Transformers and real-time human processing

链接: https://arxiv.org/abs/2504.14107
作者: Jennifer Hu,Michael A. Lepori,Michael Franke
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-95] LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Models

链接: https://arxiv.org/abs/2504.14089
作者: Kang He,Kaushik Roy
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-96] A Baseline for Self-state Identification and Classification in Mental Health Data: CLPsych 2025 Task NAACL2025

链接: https://arxiv.org/abs/2504.14066
作者: Laerdon Kim
机构: Cornell University (康奈尔大学)
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: Accepted to CLPsych Workshop, NAACL 2025

点击查看摘要

[NLP-97] Sentiment Analysis of Airbnb Reviews: Exploring Their Impact on Acceptance Rates and Pricing Across Multiple U.S. Regions

链接: https://arxiv.org/abs/2504.14053
作者: Ali Safari
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-98] MEQA: A Meta-Evaluation Framework for Question Answer LLM Benchmarks

链接: https://arxiv.org/abs/2504.14039
作者: Jaime Raldua Veuthey,Zainab Ali Majid,Suhas Hariharan,Jacob Haimes
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-99] Uncovering Conspiratorial Narratives within Arabic Online Content

链接: https://arxiv.org/abs/2504.14037
作者: Djamila Mohdeb,Meriem Laifa,Zineb Guemraoui,Dalila Behih
机构: 未知
类目: Computation and Language (cs.CL); Computers and Society (cs.CY); Social and Information Networks (cs.SI)
备注:

点击查看摘要

[NLP-100] Gradual Binary Search and Dimension Expansion : A general method for activation quantization in LLM s

链接: https://arxiv.org/abs/2504.13989
作者: Lucas Maisonnave,Cyril Moineau,Olivier Bichler,Fabrice Rastello
机构: CEA LIST (CEA LIST); Université Paris-Saclay (巴黎萨克雷大学); Univ. Grenoble Alpes (格勒诺布尔阿尔卑斯大学); Inria (法国国家信息与自动化研究所); CNRS (法国国家科学研究中心); Grenoble INP (格勒诺布尔国立理工学院); LIG (格勒诺布尔信息系统实验室)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-101] One Jump Is All You Need: Short-Cutting Transformers for Early Exit Prediction with One Jump to Fit All Exit Levels

链接: https://arxiv.org/abs/2504.13984
作者: Amrit Diggavi Seshadri
机构: Sudarshantech Software (苏达山科技软件)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-102] AI Safety Should Prioritize the Future of Work

链接: https://arxiv.org/abs/2504.13959
作者: Sanchaita Hazra,Bodhisattwa Prasad Majumder,Tuhin Chakrabarty
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); General Economics (econ.GN)
备注:

点击查看摘要

[NLP-103] oolRL: Reward is All Tool Learning Needs

链接: https://arxiv.org/abs/2504.13958
作者: Cheng Qian,Emre Can Acikgoz,Qi He,Hongru Wang,Xiusi Chen,Dilek Hakkani-Tür,Gokhan Tur,Heng Ji
机构: University of Illinois Urbana-Champaign (伊利诺伊大学厄巴纳-香槟分校)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 19 Pages, 12 Figures, 12 Tables

点击查看摘要

[NLP-104] housand Voices of Trauma: A Large-Scale Synthetic Dataset for Modeling Prolonged Exposure Therapy Conversations

链接: https://arxiv.org/abs/2504.13955
作者: Suhas BN,Dominik Mattioli,Saeed Abdullah,Rosa I. Arriaga,Chris W. Wiese,Andrew M. Sherrill
机构: College of Information Sciences and Technology, Penn State University (宾夕法尼亚州立大学); School of Interactive Computing, Georgia Tech (乔治亚理工学院); School of Psychology, Georgia Tech (乔治亚理工学院); Department of Psychiatry and Behavioral Sciences, Emory University (埃默里大学)
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
备注: 14 pages, 6 figures

点击查看摘要

[NLP-105] Enhancing Ultra-Low-Bit Quantization of Large Language Models Through Saliency-Aware Partial Retraining

链接: https://arxiv.org/abs/2504.13932
作者: Deyu Cao,Samin Aref
机构: 未知
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注: 28 pages, 5 figures, 11 tables

点击查看摘要

[NLP-106] Evaluation and Incident Prevention in an Enterprise AI Assistant

链接: https://arxiv.org/abs/2504.13924
作者: Akash V. Maharaj,David Arbour,Daniel Lee,Uttaran Bhattacharya,Anup Rao,Austin Zane,Avi Feller,Kun Qian,Yunyao Li
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC)
备注: 7 pages, 5 figures. Accepted at IAAI-25

点击查看摘要

[NLP-107] Seed-Thinking-v1.5: Advancing Superb Reasoning Models with Reinforcement Learning

链接: https://arxiv.org/abs/2504.13914
作者: ByteDance Seed:Yufeng Yuan,Yu Yue,Mingxuan Wang,Xiaochen Zuo,Jiaze Chen,Lin Yan,Wenyuan Xu,Chi Zhang,Xin Liu,Chengyi Wang,TianTian Fan,Lingjun Liu,Qiying Yu,Xiangpeng Wei,Zhiqi Lin,Ruofei Zhu,Qingping Yang,Chengzhi Wei,Jerry He,Guanlin Liu,Zheng Wu,Xiangyu Yu,Zhicheng Liu,Jingjing Xu,Jiangjie Chen,Haojie Pan,Shengding Hu,Zhengyin Du,Wenqi Wang,Zewei Sun,Chenwei Lou,Bole Ma,Zihan Wang,Mofan Zhang,Wang Zhang,Gaohong Liu,Kaihua Jiang,Haibin Lin,Ru Zhang,Juncai Liu,Li Han,Jinxin Chi,Wenqiang Zhang,Jiayi Xu,Jun Yuan,Zhen Xiao,Yuqiao Xian,Jingqiao Wu,Kai Hua,Na Zhou,Jianhui Duan,Heyang Lu,Changbao Wang,Jinxiang Ou,Shihang Wang,Xiaoran Jin,Xuesong Yao,Chengyin Xu,Wenchang Ma,Zhecheng An,Renming Pang,Xia Xiao,Jing Su,Yuyu Zhang,Tao Sun,Kaibo Liu,Yifan Sun,Kai Shen,Sijun Zhang,Yiyuan Ma,Xingyan Bin,Ji Li,Yao Luo,Deyi Liu,Shiyi Zhan,Yunshui Li,Yuan Yang,Defa Zhu,Ke Shen,Chenggang Li,Xun Zhou,Liang Xiang,Yonghui Wu
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-108] Generative Framework for Personalized Persuasion: Inferring Causal Counterfactual and Latent Knowledge

链接: https://arxiv.org/abs/2504.13904
作者: Donghuo Zeng,Roberto Legaspi,Yuewen Sun,Xinshuai Dong,Kazushi Ikeda,Peter Spirtes,Kun Zhang
机构: KDDI Research, Inc. (KDDI 研究院); Carnegie Mellon University (卡内基梅隆大学)
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 12 pages, 10 figures, 1 table. Accepted by ACM UMAP 2025

点击查看摘要

[NLP-109] ALLM esh: a simple application for performing Thematic Analysis with Large Language Models

链接: https://arxiv.org/abs/2504.13892
作者: Stefano De Paoli,Alex Fawzi
机构: 未知
类目: Human-Computer Interaction (cs.HC); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-110] Measuring Mental Health Variables in Computational Research: Toward Validated Dimensional and Transdiagnostic Approaches

链接: https://arxiv.org/abs/2504.13890
作者: Chen Shani,Elizabeth C. Stade
机构: Stanford University (斯坦福大学)
类目: Human-Computer Interaction (cs.HC); Computation and Language (cs.CL)
备注: No figures, 1 Table

点击查看摘要

[NLP-111] Kanji Workbook: A Writing-Based Intelligent Tutoring System for Learning Proper Japanese Kanji Writing Technique with Instructor-Emulated Assessment

链接: https://arxiv.org/abs/2504.13888
作者: Paul Taele,Jung In Koh,Tracy Hammond
机构: Texas A&M University (德克萨斯农工大学)
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-112] AI as a deliberative partner fosters intercultural empathy for Americans but fails for Latin American participants

链接: https://arxiv.org/abs/2504.13887
作者: Isabel Villanueva,Tara Bobinac,Binwei Yao,Junjie Hu,Kaiping Chen
机构: 未知
类目: Human-Computer Interaction (cs.HC); Computation and Language (cs.CL); Computers and Society (cs.CY)
备注:

点击查看摘要

[NLP-113] oward Automated Qualitative Analysis: Leverag ing Large Language Models for Tutoring Dialogue Evaluation

链接: https://arxiv.org/abs/2504.13882
作者: Megan Gu,Chloe Qianhui Zhao,Claire Liu,Nikhil Patel,Jahnvi Shah,Jionghao Lin,Kenneth R. Koedinger
机构: Carnegie Mellon University (卡内基梅隆大学); The University of Hong Kong (香港大学); Monash University (蒙纳士大学)
类目: Human-Computer Interaction (cs.HC); Computation and Language (cs.CL)
备注: Manuscript accepted to the Workshop on “From Data to Discovery: LLMs for Qualitative Analysis in Education” at LAK25

点击查看摘要

[NLP-114] A Survey on (M)LLM -Based GUI Agents

链接: https://arxiv.org/abs/2504.13865
作者: Fei Tang,Haolei Xu,Hang Zhang,Siqi Chen,Xingyu Wu,Yongliang Shen,Wenqi Zhang,Guiyang Hou,Zeqi Tan,Yuchen Yan,Kaitao Song,Jian Shao,Weiming Lu,Jun Xiao,Yueting Zhuang
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[NLP-115] 3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark

链接: https://arxiv.org/abs/2504.13861
作者: Ivan Sviridov,Amina Miftakhova,Artemiy Tereshchenko,Galina Zubkova,Pavel Blinov,Andrey Savchenko
机构: 未知
类目: Human-Computer Interaction (cs.HC); Computation and Language (cs.CL); Multiagent Systems (cs.MA)
备注: 26 pages, 8 figures, 7 tables

点击查看摘要

[NLP-116] Interview AI-ssistant: Designing for Real-Time Human-AI Collaboration in Interview Preparation and Execution

链接: https://arxiv.org/abs/2504.13847
作者: Zhe Liu
机构: University of British Columbia (不翻译)
类目: Human-Computer Interaction (cs.HC); Computation and Language (cs.CL)
备注: 4 pages, 2 figures, submitted and accepted by IUI 2025 Doctoral Consortium

点击查看摘要

[NLP-117] Density Measures for Language Generation

链接: https://arxiv.org/abs/2504.14370
作者: Jon Kleinberg,Fan Wei
机构: 未知
类目: Combinatorics (math.CO); Computation and Language (cs.CL); Discrete Mathematics (cs.DM); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-118] he First VoicePrivacy Attacker Challenge ICASSP ICASSP2025

链接: https://arxiv.org/abs/2504.14183
作者: Natalia Tomashenko,Xiaoxiao Miao,Emmanuel Vincent,Junichi Yamagishi
机构: 未知
类目: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Cryptography and Security (cs.CR)
备注: Published in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

点击查看摘要

[NLP-119] System of Agent ic AI for the Discovery of Metal-Organic Frameworks

链接: https://arxiv.org/abs/2504.14110
作者: Theo Jaffrelot Inizan,Sherry Yang,Aaron Kaplan,Yen-hsu Lin,Jian Yin,Saber Mirzaei,Mona Abdelgaid,Ali H. Alawadhi,KwangHwan Cho,Zhiling Zheng,Ekin Dogus Cubuk,Christian Borgs,Jennifer T. Chayes,Kristin A. Persson,Omar M. Yaghi
机构: 未知
类目: Materials Science (cond-mat.mtrl-sci); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA)
备注:

点击查看摘要

计算机视觉

[CV-0] StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussians

链接: https://arxiv.org/abs/2504.15281
作者: Cailin Zhuang,Yaoqi Hu,Xuanyang Zhang,Wei Cheng,Jiacheng Bao,Shengqi Liu,Yiying Yang,Xianfang Zeng,Gang Yu,Ming Li
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 16 pages; Project page: this https URL

点击查看摘要

[CV-1] VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models

链接: https://arxiv.org/abs/2504.15279
作者: Weiye Xu,Jiahao Wang,Weiyun Wang,Zhe Chen,Wengang Zhou,Aijun Yang,Lewei Lu,Houqiang Li,Xiaohua Wang,Xizhou Zhu,Wenhai Wang,Jifeng Dai,Jinguo Zhu
机构: University of Science and Technology of China (中国科学技术大学); Xi’an Jiaotong University (西安交通大学); Shanghai Artifcial Intelligence Laboratory (上海人工智能实验室); SenseTime Research (商汤研究); Tsinghua University (清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Code, data, and baselines are available at this https URL

点击查看摘要

[CV-2] DRAWER: Digital Reconstruction and Articulation With Environment Realism

链接: https://arxiv.org/abs/2504.15278
作者: Hongchi Xia,Entong Su,Marius Memmel,Arhan Jain,Raymond Yu,Numfor Mbiziwo-Tiapo,Ali Farhadi,Abhishek Gupta,Shenlong Wang,Wei-Chiu Ma
机构: University of Illinois Urbana-Champaign (伊利诺伊大学香槟分校); University of Washington (华盛顿大学); Allen Institute for AI (艾伦人工智能研究所); Cornell University (康奈尔大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: Project page: this https URL

点击查看摘要

[CV-3] Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

链接: https://arxiv.org/abs/2504.15271
作者: Guo Chen,Zhiqi Li,Shihao Wang,Jindong Jiang,Yicheng Liu,Lidong Lu,De-An Huang,Wonmin Byeon,Matthieu Le,Tuomas Rintamaki,Tyler Poon,Max Ehrlich,Tuomas Rintamaki,Tyler Poon,Tong Lu,Limin Wang,Bryan Catanzaro,Jan Kautz,Andrew Tao,Zhiding Yu,Guilin Liu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-4] Diffusion Bridge Models for 3D Medical Image Translation

链接: https://arxiv.org/abs/2504.15267
作者: Shaorong Zhang,Tamoghna Chattopadhyay,Sophia I. Thomopoulos,Jose-Luis Ambite,Paul M. Thompson,Greg Ver Steeg
机构: University of California Riverside (加州大学河滨分校); Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California (南加州大学凯克医学院影像遗传学中心，马克和玛丽·史蒂文斯神经成像与信息学研究所); Information Sciences Institute, University of Southern California (南加州大学信息科学研究所)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-5] Bringing Diversity from Diffusion Models to Semantic-Guided Face Asset Generation

链接: https://arxiv.org/abs/2504.15259
作者: Yunxuan Cai,Sitao Xiang,Zongjian Li,Haiwei Chen,Yajie Zhao
机构: University of Southern California, USC Institute for Creative Technologies (南加州大学, 南加州大学创意技术研究所)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-6] SuoiAI: Building a Dataset for Aquatic Invertebrates in Vietnam ICLR2025

链接: https://arxiv.org/abs/2504.15252
作者: Tue Vo,Lakshay Sharma,Tuan Dinh,Khuong Dinh,Trang Nguyen,Trung Phan,Minh Do,Duong Vu
机构: Nuoc Solutions; Microsoft (微软); University of Oslo (奥斯陆大学); Bowdoin College (鲍登学院); Fulbright University Vietnam (弗尔布莱特大学越南校区); Westerdijk Fungal Biodiversity Institute (韦斯特迪克真菌生物多样性研究所)
类目: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Published as a workshop paper at “Tackling Climate Change with Machine Learning”, ICLR 2025

点击查看摘要

[CV-7] Shape-Guided Clothing Warping for Virtual Try-On ACM-MM2024

链接: https://arxiv.org/abs/2504.15232
作者: Xiaoyu Han,Shunyuan Zheng,Zonglin Li,Chenyang Wang,Xin Sun,Quanling Meng
机构: Harbin Institute of Technology Weihai (哈尔滨工业大学威海校区)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by ACM MM 2024. The code is available at this https URL

点击查看摘要

[CV-8] Zero-Shot But at What Cost? Unveiling the Hidden Overhead of MILSs LLM -CLIP Framework for Image Captioning

链接: https://arxiv.org/abs/2504.15199
作者: Yassir Benhammou,Alessandro Tiberio,Gabriel Trautmann,Suman Kalyan
机构: NstarX(未知中文)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Performance (cs.PF)
备注: 9 pages, 2 tables, 1 figure

点击查看摘要

[CV-9] Automated Measurement of Eczema Severity with Self-Supervised Learning

链接: https://arxiv.org/abs/2504.15193
作者: Neelesh Kumar,Oya Aran
机构: The Procter and Gamble Company (宝洁公司)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-10] Breast density in MRI: an AI-based quantification and relationship to assessment in mammography

链接: https://arxiv.org/abs/2504.15192
作者: Yaqian Chen,Lin Li,Hanxue Gu,Haoyu Dong,Derek L. Nguyen,Allan D. Kirk,Maciej A. Mazurowski,E. Shelley Hwang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 13 pages, 5 figures

点击查看摘要

[CV-11] ger200K: Manually Curated High Visual Quality Video Dataset from UGC Platform

链接: https://arxiv.org/abs/2504.15182
作者: Xianpan Zhou
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-12] FaceCraft4D: Animated 3D Facial Avatar Generation from a Single Image

链接: https://arxiv.org/abs/2504.15179
作者: Fei Yin,Mallikarjun B R,Chun-Han Yao,Rafał Mantiuk,Varun Jampani
机构: University of Cambridge (剑桥大学); Stability AI (Stability AI)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-13] DSPO: Direct Semantic Preference Optimization for Real-World Image Super-Resolution

链接: https://arxiv.org/abs/2504.15176
作者: Miaomiao Cai,Simiao Li,Wei Li,Xudong Huang,Hanting Chen,Jie Hu,Yunhe Wang
机构: University of Science and Technology of China (中国科学技术大学); Huawei Noah’s Ark Lab (华为诺亚方舟实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-14] HSANET: A Hybrid Self-Cross Attention Network For Remote Sensing Change Detection

链接: https://arxiv.org/abs/2504.15170
作者: Chengxi Han,Xiaoyu Su,Zhiqiang Wei,Meiqi Hu,Yichu Xu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-15] An Efficient Aerial Image Detection with Variable Receptive Fields

链接: https://arxiv.org/abs/2504.15165
作者: Liu Wenbin
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-16] Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration CVPR2025

链接: https://arxiv.org/abs/2504.15159
作者: Junyuan Deng,Xinyi Wu,Yongxing Yang,Congchao Zhu,Song Wang,Zhenyao Wu
机构: Honor Device Co., Ltd (荣耀终端有限公司); Shenzhen University of Advanced Technology (深圳先进技术研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025

点击查看摘要

[CV-17] Dynamic 3D KAN Convolution with Adaptive Grid Optimization for Hyperspectral Image Classification

链接: https://arxiv.org/abs/2504.15155
作者: Guandong Li,Mengxia Ye
机构: aiFLYTEK (科大讯飞); Aegon THTF (安信信托)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-18] Landmark-Free Preoperative-to-Intraoperative Registration in Laparoscopic Liver Resection

链接: https://arxiv.org/abs/2504.15152
作者: Jun Zhou,Bingchen Gao,Kai Wang,Jialun Pei,Pheng-Ann Heng,Jing Qin
机构: The Hong Kong Polytechnic University (香港理工大学); Department of Computer Science and Engineering, The Chinese University of Hong Kong (香港中文大学计算机科学与工程系); Division of Hepatobiliopancreatic Surgery, Department of General Surgery, Nanfang Hospital, Southern Medical University (南方医院普通外科肝胆胰外科分部)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: TMI under review

点击查看摘要

[CV-19] “I Know It When I See It”: Mood Spaces for Connecting and Expressing Visual Concepts

链接: https://arxiv.org/abs/2504.15145
作者: Huzheng Yang,Katherine Xu,Michael D. Grossberg,Yutong Bai,Jianbo Shi
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-20] Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose Estimation

链接: https://arxiv.org/abs/2504.15134
作者: Xiao Zhang,Lu Zou,Tao Lu,Yuan Yao,Zhangjin Huang,Guoping Wang
机构: Wuhan Institute of Technology (武汉理工大学); University of Science and Technology of China (中国科学技术大学); Peking University (北京大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-21] A General Infrastructure and Workflow for Quadrotor Deep Reinforcement Learning and Reality Deployment

链接: https://arxiv.org/abs/2504.15129
作者: Kangyao Huang,Hao Wang,Yu Luo,Jingyu Chen,Jintao Chen,Xiangkui Zhang,Xiangyang Ji,Huaping Liu
机构: Department of Computer Science and Technology, Tsinghua University (清华大学计算机科学与技术系); School of Computer Science and Technology, Dalian University of Technology (大连理工大学计算机科学与技术学院); Department of Automation, Tsinghua University (清华大学自动化系); Institute of Software, Chinese Academy of Sciences (中国科学院软件研究所)
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-22] MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video

链接: https://arxiv.org/abs/2504.15122
作者: Minh-Quan Viet Bui,Jongmin Park,Juan Luis Gonzalez Bello,Jaeho Moon,Jihyong Oh,Munchurl Kim
机构: KAIST (高丽大学); Chung-Ang University (中央大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: The first two authors contributed equally to this work (equal contribution). The last two authors advised equally to this work

点击查看摘要

[CV-23] Robust and Real-time Surface Normal Estimation from Stereo Disparities using Affine Transformations

链接: https://arxiv.org/abs/2504.15121
作者: Csongor Csanad Kariko,Muhammad Rafi Faisal,Levente Hajder
机构: Geometric Computer Vision Group (几何计算机视觉小组), Faculty of Informatics (信息学学院), Eötvös Loránd University (厄特沃什·洛兰大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-24] Improving Sound Source Localization with Joint Slot Attention on Image and Audio CVPR2025

链接: https://arxiv.org/abs/2504.15118
作者: Inho Kim,Youngkil Song,Jicheol Park,Won Hwa Kim,Suha Kwak
机构: Dept. of CSE, POSTECH (计算机科学与工程系, POSTECH); Graduate School of AI, POSTECH (人工智能研究生院, POSTECH)
类目: Computer Vision and Pattern Recognition (cs.CV); Sound (cs.SD)
备注: Accepted to CVPR 2025

点击查看摘要

[CV-25] Unwarping Screen Content Images via Structure-texture Enhancement Network and Transformation Self-estimation

链接: https://arxiv.org/abs/2504.15108
作者: Zhenzhen Xiao,Heng Liu,Bingwen Hu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-26] A triple-branch network for latent fingerprint enhancement guided by orientation fields and minutiae

链接: https://arxiv.org/abs/2504.15105
作者: Yurun Wang,Zerong Qi,Shujun Fu,Mingzheng Hu
机构: School of Matahematics, Shandong University (山东大学); Shandong Chengshi Electronic Technology Limited Company (山东城仕电子科技有限公司)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-27] VistaDepth: Frequency Modulation With Bias Reweighting For Enhanced Long-Range Depth Estimation

链接: https://arxiv.org/abs/2504.15095
作者: Mingxia Zhan,Li Zhang,XiaoMeng Chu,Beibei Wang
机构: Hefei University of Technology (合肥工业大学), Hefei, Anhui, China; University of Science and Technology of China (中国科学技术大学), Hefei, Anhui, China; Institute of Artificial Intelligence, Hefei Comprehensive National Science Center (合肥综合性国家科学中心人工智能研究院), Hefei, Anhui, China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 6 figures, 4 tables

点击查看摘要

[CV-28] Hierarchical Attention Fusion of Visual and Textual Representations for Cross-Domain Sequential Recommendation

链接: https://arxiv.org/abs/2504.15085
作者: Wangyu Wu,Zhenhong Chen,Siqi Song,Xianglin Qiua,Xiaowei Huang,Fei Ma,Jimin Xiao
机构: Xi’an Jiaotong-Liverpool University (西安交通大学利物浦大学); The University of Liverpool (利物浦大学); Microsoft (微软)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at CogSCI 2025

点击查看摘要

[CV-29] Structure-guided Diffusion Transformer for Low-Light Image Enhancement

链接: https://arxiv.org/abs/2504.15054
作者: Xiangchen Yin,Zhenda Yu,Longtao Jiang,Xin Gao,Xiao Sun,Zhi Liu,Xun Yang
机构: University of Science and Technology of China (中国科学技术大学); Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei 230088, China (合肥综合性国家科学中心人工智能研究所); Anhui University, China (安徽大学); School of Vehicle and Mobility, Tsinghua University, China (清华大学车辆与 mobility学院); State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China (清华大学汽车安全与能源国家重点实验室); School of Computer Science and Information Engineering, Hefei University of Technology, China (合肥工业大学计算机科学与信息工程学院); Department of Computer and Network Engineering, The University of Electro-Communications, Chofu-shi, Tokyo, 1828585 Japan (电气通信大学计算机与网络工程系)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by IEEE Transactions on Multimedia (TMM)

点击查看摘要

[CV-30] VeLU: Variance-enhanced Learning Unit for Deep Neural Networks

链接: https://arxiv.org/abs/2504.15051
作者: Ashkan Shakarami,Yousef Yeganeh,Azade Farshad,Lorenzo Nicolè,Stefano Ghidoni,Nassir Navab
机构: University of Padova (帕多瓦大学), Italy; Technical University of Munich (慕尼黑工业大学), Germany
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-31] ScanEdit: Hierarchically-Guided Functional 3D Scan Editing WWW ATC

链接: https://arxiv.org/abs/2504.15049
作者: Mohamed el amine Boudjoghra,Ivan Laptev,Angela Dai
机构: Technical University of Munich (慕尼黑工业大学); Mohamed Bin Zayed University of Artificial Intelligence (穆罕默德·本·扎耶德人工智能大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project webpage: this https URL Video: this https URL

点击查看摘要

[CV-32] Distribution-aware Forgetting Compensation for Exemplar-Free Lifelong Person Re-identification

链接: https://arxiv.org/abs/2504.15041
作者: Shiben Liu,Huijie Fan,Qiang Wang,Baojie Fan,Yandong Tang,Liangqiong Qu
机构: State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences (中国科学院沈阳自动化研究所机器人国家重点实验室); University of Chinese Academy of Sciences (中国科学院大学); Key Laboratory of Manufacturing Industrial Integrated Automation, Shenyang University (沈阳大学制造工业集成自动化重点实验室); Automation and AI College, Nanjing University of Posts and Telecommunications (南京邮电大学自动化与人工智能学院); Department of Statistics and Actuarial Science and the Institute of Data Science, The University of Hong Kong (香港大学统计精算系及数据科学研究所)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 12 pages, 5 figures

点击查看摘要

[CV-33] DyST-XL: Dynamic Layout Planning and Content Control for Compositional Text-to-Video Generation

链接: https://arxiv.org/abs/2504.15032
作者: Weijie He,Mushui Liu,Yunlong Yu,Zhao Wang,Chao Wu
机构: Zhejiang University (浙江大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages, 6 figures

点击查看摘要

[CV-34] A Controllable Appearance Representation for Flexible Transfer and Editing

链接: https://arxiv.org/abs/2504.15028
作者: Santiago Jimenez-Navarro,Julia Guerrero-Viu,Belen Masia
机构: 未知
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-35] Gaussian Shading: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion Models

链接: https://arxiv.org/abs/2504.15026
作者: Zijin Yang,Xin Zhang,Kejiang Chen,Kai Zeng,Qiyi Yao,Han Fang,Weiming Zhang,Nenghai Yu
机构: University of Science and Technology of China (中国科学技术大学); Anhui Province Key Laboratory of Digital Security (安徽省数字安全重点实验室); Department of Information Engineering and Mathematics, University of Siena (意大利锡耶纳大学信息工程与数学系); School of Computing, National University of Singapore (新加坡国立大学计算学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Cryptography and Security (cs.CR)
备注: 18 pages, 8 figures

点击查看摘要

[CV-36] Insert Anything: Image Insertion via In-Context Editing in DiT

链接: https://arxiv.org/abs/2504.15009
作者: Wensong Song,Hong Jiang,Zongxing Yang,Ruijie Quan,Yi Yang
机构: Zhejiang University (浙江大学); Harvard University (哈佛大学); Nanyang Technological University (南洋理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-37] Shifts in Doctors Eye Movements Between Real and AI-Generated Medical Images

【速读】：该论文试图解决的问题是：通过眼动追踪分析，探讨放射科医生在解读真实医学影像（Real）与深度学习生成的合成影像（Fake）时，其注意力分配及视觉行为是否存在差异。论文的关键解决方案在于采用多种定量指标，包括不同扫视方向（saccades direction）、幅度（amplitude）及其联合分布的测量，以及对注视偏移图（fixation bias maps）的详细分析，重点关注首次、末次、短时及最长注视，并结合扫视模式的全面考察，以此量化真实影像与合成影像之间在注视分布和视觉显著性方面的差异。

链接: https://arxiv.org/abs/2504.15007
作者: David C Wong,Bin Wang,Gorkem Durak,Marouane Tliba,Mohamed Amine Kerkouri,Aladine Chetouani,Ahmet Enis Cetin,Cagdas Topel,Nicolo Gennaro,Camila Vendrami,Tugce Agirlar Trabzonlu,Amir Ali Rahsepar,Laetitia Perronne,Matthew Antalek,Onural Ozturk,Gokcan Okur,Andrew C. Gordon,Ayis Pyrros,Frank H Miller,Amir A Borhani,Hatice Savas,Eric M. Hart
机构: Northwestern University (西北大学, USA); University of Orleans (奥尔良大学, France); f-initiatives (法国); University Sorbonne Paris Nord (巴黎北部索邦大学, France); University of Illinois Chicago (伊利诺伊大学芝加哥分校, USA); Duly Health and Care (美国)
类目: Computer Vision and Pattern Recognition (cs.CV); Human-Computer Interaction (cs.HC)
备注: This paper was accepted at ETRA 2025 Japan

点击查看摘要

Abstract:Eye-tracking analysis plays a vital role in medical imaging, providing key insights into how radiologists visually interpret and diagnose clinical cases. In this work, we first analyze radiologists’ attention and agreement by measuring the distribution of various eye-movement patterns, including saccades direction, amplitude, and their joint distribution. These metrics help uncover patterns in attention allocation and diagnostic strategies. Furthermore, we investigate whether and how doctors’ gaze behavior shifts when viewing authentic (Real) versus deep-learning-generated (Fake) images. To achieve this, we examine fixation bias maps, focusing on first, last, short, and longest fixations independently, along with detailed saccades patterns, to quantify differences in gaze distribution and visual saliency between authentic and synthetic images.
zh

[CV-38] NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: KwaiSR Dataset and Study CVPR2025 CVPR

链接: https://arxiv.org/abs/2504.15003
作者: Xin Li,Xijun Wang,Bingchen Li,Kun Yuan,Yizhen Shao,Suhang Yao,Ming Sun,Chao Zhou,Radu Timofte,Zhibo Chen
机构: University of Science and Technology of China (中国科学技术大学); KuaiShou Technology (快手科技); University of Würzburg (维尔茨堡大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: KwaiSR dataset, a new dataset for image super-resolution, used for CVPR NTIRE 2025 Challenge; CVPR 2025 workshop paper

点击查看摘要

[CV-39] Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation

链接: https://arxiv.org/abs/2504.14988
作者: Hong-Tao Yu,Xiu-Shen Wei,Yuxin Peng,Serge Belongie
机构: School of Computer Science and Engineering, Southeast University (东南大学), China; Wangxuan Institute of Computer Technology, Peking University (北京大学王选计算机研究所), China; University of Copenhagen (哥本哈根大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-40] RealisDance-DiT: Simple yet Strong Baseline towards Controllable Character Animation in the Wild

链接: https://arxiv.org/abs/2504.14977
作者: Jingkai Zhou,Yifan Wu,Shikai Li,Min Wei,Chao Fan,Weihua Chen,Wei Jiang,Fan Wang
机构: DAMO Academy, Alibaba Group (达摩院，阿里巴巴集团); Zhejiang University (浙江大学); Hupan Lab (湖畔实验室); Southern University of Science and Technology (南方科技大学); Shenzhen University (深圳大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project Page: this https URL

点击查看摘要

[CV-41] Cyc3D: Fine-grained Controllable 3D Generation via Cycle Consistency Regularization

链接: https://arxiv.org/abs/2504.14975
作者: Hongbin Xu,Chaohui Yu,Feng Xiao,Jiazheng Xing,Hai Ci,Weitao Chen,Ming Li
机构: South China University of Technology (华南理工大学); Alibaba Group (阿里巴巴集团); 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）); National University of Technology (国家理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Preprint version. The code will be open after finishing the reviewing process

点击查看摘要

[CV-42] 3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations

链接: https://arxiv.org/abs/2504.14967
作者: Yating Wang,Xuan Wang,Ran Yi,Yanbo Fan,Jichen Hu,Jingcheng Zhu,Lizhuang Ma
机构: Shanghai Jiao Tong University (上海交通大学); AntGroup Research (蚂蚁集团研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-43] PIV-FlowDiffuser:Transfer-learning-based denoising diffusion models for PIV

链接: https://arxiv.org/abs/2504.14952
作者: Qianyu Zhu,Junjie Wang,Jeremiah Hu,Jia Ai,Yong Lee
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-44] WIG: Two-Step Image Generation using Segmentation Masks in Diffusion Models

链接: https://arxiv.org/abs/2504.14933
作者: Mazharul Islam Rakib,Showrin Rahman,Joyanta Jyoti Mondal,Xi Xiao,David Lewis,Alessandra Mileo,Meem Arafat Manab
机构: BRAC University (BRAC大学), Dhaka, Bangladesh; University of Delaware (特拉华大学), Newark, DE, USA; University of Alabama at Birmingham (阿拉巴马大学伯明翰分校), Birmingham, AL, USA; ADAPT SFI Research Center (ADAPT SFI 研究中心), Trinity College Dublin (都柏林三一学院), Dublin, Ireland; Insight SFI Research Center for Data Analytics (Insight SFI 数据分析研究中心), Dublin City University (都柏林城市大学), Dublin, Ireland; Dublin City University (都柏林城市大学), Dublin, Ireland
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 16 pages, 9 figures, preprint

点击查看摘要

[CV-45] Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos

链接: https://arxiv.org/abs/2504.14921
作者: Songping Wang,Hanqing Liu,Yueming Lyu,Xiantao Hu,Ziwen He,Wei Wang,Caifeng Shan,Liang Wang
机构: School of Intelligence Science and Technology, Nanjing University (南京大学智能科学与技术学院); School of Software, Beihang University (北京航空航天大学软件学院); School of Computer Science and Engineering, Nanjing University of Science and Technology (南京理工大学计算机科学与工程学院); Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology (教育部南京信息工程大学数字取证工程研究中心); State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Center for Research on Intelligent Perception and Computing (CRIPAC), Institute of Automation Chinese Academy of Sciences (中国科学院自动化研究所多模态人工智能系统国家重点实验室智能感知与计算研究中心)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-46] DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding CVPR2025

链接: https://arxiv.org/abs/2504.14920
作者: Geng Li,Jinglin Xu,Yunzhen Zhao,Yuxin Peng
机构: Wangxuan Institute of Computer Technology, Peking University (王选计算机技术研究所，北京大学); School of Intelligence Science and Technology, University of Science and Technology Beijing (智能科学与技术学院，北京科技大学); Tencent Beijing Research (腾讯北京研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025 (Hightlight). Project page with code: this https URL

点击查看摘要

[CV-47] GenCLIP: Generalizing CLIP Prompts for Zero-shot Anomaly Detection

链接: https://arxiv.org/abs/2504.14919
作者: Donghyeong Kim,Chaewon Park,Suhwan Cho,Hyeonjeong Lim,Minseok Kang,Jungho Lee,Sangyoun Lee
机构: Yonsei University (延世大学), Seoul, Korea
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-48] Guidelines for External Disturbance Factors in the Use of OCR in Real-World Environments

链接: https://arxiv.org/abs/2504.14913
作者: Kenji Iwata(1),Eiki Ishidera(2),Toshifumi Yamaai(3),Yutaka Satoh(1),Hiroshi Tanaka(4),Katsuhiko Takahashi(2),Akio Furuhata(5),Yoshihisa Tanabe,Hiroshi Matsumura((1) National Institute of Advanced Industrial Science and Technology (AIST), (2) NEC Corporation, (3) Ricoh Co., Ltd., (4) Fujitsu Limited, (5) Toshiba Digital Solutions Corporation)
机构: National Institute of Advanced Industrial Science and Technology (AIST); NEC Corporation; Ricoh Co., Ltd.; Fujitsu Limited; Toshiba Digital Solutions Corporation
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 16 pages, 14 figures

点击查看摘要

[CV-49] Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation

链接: https://arxiv.org/abs/2504.14899
作者: Chenjie Cao,Jingkai Zhou,Shikai Li,Jingyun Liang,Chaohui Yu,Fan Wang,Xiangyang Xue,Yanwei Fu
机构: Alibaba (阿里巴巴)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-50] WMKA-Net: A Weighted Multi-Kernel Attention NetworkMethod for Retinal Vessel Segmentation

链接: https://arxiv.org/abs/2504.14888
作者: Xinran Xu,Yuliang Ma,Sifu Cai
机构: Hangzhou Dianzi University (杭州电子科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-51] Memory-Augmented Dual-Decoder Networks for Multi-Class Unsupervised Anomaly Detection

链接: https://arxiv.org/abs/2504.14884
作者: Jingyu Xing,Chenwei Tang,Tao Wang,Rong Xiao,Wei Ju,Ji-Zhe Zhou,Liangli Zhen,Jiancheng Lv
机构: Sichuan University (四川大学); Institute of High Performance Computing, A*STAR (高性能计算研究所, 新加坡科技研究局)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-52] Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness

链接: https://arxiv.org/abs/2504.14882
作者: Mojtaba Kolahdouzi,Hatice Gunes,Ali Etemad
机构: Department of Electrical and Computer Engineering, Queen’s University, Canada (电气与计算机工程系，皇后大学，加拿大); Department of Computer Science and Technology, University of Cambridge, United Kingdom (计算机科学与技术系，剑桥大学，英国)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
备注:

点击查看摘要

[CV-53] Collaborative Enhancement Network for Low-quality Multi-spectral Vehicle Re-identification

链接: https://arxiv.org/abs/2504.14877
作者: Aihua Zheng,Yongqi Sun,Zi Wang,Chenglong Li,Jin Tang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-54] ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams CVPR2025

链接: https://arxiv.org/abs/2504.14875
作者: Chris Dongjoo Kim,Jihwan Moon,Sangwoo Moon,Heeseung Yun,Sihaeng Lee,Aniruddha Kembhavi,Soonyoung Lee,Gunhee Kim,Sangho Lee,Christopher Clark
机构: Seoul National University (首尔国立大学); LG AI Research (LG AI 研究); Allen Institute for AI (艾伦人工智能研究所)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: CVPR 2025 (main conference)

点击查看摘要

[CV-55] win Co-Adaptive Dialogue for Progressive Image Generation

链接: https://arxiv.org/abs/2504.14868
作者: Jianhui Wang,Yangfan He,Yan Zhong,Xinyuan Song,Jiayi Su,Yuheng Feng,Hongyang He,Wenyu Zhu,Xinhang Yuan,Kuan Lu,Menghao Huo,Miao Zhang,Keqin Li,Jiaqi Chen,Tianyu Shi,Xueqian Wang
机构: University of Electronic Science and Technology of China (电子科技大学); University of Minnesota—Twin Cities (明尼苏达大学双城校区); Peking University (北京大学); Emory University (埃默里大学); Xiamen University (厦门大学); Baidu (百度); University of Warwick (华威大学); Tsinghua University (清华大学); Washington University, Saint Louis (圣路易斯华盛顿大学); Cornell University (康奈尔大学); Santa Clara University (圣克拉拉大学); Independent Researcher (独立研究者); University of Toronto (多伦多大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-56] Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer CVPR2025

链接: https://arxiv.org/abs/2504.14860
作者: Ziyi Liu,Yangcen Liu
机构: University of Science and Technology Beijing (北京科技大学); Georgia Institute of Technology (乔治亚理工学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: CVPR 2025: IEEE Conference on Computer Vision and Pattern Recognition

点击查看摘要

[CV-57] Object-Level Verbalized Confidence Calibration in Vision-Language Models via Semantic Perturbation

链接: https://arxiv.org/abs/2504.14848
作者: Yunpu Zhao,Rui Zhang,Junbin Xiao,Ruibo Hou,Jiaming Guo,Zihao Zhang,Yifan Hao,Yunji Chen
机构: University of Science and Technology of China (中国科学技术大学); SKL of Processors, Institute of Computing Technology, CAS (处理器体系结构国家重点实验室, 中国科学院计算技术研究所); National University of Singapore (新加坡国立大学); University of Chinese Academy of Sciences (中国科学院大学); University of Illinois at Urbana-Champaign (伊利诺伊大学香槟分校)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-58] Reliable Multi-Modal Object Re-Identification via Modality-Aware Graph Reasoning

链接: https://arxiv.org/abs/2504.14847
作者: Xixi Wan,Aihua Zheng,Zi Wang,Bo Jiang,Jin Tang,Jixin Ma
机构: Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, Anhui University (安徽大学人工智能学院, 安徽省信息材料与智能感知重点实验室, 安徽省人工智能重点实验室), Hefei, China; School of Biomedical Engineering, Anhui Medical University (安徽医科大学生物医学工程学院), and the Key Laboratory of Intelligent Computing & Signal Processing, Ministry of Education, Anhui University (教育部智能计算与信号处理重点实验室, 安徽大学), Hefei, China; Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University (安徽大学计算机科学与技术学院, 多模态认知计算安徽省重点实验室), Hefei, China; School of Computing and Mathematical Sciences, University of Greenwich (格林威治大学计算与数学科学学院), London SE10 9LS, UK
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-59] Distribution-aware Dataset Distillation for Efficient Image Restoration

链接: https://arxiv.org/abs/2504.14826
作者: Zhuoran Zheng,Xin Su,Chen Wu,Xiuyi Jia
机构: Sun Yat‑sen University (中山大学); Fuzhou University (福州大学); University of Science and Technology of China (中国科学技术大学); Nanjing University of Science and Technology (南京理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-60] ECViT: Efficient Convolutional Vision Transformer with Local-Attention and Multi-scale Stages

链接: https://arxiv.org/abs/2504.14825
作者: Zhoujie Qian
机构: School of Computer Engineering and Science (计算机工程与科学学院), Shanghai University (上海大学), Shanghai, China
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-61] What Lurks Within? Concept Auditing for Shared Diffusion Models at Scale

链接: https://arxiv.org/abs/2504.14815
作者: Xiaoyong Yuan,Xiaolong Ma,Linke Guo,Lan Zhang
机构: Clemson University (克莱姆森大学)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV)
备注: 17 pages, 15 figures

点击查看摘要

[CV-62] Real-Time Sleepiness Detection for Driver State Monitoring System

链接: https://arxiv.org/abs/2504.14807
作者: Deepak Ghimire,Sunghwan Jeong,Sunhong Yoon,Sanghyun Park,Juhwan Choi
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
备注: 8 pages, published in GST 2015

点击查看摘要

[CV-63] A Survey on Small Sample Imbalance Problem: Metrics Feature Analysis and Solutions

链接: https://arxiv.org/abs/2504.14800
作者: Shuxian Zhao,Jie Gui,Minjing Dong,Baosheng Yu,Zhipeng Gui,Lu Dong,Yuan Yan Tang,James Tin-Yau Kwok
机构: School of Cyber Science and Engineering, Southeast University (东南大学网络空间安全学院); Engineering Research Center of Blockchain Application, Supervision and Management, Southeast University (东南大学区块链应用与监管工程研究中心); Purple Mountain Laboratories (紫金山实验室); Department of Computer Science, City University of Hong Kong (香港城市大学计算机科学系); Lee Kong Chian School of Medicine at Nanyang Technological University (新加坡南洋理工大学李光前医学院); School of Remote Sensing and Information Engineering, Wuhan University (武汉大学遥感信息工程学院); Collaborative Innovation Center of Geospatial Technology, Wuhan University (武汉大学地理空间信息技术协同创新中心); Department of Computer and Information Science, University of Macau (澳门大学计算机与信息科学系); Department of Computer Science and Engineering, The Hong Kong University of Science and Technology (香港科技大学计算机科学与工程系)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-64] Verifying Robust Unlearning: Probing Residual Knowledge in Unlearned Models

链接: https://arxiv.org/abs/2504.14798
作者: Hao Xuan,Xingyu Li
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-65] When Cloud Removal Meets Diffusion Model in Remote Sensing

链接: https://arxiv.org/abs/2504.14785
作者: Zhenyu Yu,Mohd Yamani Idna Idris,Pei Wang
机构: Kunming University of Science and Technology (昆明理工大学); Universiti Malaya (马来亚大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-66] How Effective Can Dropout Be in Multiple Instance Learning ?

链接: https://arxiv.org/abs/2504.14783
作者: Wenhui Zhu,Peijie Qiu,Xiwen Chen,Zhangsihao Yang,Aristeidis Sotiras,Abolfazl Razi,Yalin Wang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV); Machine Learning (stat.ML)
备注:

点击查看摘要

[CV-67] Advancing Video Anomaly Detection: A Bi-Directional Hybrid Framework for Enhanced Single- and Multi-Task Approaches

链接: https://arxiv.org/abs/2504.14753
作者: Guodong Shen,Yuqi Ouyang,Junru Lu,Yixuan Yang,Victor Sanchez
机构: Computer Science Department at the University of Warwick (华威大学计算机科学系), Coventry, United Kingdom; College of Computer Science, Sichuan University (四川大学计算机学院), Chengdu, China
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注: Accepted by IEEE Transactions on Image Processing (TIP)

点击查看摘要

[CV-68] SuperCL: Superpixel Guided Contrastive Learning for Medical Image Segmentation Pre-training

链接: https://arxiv.org/abs/2504.14737
作者: Shuang Zeng,Lei Zhu,Xinliang Zhang,Hangzhou He,Yanye Lu
机构: Institute of Medical Technology, Peking University Health Science Center, Peking University (北京大学健康科学中心医学技术研究所，北京大学), Department of Biomedical Engineering, Peking University (北京大学生物医学工程系), National Biomedical Imaging Center, Peking University (北京大学国家生物医学成像中心), Institute of Biomedical Engineering, Shenzhen Bay Laboratory (深圳湾实验室生物医学工程研究所), Institute of Biomedical Engineering, Peking University Shenzhen Graduate School (北京大学深圳研究生院生物医学工程研究所)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-69] ChronoRoot 2.0: An Open AI-Powered Platform for 2D Temporal Plant Phenotyping

链接: https://arxiv.org/abs/2504.14736
作者: Nicolás Gaggion,Rodrigo Bonazzola,María Florencia Legascue,María Florencia Mammarella,Florencia Sol Rodriguez,Federico Emanuel Aballay,Florencia Belén Catulo,Andana Barrios,Franco Accavallo,Santiago Nahuel Villarreal,Martin Crespi,Martiniano María Ricardi,Ezequiel Petrillo,Thomas Blein,Federico Ariel,Enzo Ferrante
机构: Instituto de Fisiología, Biología Molecular y Neurociencias (IFIBYNE), CONICET-Universidad de Buenos Aires (阿根廷); APOLO Biotech (阿根廷); Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional sinc(i), CONICET-Universidad Nacional del Litoral (阿根廷); Université Paris-Saclay, CNRS, INRAE, Université Evry, Institute of Plant Sciences Paris-Saclay (IPS2), 91190 Gif-sur-Yvette, France (法国); Université Paris Cité, CNRS, INRAE, Institute of Plant Sciences Paris-Saclay (IPS2), 91190 Gif-sur-Yvette, France (法国); Instituto de Ciencias de la Computación, CONICET-Universidad de Buenos Aires (阿根廷)
类目: Computer Vision and Pattern Recognition (cs.CV); Quantitative Methods (q-bio.QM)
备注:

点击查看摘要

[CV-70] Semi-parametric Memory Consolidation: Towards Brain-like Deep Continual Learning

链接: https://arxiv.org/abs/2504.14727
作者: Geng Liu,Fei Zhu,Rong Feng,Zhiqiang Yi,Shiqi Wang,Gaofeng Meng,Zhaoxiang Zhang
机构: Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences, Hong Kong SAR, China.; Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China.; The Department of Neurosurgery, Peking University First Hospital, Beijing, China.; State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China.
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-71] APIP3D: Tracking Any Point in Persistent 3D Geometry

链接: https://arxiv.org/abs/2504.14717
作者: Bowei Zhang,Lei Ke,Adam W. Harley,Katerina Fragkiadaki
机构: Carnegie Mellon University (卡内基梅隆大学); Peking University (北京大学); Stanford University (斯坦福大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Long-term feed-forward 3D point tracking in persistent 3D point maps. Code: this https URL

点击查看摘要

[CV-72] Med-2D SegNet: A Light Weight Deep Neural Network for Medical 2D Image Segmentation

链接: https://arxiv.org/abs/2504.14715
作者: Md. Sanaullah Chowdhury,Salauddin Tapu,Noyon Kumar Sarkar,Ferdous Bin Ali,Lameya Sabrin
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-73] Exposing the Copycat Problem of Imitation-based Planner: A Novel Closed-Loop Simulator Causal Benchmark and Joint IL-RL Baseline

链接: https://arxiv.org/abs/2504.14709
作者: Hui Zhou,Shaoshuai Shi,Hongsheng Li
机构: Department of Electronic Engineering, The Chinese University of Hong Kong (香港中文大学电子工程系); DiDi Global (滴滴全球)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-74] me Frequency Analysis of EMG Signal for Gesture Recognition using Fine grained Features

链接: https://arxiv.org/abs/2504.14708
作者: Parshuram N. Aarotale,Ajita Rattani
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-75] IXGS-Intraoperative 3D Reconstruction from Sparse Arbitrarily Posed Real X-rays

链接: https://arxiv.org/abs/2504.14699
作者: Sascha Jecklin,Aidana Massalimova,Ruyi Zha,Lilian Calvet,Christoph J. Laux,Mazda Farshad,Philipp Fürnstahl
机构: Balgrist University Hospital (巴尔格里斯特大学医院); The Australian National University (澳大利亚国立大学); Department of Orthopedics, Balgrist University Hospital, University of Zurich (巴尔格里斯特大学医院，苏黎世大学矫形外科系)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-76] Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark

链接: https://arxiv.org/abs/2504.14693
作者: Enxin Song,Wenhao Chai,Weili Xu,Jianwen Xie,Yuxuan Liu,Gaoang Wang
机构: Zhejiang University (浙江大学); University of Washington (华盛顿大学); University of Illinois Urbana-Champaign (伊利诺伊大学香槟分校); Lambda, Inc.
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Code, docs, and benchmark are all avaliable at this https URL

点击查看摘要

[CV-77] Seurat: From Moving Points to Depth CVPR2025 CVPR

链接: https://arxiv.org/abs/2504.14687
作者: Seokju Cho,Jiahui Huang,Seungryong Kim,Joon-Young Lee
机构: KAIST AI (KAIST AI); Adobe Research (Adobe 研究)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: CVPR 2025 Highlight. Project page: this https URL

点击查看摘要

[CV-78] Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens CVPR2025

链接: https://arxiv.org/abs/2504.14666
作者: Kaihang Pan,Wang Lin,Zhongqi Yue,Tenglong Ao,Liyu Jia,Wei Zhao,Juncheng Li,Siliang Tang,Hanwang Zhang
机构: Zhejiang University (浙江大学); Nanyang Technological University (南洋理工大学); Peking University (北京大学); Huawei Singapore Research Center (华为新加坡研究中心)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025 (Oral)

点击查看摘要

[CV-79] DMPCN: Dynamic Modulated Predictive Coding Network with Hybrid Feedback Representations

链接: https://arxiv.org/abs/2504.14665
作者: A S M Sharifuzzaman Sagar,Yu Chen,Jun Hoong Chan
机构: Department of Artificial Intelligence and Robotics (人工智能与机器人系), Sejong University (世宗大学); AI Lab (人工智能实验室), MetaSyntec (MetaSyntec公司); School of Computer Science (计算机科学学院), Peking University (北京大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-80] Frequency-domain Learning with Kernel Prior for Blind Image Deblurring

链接: https://arxiv.org/abs/2504.14664
作者: Jixiang Sun,Fei Lei,Jiawei Zhang,Wenxiu Sun,Yujiu Yang
机构: Tsinghua University (清华大学); Sensetime Research (商汤科技研究部)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-81] Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning ICLR2025

链接: https://arxiv.org/abs/2504.14662
作者: Yeoreum Lee,Jinwook Jung,Sungyong Baik
机构: Hanyang University (汉阳大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: ICLR 2025

点击查看摘要

[CV-82] EmoSEM: Segment and Explain Emotion Stimuli in Visual Art

链接: https://arxiv.org/abs/2504.14658
作者: Jing Zhang,Dan Guo,Zhangbin Li,Meng Wang
机构: Hefei University of Technology (合肥工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-83] Relation-R1: Cognitive Chain-of-Thought Guided Reinforcement Learning for Unified Relational Comprehension

链接: https://arxiv.org/abs/2504.14642
作者: Lin Li,Wei Chen,Jiahui Li,Long Chen
机构: The Hong Kong University of Science and Technology (香港科技大学); ACCESS – AI Chip Center for Emerging Smart Systems (ACCESS–新兴智能系统AI芯片中心); Zhejiang University (浙江大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Ongoing project

点击查看摘要

[CV-84] NVSMask3D: Hard Visual Prompting with Camera Pose Interpolation for 3D Open Vocabulary Instance Segmentation

链接: https://arxiv.org/abs/2504.14638
作者: Junyuan Fang(1 and 2),Zihan Wang(1),Yejun Zhang(1),Shuzhe Wang(1),Iaroslav Melekhov(1),Juho Kannala(1 and 3) ((1) Aalto University, Espoo, Finland, (2) University of Helsinki, Helsinki, Finland, (3) University of Oulu, Oulu, Finland)
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 15 pages, 4 figures, Scandinavian Conference on Image Analysis 2025

点击查看摘要

[CV-85] Latent Representations for Visual Proprioception in Inexpensive Robots

链接: https://arxiv.org/abs/2504.14634
作者: Sahara Sheikholeslami,Ladislau Bölöni
机构: University of Central Florida (中佛罗里达大学)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-86] MSAD-Net: Multiscale and Spatial Attention-based Dense Network for Lung Cancer Classification

链接: https://arxiv.org/abs/2504.14626
作者: Santanu Roy,Shweta Singh,Palak Sahu,Ashvath Suresh,Debashish Das
机构: Computer Science and Engineering Department, NIIT University (尼蒂学院), Jaipur, India; CSE department, Christ (Deemed to be University) (基督大学), Bangalore, India; Faculty of Computing, Engineering and the Built Environment, Birmingham City University (伯明翰城市大学), UK
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-87] alk is Not Always Cheap: Promoting Wireless Sensing Models with Text Prompts

链接: https://arxiv.org/abs/2504.14621
作者: Zhenkui Yang,Zeyi Huang,Ge Wang,Han Ding,Tony Xiao Han,Fei Wang
机构: Xi’an Jiaotong University (西安交通大学); University of Wisconsin - Madison (威斯康星大学麦迪逊分校); Huawei Technologies Ltd. (华为技术有限公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages

点击查看摘要

[CV-88] VM-BHINet:Vision Mamba Bimanual Hand Interaction Network for 3D Interacting Hand Mesh Recovery From a Single RGB Image

链接: https://arxiv.org/abs/2504.14618
作者: Han Bi,Ge Yu,Yu He,Wenzhuo Liu,Zijie Zheng
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-89] MP-Mat: A 3D-and-Instance-Aware Human Matting and Editing Framework with Multiplane Representation ICLR2025

链接: https://arxiv.org/abs/2504.14606
作者: Siyi Jiao,Wenzheng Zeng,Yerong Li,Huayu Zhang,Changxin Gao,Nong Sang,Mike Zheng Shou
机构: Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology (华中科技大学), China; Show Lab, National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by ICLR 2025

点击查看摘要

[CV-90] NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results WWW

链接: https://arxiv.org/abs/2504.14600
作者: Zheng Chen,Jingkai Wang,Kai Liu,Jue Gong,Lei Sun,Zongwei Wu,Radu Timofte,Yulun Zhang,Jianxing Zhang,Jinlong Wu,Jun Wang,Zheng Xie,Hakjae Jeon,Suejin Han,Hyung-Ju Chun,Hyunhee Park,Zhicun Yin,Junjie Chen,Ming Liu,Xiaoming Li,Chao Zhou,Wangmeng Zuo,Weixia Zhang,Dingquan Li,Kede Ma,Yun Zhang,Zhuofan Zheng,Yuyue Liu,Shizhen Tang,Zihao Zhang,Yi Ning,Hao Jiang,Wenjie An,Kangmeng Yu,Chenyang Wang,Kui Jiang,Xianming Liu,Junjun Jiang,Yingfu Zhang,Gang He,Siqi Wang,Kepeng Xu,Zhenyang Liu,Changxin Zhou,Shanlan Shen,Yubo Duan,Yiang Chen,Jin Guo,Mengru Yang,Jen-Wei Lee,Chia-Ming Lee,Chih-Chung Hsu,Hu Peng,Chunming He
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: NTIRE 2025 webpage: this https URL . Code: this https URL

点击查看摘要

[CV-91] Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction CVPR2025

链接: https://arxiv.org/abs/2504.14588
作者: Wenke Xia,Ruoxuan Feng,Dong Wang,Di Hu
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); Shanghai AI Laboratory (上海人工智能实验室)
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR2025

点击查看摘要

[CV-92] Using street view imagery and deep generative modeling for estimating the health of urban forests ICLR2025

链接: https://arxiv.org/abs/2504.14583
作者: Akshit Gupta,Remko Uijlenhoet
机构: TU Delft (代尔夫特理工大学); TU Delft (代尔夫特理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Computers and Society (cs.CY)
备注: Accepted at ICLR 2025 Workshop

点击查看摘要

[CV-93] NTIRE 2025 Challenge on Image Super-Resolution (times4): Methods and Results WWW

链接: https://arxiv.org/abs/2504.14582
作者: Zheng Chen,Kai Liu,Jue Gong,Jingkai Wang,Lei Sun,Zongwei Wu,Radu Timofte,Yulun Zhang,Xiangyu Kong,Xiaoxuan Yu,Hyunhee Park,Suejin Han,Hakjae Jeon,Dafeng Zhang,Hyung-Ju Chun,Donghun Ryou,Inju Ha,Bohyung Han,Lu Zhao,Yuyi Zhang,Pengyu Yan,Jiawei Hu,Pengwei Liu,Fengjun Guo,Hongyuan Yu,Pufan Xu,Zhijuan Huang,Shuyuan Cui,Peng Guo,Jiahui Liu,Dongkai Zhang,Heng Zhang,Huiyuan Fu,Huadong Ma,Yanhui Guo,Sisi Tian,Xin Liu,Jinwen Liang,Jie Liu,Jie Tang,Gangshan Wu,Zeyu Xiao,Zhuoyuan Li,Yinxiang Zhang,Wenxuan Cai,Vijayalaxmi Ashok Aralikatti,Nikhil Akalwadi,G Gyaneshwar Rao,Chaitra Desai,Ramesh Ashok Tabib,Uma Mudenagudi,Marcos V. Conde,Alejandro Merino,Bruno Longarela,Javier Abad,Weijun Yuan,Zhan Li,Zhanglu Chen,Boyang Yao,Aagam Jain,Milan Kumar Singh,Ankit Kumar,Shubh Kawa,Divyavardhan Singh,Anjali Sarvaiya,Kishor Upla,Raghavendra Ramachandra,Chia-Ming Lee,Yu-Fan Lin,Chih-Chung Hsu,Risheek V Hiremath,Yashaswini Palani,Yuxuan Jiang,Qiang Zhu,Siyue Teng,Fan Zhang,Shuyuan Zhu,Bing Zeng,David Bull,Jingwei Liao,Yuqing Yang,Wenda Shao,Junyi Zhao,Qisheng Xu,Kele Xu,Sunder Ali Khowaja,Ik Hyun Lee,Snehal Singh Tomar,Rajarshi Ray,Klaus Mueller,Sachin Chaudhary,Surya Vashisth,Akshay Dudhane,Praful Hambarde,Satya Naryan Tazi,Prashant Patil,Santosh Kumar Vipparthi,Subrahmanyam Murala,Bilel Benjdira,Anas M. Ali
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: NTIRE 2025 webpage: this https URL . Code: this https URL

点击查看摘要

[CV-94] SMTT: Novel Structured Multi-task Tracking with Graph-Regularized Sparse Representation for Robust Thermal Infrared Target Tracking

链接: https://arxiv.org/abs/2504.14566
作者: Shang Zhang,HuiPan Guan,XiaoBo Ding,Ruoyan Xiong,Yue Zhang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-95] REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-to-Image Diffusion Models

链接: https://arxiv.org/abs/2504.14554
作者: Chongye Guo,Jinhu Fu,Junfeng Fang,Kun Wang,Guorui Feng
机构: Shanghai University(上海大学); Beijing University of Posts and Telecommunications(北京邮电大学); National University of Singapore(新加坡国立大学); Nanyang Technological University(南洋理工大学); Shanghai University(上海大学)
类目: Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 7 figures

点击查看摘要

[CV-96] Grounding-MD: Grounded Video-language Pre-training for Open-World Moment Detection

链接: https://arxiv.org/abs/2504.14553
作者: Weijun Zhuang,Qizhang Li,Xin Li,Ming Liu,Xiaopeng Hong,Feng Gao,Fan Yang,Wangmeng Zuo
机构: Harbin Institute of Technology (哈尔滨工业大学); Pengcheng Laboratory (鹏城实验室); Peking University (北京大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-97] VGNC: Reducing the Overfitting of Sparse-view 3DGS via Validation-guided Gaussian Number Control

链接: https://arxiv.org/abs/2504.14548
作者: Lifeng Lin,Rongfeng Lu,Quan Chen,Haofan Ren,Ming Lu,Yaoqi Sun,Chenggang Yan,Anke Xue
机构: Hangzhou Dianzi University (杭州电子科技大学); Intel Labs China (英特尔中国实验室); Lishui University (丽水大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 10 pages,8 figures

点击查看摘要

[CV-98] owards Model Resistant to Transferable Adversarial Examples via Trigger Activation

链接: https://arxiv.org/abs/2504.14541
作者: Yi Yu,Song Xia,Xun Lin,Chenqi Kong,Wenhan Yang,Shijian Lu,Yap-Peng Tan,Alex C. Kot
机构: Rapid-Rich Object Search (ROSE) Lab, Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore (南洋理工大学); PengCheng Laboratory, Shenzhen, China (鹏城实验室); School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore (南洋理工大学电气与电子工程学院); School of Computer Science and Engineering, Beihang University, Beijing, China (北京航空航天大学计算机科学与工程学院); College of Computing and Data Science, Nanyang Technological University, Singapore (南洋理工大学计算与数据科学学院); Rapid-Rich Object Search (ROSE) Lab, Nanyang Technological University (NTU), Singapore (南洋理工大学快速丰富对象搜索（ROSE）实验室); National Research Foundation, Singapore (新加坡国家研究基金会); Infocomm Media Development Authority, Singapore (新加坡资讯通信媒体发展局); Basic and Frontier Research Project of PCL (鹏城实验室基础前沿研究项目); Major Key Project of PCL (鹏城实验室重大关键项目); Guangdong Basic and Applied Basic Research Foundation, China (广东基础与应用基础研究基金)
类目: Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Accepted by IEEE TIFS 2025

点击查看摘要

[CV-99] FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models

链接: https://arxiv.org/abs/2504.14535
作者: Kuanting Wu,Kei Ota,Asako Kanezaki
机构: Science Tokyo (科学东京); Mitsubishi Electric (三菱电机)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-100] SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization

链接: https://arxiv.org/abs/2504.14534
作者: Liang Peng,Boxi Wu,Haoran Cheng,Yibo Zhao,Xiaofei He
机构: FABU Inc.; Zhejiang University (浙江大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-101] Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction

链接: https://arxiv.org/abs/2504.14516
作者: Weirong Chen,Ganlin Zhang,Felix Wimbauer,Rui Wang,Nikita Araslanov,Andrea Vedaldi,Daniel Cremers
机构: TU Munich (慕尼黑工业大学); MCML (未知); University of Oxford (牛津大学); Microsoft (微软)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-102] DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning

链接: https://arxiv.org/abs/2504.14509
作者: Fulong Ye,Miao Hua,Pengze Zhang,Xinghui Li,Qichao Sun,Songtao Zhao,Qian He,Xinglong Wu
机构: Intelligent Creation Team, ByteDance (字节跳动智能创作团队)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-103] STARS: Sparse Learning Correlation Filter with Spatio-temporal Regularization and Super-resolution Reconstruction for Thermal Infrared Target Tracking

链接: https://arxiv.org/abs/2504.14491
作者: Shang Zhang,Xiaobo Ding,Huanbin Zhang,Ruoyan Xiong,Yue Zhang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-104] Vision-Centric Representation-Efficient Fine-Tuning for Robust Universal Foreground Segmentation

链接: https://arxiv.org/abs/2504.14481
作者: Guoyi Zhang,Siyang Chen,Guangsheng Xu,Han Wang,Xiaohu Zhang
机构: School of Aeronautics and Astronautics, 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-105] Efficient Implicit Neural Compression of Point Clouds via Learnable Activation in Latent Space

链接: https://arxiv.org/abs/2504.14471
作者: Yichi Zhang,Qianqian Yang
机构: Zhejiang University (浙江大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages

点击查看摘要

[CV-106] urbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis

链接: https://arxiv.org/abs/2504.14470
作者: Jingjing Ren,Wenbo Li,Zhongdao Wang,Haoze Sun,Bangzhen Liu,Haoyu Chen,Jiaqi Xu,Aoxue Li,Shifeng Zhang,Bin Shao,Yong Guo,Lei Zhu
机构: The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学（广州）); Huawei Noah’s Ark Lab (华为诺亚方舟实验室); South China University of Technology (华南理工大学); Max Planck Institute for Informatics (马克斯·普朗克计算机科学研究所); The Hong Kong University of Science and Technology (香港科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Webpage at this https URL

点击查看摘要

[CV-107] LGD: Leverag ing Generative Descriptions for Zero-Shot Referring Image Segmentation

链接: https://arxiv.org/abs/2504.14467
作者: Jiachen Li,Qing Xie,Xiaohan Yu,Hongyun Wang,Jinyu Xu,Yongjian Liu,Yongsheng Gao
机构: unknown
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-108] Metamon-GS: Enhancing Representability with Variance-Guided Densification and Light Encoding

链接: https://arxiv.org/abs/2504.14460
作者: Junyan Su,Baozhu Zhao,Xiaohan Zhang,Qi Liu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-109] Causal Disentanglement for Robust Long-tail Medical Image Generation

链接: https://arxiv.org/abs/2504.14450
作者: Weizhi Nie,Zichun Zhang,Weijie Wang,Bruno Lepri,Anan Liu,Nicu Seb
机构: School of Electrical and Information Engineering, Tianjin University, China (电气与信息工程学院, 天津大学, 中国); Department of Information Engineering and Computer Science, University of Trento, Italy (信息工程与计算机科学系, 意大利特伦托大学); Fondazione Bruno Kessler, Italy (意大利布鲁诺·凯勒基金会)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-110] Neglected Risks: The Disturbing Reality of Childrens Images in Datasets and the Urgent Call for Accountability

链接: https://arxiv.org/abs/2504.14446
作者: Carlos Caetano,Gabriel O. dos Santos,Caio Petrucci,Artur Barros,Camila Laranjeira,Leo S. F. Ribeiro,Júlia F. de Mendonça,Jefersson A. dos Santos,Sandra Avila
机构: Instituto de Computação, Universidade Estadual de Campinas (UNICAMP)(计算研究所，坎皮纳斯州立大学)CampinasBrazil; Departamento de Ciência da Computação, Universidade Federal de Minas Gerais (UFMG)(计算机科学系，米纳斯吉拉斯联邦大学)Belo HorizonteBrazil; Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo (USP)(数学与计算机科学研究所，圣保罗大学)São CarlosBrazil; Instituto Alana(阿拉纳研究所)SalvadorBrazil; School of Computer Science, University of Sheffield(计算机科学学院，谢菲尔德大学)SheffieldUnited Kingdom; Instituto de Computação, Universidade Estadual de Campinas (UNICAMP)(计算研究所，坎皮纳斯州立大学)CampinasBrazil
类目: Computer Vision and Pattern Recognition (cs.CV); Computers and Society (cs.CY); Machine Learning (cs.LG)
备注: ACM Conference on Fairness, Accountability, and Transparency (FAccT 2025)

点击查看摘要

[CV-111] WT-BCP: Wavelet Transform based Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation

链接: https://arxiv.org/abs/2504.14445
作者: Mingya Zhang,Liang Wang,Limei Gu,Tingsheng Ling,Xianping Tao
机构: Nanjing University (南京大学); Jiangsu Provincial Hospital of Traditional Chinese Medicine (江苏省中医院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 6 pages

点击查看摘要

[CV-112] SG-Reg: Generalizable and Efficient Scene Graph Registration

链接: https://arxiv.org/abs/2504.14440
作者: Chuhao Liu,Zhijian Qiao,Jieqi Shi,Ke Wang,Peize Liu,Shaojie Shen
机构: the Hong Kong University of Science and Technology (香港科技大学); Nanjing University (南京大学); Chang’an University (长安大学)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注: IEEE Transactions Robotics Regular Paper

点击查看摘要

[CV-113] ResNetVLLM – Multi-modal Vision LLM for the Video Understanding Task

链接: https://arxiv.org/abs/2504.14432
作者: Ahmad Khalil,Mahmoud Khalil,Alioune Ngom
机构: Dept of Computer Science (计算机科学系), University of Windsor (温莎大学), Windsor, Canada
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-114] ResNetVLLM -2: Addressing ResNetVLLM s Multi-Modal Hallucinations

链接: https://arxiv.org/abs/2504.14429
作者: Ahmad Khalil,Mahmoud Khalil,Alioune Ngom
机构: Dept of Computer Science (计算机科学系), University of Windsor (温莎大学), Windsor, Canada
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-115] Adversarial Attack for RGB-Event based Visual Object Tracking

链接: https://arxiv.org/abs/2504.14423
作者: Qiang Chen,Xiao Wang,Haowen Wang,Bo Jiang,Lin Zhu,Dawei Zhang,Yonghong Tian,Jin Tang
机构: School of Computer Science and Technology, Anhui University (安徽大学计算机科学与技术学院); Beijing Institute of Technology, Beijing, China (北京理工大学，中国); Zhejiang Normal University (浙江师范大学); Peng Cheng Laboratory, Beijing, China. National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, China. School of Electronic and Computer Engineering, Shenzhen, Graduate School, Peking University, China. (鹏城实验室，中国；北京大学多媒体信息处理国家重点实验室；北京大学深圳研究生院电子与计算机工程学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-116] SphereDiff: Tuning-free Omnidirectional Panoramic Image and Video Generation via Spherical Latent Representation

链接: https://arxiv.org/abs/2504.14396
作者: Minho Park,Taewoong Kang,Jooyeol Yun,Sungwon Hwang,Jaegul Choo
机构: Korea Advanced Institute of Science and Technology (KAIST) (韩国科学技术院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-117] Hydra: An Agent ic Reasoning Approach for Enhancing Adversarial Robustness and Mitigating Hallucinations in Vision-Language Models

链接: https://arxiv.org/abs/2504.14395
作者: Chung-En(Johnny)Yu,Hsuan-Chih(Neil)Chen,Brian Jalaian,Nathaniel D. Bastian
机构: University of West Florida (西佛罗里达大学); New York University (纽约大学); United States Military Academy (美国军事学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
备注:

点击查看摘要

[CV-118] How Well Can General Vision-Language Models Learn Medicine By Watching Public Educational Videos?

链接: https://arxiv.org/abs/2504.14391
作者: Rahul Thapa,Andrew Li,Qingyang Wu,Bryan He,Yuki Sahashi,Christina Binder,Angela Zhang,Ben Athiwaratkun,Shuaiwen Leon Song,David Ouyang,James Zou
机构: Stanford University (斯坦福大学); Together AI; University of California, Berkeley (加州大学伯克利分校); University of California, Berkeley (加州大学伯克利分校); Cedars-Sinai Medical Center (西达赛奈医疗中心); University of California, San Francisco (加州大学旧金山分校)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-119] LOOPE: Learnable Optimal Patch Order in Positional Embeddings for Vision Transformers

链接: https://arxiv.org/abs/2504.14386
作者: Md Abtahi Majeed Chowdhury,Md Rifat Ur Rahman,Akil Ahmad Taki
机构: Bangladesh University of Engineering and Technology (孟加拉国工程技术大学), Dhaka (达卡), Bangladesh (孟加拉国)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-120] SEGA: Drivable 3D Gaussian Head Avatar from a Single Image

链接: https://arxiv.org/abs/2504.14373
作者: Chen Guo,Zhuo Su,Jian Wang,Shuang Li,Xu Chang,Zhaohu Li,Yang Zhao,Guidong Wang,Ruqi Huang
机构: Tsinghua Shenzhen International Graduate School (清华大学深圳国际研究生院); ByteDance (字节跳动)
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-121] Efficient Spiking Point Mamba for Point Cloud Analysis

链接: https://arxiv.org/abs/2504.14371
作者: Peixi Wu,Bosong Chai,Menghua Zheng,Wei Li,Zhangchi Hu,Jie Chen,Zheyu Zhang,Hebei Li,Xiaoyan Sun
机构: University of Science and Technology of China (中国科学技术大学); Zhejiang University (浙江大学); Tsingmao Intelligence (青塔智能)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-122] Manipulating Multimodal Agents via Cross-Modal Prompt Injection

链接: https://arxiv.org/abs/2504.14348
作者: Le Wang,Zonghao Ying,Tianyuan Zhang,Siyuan Liang,Shengshan Hu,Mingchuan Zhang,Aishan Liu,Xianglong Liu
机构: Beihang University (北航); Beihang University (北航); Beihang University (北航); unknown; Huazhong University of Science and Technology (华中科技大学); Huazhong University of Science and Technology (华中科技大学); Beihang University (北航)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 17 pages, 4 figures

点击查看摘要

[CV-123] Multispectral airborne laser scanning for tree species classification: a benchmark of machine learning and deep learning algorithms

链接: https://arxiv.org/abs/2504.14337
作者: Josef Taher,Eric Hyyppä,Matti Hyyppä,Klaara Salolahti,Xiaowei Yu,Leena Matikainen,Antero Kukko,Matti Lehtomäki,Harri Kaartinen,Sopitta Thurachen,Paula Litkey,Ville Luoma,Markus Holopainen,Gefei Kong,Hongchao Fan,Petri Rönnholm,Antti Polvivaara,Samuli Junttila,Mikko Vastaranta,Stefano Puliti,Rasmus Astrup,Joel Kostensalo,Mari Myllymäki,Maksymilian Kulicki,Krzysztof Stereńczak,Raul de Paula Pires,Ruben Valbuena,Juan Pedro Carbonell-Rivera,Jesús Torralba,Yi-Chen Chen,Lukas Winiwarter,Markus Hollaus,Gottfried Mandlburger,Narges Takhtkeshha,Fabio Remondino,Maciej Lisiewicz,Bartłomiej Kraszewski,Xinlian Liang,Jianchang Chen,Eero Ahokas,Kirsi Karila,Eugeniu Vezeteu,Petri Manninen,Roope Näsi,Heikki Hyyti,Siiri Pyykkönen,Peilun Hu,Juha Hyyppä
机构: Finnish Geospatial Research Institute FGI (芬兰地质调查研究所 FGI); University of Helsinki (赫尔辛基大学); Aalto University (阿尔托大学); Norwegian University of Science and Technology (挪威科技大学); University of Eastern Finland (东芬兰大学); Norwegian Institute for Bioeconomy Research (NIBIO) (挪威生物经济研究所); Natural Resources Institute Finland (自然研究所芬兰分部); Swedish University of Agricultural Sciences (瑞典农业科学大学); Universitat Politècnica de València (瓦伦西亚理工大学); Technische Universität Wien (维也纳技术大学); Bruno Kessler Foundation (FBK) (布鲁诺凯斯勒基金会); The State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University (武汉大学测绘遥感信息工程国家重点实验室); Forest Research Institute IBL (森林研究所IBL); Geo-Environmental Cartography and Remote Sensing Group (CGAT), Universitat Politècnica de València (瓦伦西亚理工大学地理环境制图与遥感小组)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-124] Visual Prompting for One-shot Controllable Video Editing without Inversion CVPR2025

链接: https://arxiv.org/abs/2504.14335
作者: Zhengbo Zhang,Yuxi Zhou,Duo Peng,Joo-Hwee Lim,Zhigang Tu,De Wen Soh,Lin Geng Foo
机构: Singapore University of Technology and Design (新加坡科技设计大学); Wuhan University (武汉大学); Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore (新加坡科学技术研究局信息通信研究院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: accepted by cvpr2025

点击查看摘要

[CV-125] DCFG: Diverse Cross-Channel Fine-Grained Feature Learning and Progressive Fusion Siamese Tracker for Thermal Infrared Target Tracking

链接: https://arxiv.org/abs/2504.14311
作者: Ruoyan Xiong,Yuke Hou,Princess Retor Torboh,Hui He,Huanbin Zhang,Yue Zhang,Yanpin Wang,Huipan Guan,Shang Zhang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-126] FGSGT: Saliency-Guided Siamese Network Tracker Based on Key Fine-Grained Feature Information for Thermal Infrared Target Tracking

链接: https://arxiv.org/abs/2504.14309
作者: Ruoyan Xiong,Huanbin Zhang,Shentao Wang,Hui He,Yuke Hou,Yue Zhang,Yujie Cui,Huipan Guan,Shang Zhang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-127] Exploring Generalizable Pre-training for Real-world Change Detection via Geometric Estimation

链接: https://arxiv.org/abs/2504.14306
作者: Yitao Zhao,Sen Lei,Nanqing Liu,Heng-Chao Li,Turgay Celik,Qing Zhu
机构: School of Information Science and Technology, Southwest Jiaotong University (西南交通大学信息科学与技术学院); School of Electrical and Information Engineering, University of the Witwatersrand (南非约翰内斯堡大学电气与信息工程学院); Faculty of Engineering and Science, University of Agder (挪威阿格德大学工程与科学学院); Faculty of Geosciences and Engineering, Southwest Jiaotong University (西南交通大学地质与工程学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Submitted to IEEE TGRS

点击查看摘要

[CV-128] Balancing Privacy and Action Performance: A Penalty-Driven Approach to Image Anonymization CVPR

链接: https://arxiv.org/abs/2504.14301
作者: Nazia Aslam,Kamal Nasrollahi
机构: Aalborg University (奥尔堡大学), Denmark; Pioneer Centre for AI (先驱人工智能中心), Denmark; Milestone Systems (Milestone 系统), Denmark
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Multimedia (cs.MM)
备注: Accepted to CVPRW 2025

点击查看摘要

[CV-129] From Missing Pieces to Masterpieces: Image Completion with Context-Adaptive Diffusion

链接: https://arxiv.org/abs/2504.14294
作者: Pourya Shamsolmoali,Masoumeh Zareapoor,Huiyu Zhou,Michael Felsberg,Dacheng Tao,Xuelong Li
机构: Department of Computer Science, University of York (英国约克大学计算机科学系); SCEE, East China Normal University (SCEE, 华东师范大学); Department of Electrical Engineering, Shanghai Jiao Tong University (上海交通大学电气工程系); School of Computing and Mathematical Sciences, University of Leicester (英国莱斯特大学计算与数学科学学院); Computer Vision Laboratory, Linkoping University (瑞典林雪平大学计算机视觉实验室); College of Computing and Data Science, Nanyang Technological University (新加坡南洋理工大学计算与数据科学学院); Institute of Artificial Intelligence (TeleAI), China Telecom (中国电信人工智能研究所)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted in TPAMI

点击查看摘要

[CV-130] owards NSFW-Free Text-to-Image Generation via Safety-Constraint Direct Preference Optimization

链接: https://arxiv.org/abs/2504.14290
作者: Shouwei Ruan,Zhenyu Wu,Yao Huang,Ruochen Zhang,Yitong Sun,Caixin Kang,Xingxing Wei
机构: Beihang University (北京航空航天大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 6 figures

点击查看摘要

[CV-131] ISTD-YOLO: A Multi-Scale Lightweight High-Performance Infrared Small Target Detection Algorithm

链接: https://arxiv.org/abs/2504.14289
作者: Shang Zhang,Yujie Cui,Ruoyan Xiong,Huanbin Zhang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-132] CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey

链接: https://arxiv.org/abs/2504.14280
作者: Jindong Li,Yongguang Li,Yali Fu,Jiahong Liu,Yixin Liu,Menglin Yang,Irwin King
机构: The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学（广州）); The Jilin University(吉林大学); Griffith University(格里菲斯大学); The Chinese University of Hong Kong(香港中文大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-133] RAMCT: Novel Region-adaptive Multi-channel Tracker with Iterative Tikhonov Regularization for Thermal Infrared Tracking

链接: https://arxiv.org/abs/2504.14278
作者: Shang Zhang,Yuke Hou,Guoqiang Gong,Ruoyan Xiong,Yue Zhang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-134] xt-Audio-Visual-conditioned Diffusion Model for Video Saliency Prediction

链接: https://arxiv.org/abs/2504.14267
作者: Li Yu,Xuanzhe Sun,Wei Zhou,Moncef Gabbouj
机构: School of Computer Science, Nanjing University of Information Science and Technology (南京信息工程大学计算机科学学院); Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology (南京信息工程大学江苏省大气环境与装备技术协同创新中心); School of Computer science, Nanjing University of Information Science and Technology (南京信息工程大学计算机科学学院); School of Computer Science and Informatics, Cardiff University (卡迪夫大学计算机科学与信息学学院); Faculty of Information Technology and Communication Sciences, Tampere University (坦佩雷大学信息技术与通信科学学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-135] HoLa: B-Rep Generation using a Holistic Latent Representation

链接: https://arxiv.org/abs/2504.14257
作者: Yilin Liu,Duoteng Xu,Xingyao Yu,Xiang Xu,Daniel Cohen-Or,Hao Zhang,Hui Huang
机构: 未知
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-136] Visual Consensus Prompting for Co-Salient Object Detection CVPR2025

链接: https://arxiv.org/abs/2504.14254
作者: Jie Wang,Nana Yu,Zihao Zhang,Yahong Han
机构: College of Intelligence and Computing, Tianjin University (天津大学), Tianjin, China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: CVPR 2025

点击查看摘要

[CV-137] ColorVein: Colorful Cancelable Vein Biometrics

链接: https://arxiv.org/abs/2504.14253
作者: Yifan Wang,Jie Gui,Xinli Shi,Linqing Gui,Yuan Yan Tang,James Tin-Yau Kwok
机构: School of Cyber Science and Engineering, Southeast University (东南大学网络空间安全学院); Engineering Research Center of Blockchain Application, Supervision and Management (Southeast University), Ministry of Education (教育部区块链应用与监管工程研究中心（东南大学）); Purple Mountain Laboratories (紫金山实验室); College of Computer, Nanjing University of Posts and Telecommunications (南京邮电大学计算机学院); Department of Computer and Information Science, University of Macao (澳门大学计算机与信息科学系); Department of Computer Science and Engineering, The Hong Kong University of Science and Technology (香港科技大学计算机科学与工程系)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-138] Any Image Restoration via Efficient Spatial-Frequency Degradation Adaptation

链接: https://arxiv.org/abs/2504.14249
作者: Bin Ren,Eduard Zamfir,Zongwei Wu,Yawei Li,Yidi Li,Danda Pani Paudel,Radu Timofte,Ming-Hsuan Yang,Luc Van Gool,Nicu Sebe
机构: University of Pisa (比萨大学); University of Trento (特伦托大学); INSAIT, Sofia University ”St. Kliment Ohridski” (索非亚大学); University of Würzburg (维尔茨堡大学); ETH Zürich (苏黎世联邦理工学院); Taiyuan University of Technology (太原理工大学); University of California, Merced (加州大学默塞德分校)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Efficient All in One Image Restoration

点击查看摘要

[CV-139] ROI-Guided Point Cloud Geometry Compression Towards Human and Machine Vision

链接: https://arxiv.org/abs/2504.14240
作者: Xie Liang,Gao Wei,Zhenghui Ming,Li Ge
机构: Peking University Shenzhen Graduate School (北京大学深圳研究生院); Peng Cheng Laboratory (鹏城实验室); Peking University Shenzhen Graduate School (北京大学深圳研究生院)
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注: 10 pages, 5 figures

点击查看摘要

[CV-140] Single Document Image Highlight Removal via A Large-Scale Real-World Dataset and A Location-Aware Network

链接: https://arxiv.org/abs/2504.14238
作者: Lu Pan,Yu-Hsuan Huang,Hongxia Xie,Cheng Zhang,Hongwei Zhao,Hong-Han Shuai,Wen-Huang Cheng
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: main paper with 8 pages, conference

点击查看摘要

[CV-141] Exploring Modality Guidance to Enhance VFM-based Feature Fusion for UDA in 3D Semantic Segmentation

链接: https://arxiv.org/abs/2504.14231
作者: Johannes Spoecklberger,Wei Lin,Pedro Hermosilla,Sivan Doveh,Horst Possegger,M. Jehanzeb Mirza
机构: Institute of Visual Computing, Graz University of Technology (格拉茨技术大学); JKU LINZ; TU Wien (维也纳技术大学); IBM Research; MIT CSAIL (麻省理工学院计算机科学与人工智能实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-142] Revisiting CLIP for SF-OSDA: Unleashing Zero-Shot Potential with Adaptive Threshold and Training-Free Feature Filtering

链接: https://arxiv.org/abs/2504.14224
作者: Yongguang Li,Jindong Li,Qi Wang,Qianli Xing,Runliang Niu,Shengsheng Wang,Menglin Yang
机构: Jilin University (吉林大学); HKUST(GZ) (香港科技大学（广州）); Jilin University (吉林大学); Jilin University (吉林大学); Jilin University (吉林大学); Jilin University (吉林大学); HKUST(GZ) (香港科技大学（广州）); Jilin University (吉林大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-143] Real-IAD D3: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detection

链接: https://arxiv.org/abs/2504.14221
作者: Wenbing Zhu,Lidong Wang,Ziqing Zhou,Chengjie Wang,Yurui Pan,Ruoyi Zhang,Zhuhao Chen,Linjie Cheng,Bin-Bin Gao,Jiangning Zhang,Zhenye Gan,Yuxie Wang,Yulong Chen,Shuguang Qian,Mingmin Chi,Bo Peng,Lizhuang Ma
机构: Fudan University (复旦大学); Shanghai Jiao Tong University (上海交通大学); YouTu Lab, Tencent (腾讯优图实验室); Rongcheer Co., Ltd. (荣程创新有限公司); Shanghai Ocean University (上海海洋大学); Suzhou University (苏州大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 13 pages. Dataset and code: this https URL D3

点击查看摘要

[CV-144] PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling

链接: https://arxiv.org/abs/2504.14219
作者: Alara Dirik,Tuanfeng Wang,Duygu Ceylan,Stefanos Zafeiriou,Anna Frühstück
机构: 未知
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-145] Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis

链接: https://arxiv.org/abs/2504.14202
作者: Zichuan Liu,Liming Jiang,Qing Yan,Yumin Jia,Hao Kang,Xin Lu
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-146] Enhancing Multimodal In-Context Learning for Image Classification through Coreset Optimization

链接: https://arxiv.org/abs/2504.14200
作者: Huiyi Chen,Jiawei Peng,Kaihua Tang,Xin Geng,Xu Yang
机构: School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院) Nanjing China; Huawei Singapore Research Center(华为新加坡研究中心) Singapore
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 11 pages, 5 figures

点击查看摘要

[CV-147] Segregation and Context Aggregation Network for Real-time Cloud Segmentation

链接: https://arxiv.org/abs/2504.14178
作者: Yijie Li,Hewei Wang,Jiayi Zhang,Jinjiang You,Jinfeng Xu,Puzhen Wu,Yunzhong Xiao,Soumyabrata Dev
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 15 pages

点击查看摘要

[CV-148] Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D

链接: https://arxiv.org/abs/2504.14151
作者: Sergio Arnaud,Paul McVay,Ada Martin,Arjun Majumdar,Krishna Murthy Jatavallabhula,Phillip Thomas,Ruslan Partsey,Daniel Dugas,Abha Gejji,Alexander Sax,Vincent-Pierre Berges,Mikael Henaff,Ayush Jain,Ang Cao,Ishita Prasad,Mrinal Kalakrishnan,Michael Rabbat,Nicolas Ballas,Mido Assran,Oleksandr Maksymets,Aravind Rajeswaran,Franziska Meier
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Robotics (cs.RO)
备注:

点击查看摘要

[CV-149] hyroidEffi 1.0: A Cost-Effective System for High-Performance Multi-Class Thyroid Carcinoma Classification

链接: https://arxiv.org/abs/2504.14139
作者: Hai Pham-Ngoc,De Nguyen-Van,Dung Vu-Tien,Phuong Le-Hong
机构: Data Science Laboratory (数据科学实验室), Vietnam National University (越南国立大学); Department of Pathology (C2-E) (病理学系(C2-E)), 108 Military Central Hospital (108军事中心医院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-150] Segment Any Crack: Deep Semantic Segmentation Adaptation for Crack Detection

链接: https://arxiv.org/abs/2504.14138
作者: Ghodsiyeh Rostami,Po-Han Chen,Mahdi S. Hosseini
机构: Concordia University (康考迪亚大学), Montreal, Canada
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-151] Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approach

链接: https://arxiv.org/abs/2504.14137
作者: Hangyu Liu,Bo Peng,Pengxiang Ding,Donglin Wang
机构: Westlake University (西湖大学); Beijing University of Posts and Telecommunications (北京邮电大学); Zhejiang University (浙江大学); Westlake Milab (西湖Milab)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 12 pages, 4 figures

点击查看摘要

[CV-152] Unreal Robotics Lab: A High-Fidelity Robotics Simulator with Advanced Physics and Rendering

链接: https://arxiv.org/abs/2504.14135
作者: Jonathan Embley-Riches,Jianwei Liu,Simon Julier,Dimitrios Kanoulas
机构: Department of Computer Science, University College London (伦敦大学学院计算机科学系); UKRI Future Leaders Fellowship (英国研究与创新未来领导人 fellowship); CDT for Foundational Artificial Intelligence (基础人工智能中心博士培训中心)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-153] HFBRI-MAE: Handcrafted Feature Based Rotation-Invariant Masked Autoencoder for 3D Point Cloud Analysis IJCNN2025

链接: https://arxiv.org/abs/2504.14132
作者: Xuanhua Yin,Dingxin Zhang,Jianhui Yu,Weidong Cai
机构: School of Computer Science, The University of Sydney (悉尼大学计算机学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 12 pages, 9 figures, accepted by IJCNN 2025

点击查看摘要

[CV-154] ransforming hyperspectral images into chemical maps: A new deep learning based approach to hyperspectral image processing

链接: https://arxiv.org/abs/2504.14131
作者: Ole-Christian Galbo Engstrøm,Michela Albano-Gaglio,Erik Schou Dreier,Yamine Bouzembrak,Maria Font-i-Furnols,Puneet Mishra,Kim Steenstrup Pedersen
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
备注:

点击查看摘要

[CV-155] BMRL: Bi-Modal Guided Multi-Perspective Representation Learning for Zero-Shot Deepfake Attribution

链接: https://arxiv.org/abs/2504.14129
作者: Yaning Zhang,Jiahe Zhang,Chunjie Ma,Weili Guan,Tian Gan,Zan Gao
机构: Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学（山东省科学院）); Shandong University of Science and Technology(山东科技大学); Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学（深圳）); Shandong University(山东大学); Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学（山东省科学院）)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-156] Lightweight Road Environment Segmentation using Vector Quantization

链接: https://arxiv.org/abs/2504.14113
作者: Jiyong Kwag,Alper Yilmaz,Charles Toth
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-157] Point-Driven Interactive Text and Image Layer Editing Using Diffusion Models

链接: https://arxiv.org/abs/2504.14108
作者: Zhenyu Yu,Mohd Yamani Idna Idris,Pei Wang,Yuelong Xia
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-158] VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment

链接: https://arxiv.org/abs/2504.14096
作者: Yogesh Kulkarni,Pooyan Fazli
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-159] Retinex-guided Histogram Transformer for Mask-free Shadow Removal CVPR2025

链接: https://arxiv.org/abs/2504.14092
作者: Wei Dong,Han Zhou,Seyed Amirreza Mousavi,Jun Chen
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accpeted by CVPR 2025 NTIRE Workshop, Retinex Guidance, Histogram Transformer

点击查看摘要

[CV-160] Infrared Vision Systems for Emergency Vehicle Driver Assistance in Low-Visibility Conditions

链接: https://arxiv.org/abs/2504.14078
作者: M-Mahdi Naddaf-Sh,Andrew Lee,Kin Yen,Eemon Amini,Iman Soltani
机构: 未知
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-161] owards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design CVPR2025

链接: https://arxiv.org/abs/2504.14075
作者: Wei Dong,Yan Min,Han Zhou,Jun Chen
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025 NTIRE Workshop, Structure prior, CNN-Transformer, LLIE

点击查看摘要

[CV-162] Occlusion-Ordered Semantic Instance Segmentation

链接: https://arxiv.org/abs/2504.14054
作者: Soroosh Baselizadeh,Cheuk-To Yu,Olga Veksler,Yuri Boykov
机构: School of Computer Science, University of Waterloo (滑铁卢大学计算机学院); School of Computer Science, University of Waterloo, Canada (加拿大滑铁卢大学计算机学院)
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-163] LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models

链接: https://arxiv.org/abs/2504.14032
作者: Haiwen Huang,Anpei Chen,Volodymyr Havrylov,Andreas Geiger,Dan Zhang
机构: University of Tübingen (蒂宾根大学); Tübingen AI Center (蒂宾根人工智能中心); Bosch Center for Artificial Intelligence (博世人工智能中心)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-164] Fashion-RAG : Multimodal Fashion Image Editing via Retrieval-Augmented Generation IJCNN2025

链接: https://arxiv.org/abs/2504.14011
作者: Fulvio Sanguigni,Davide Morelli,Marcella Cornia,Rita Cucchiara
机构: University of Modena and Reggio Emilia (摩德纳-雷焦艾米利亚大学); University of Pisa (比萨大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Multimedia (cs.MM)
备注: IJCNN 2025

点击查看摘要

[CV-165] Scaling LLaNA: Advancing NeRF-Language Understanding Through Large-Scale Training

链接: https://arxiv.org/abs/2504.13995
作者: Andrea Amaduzzi,Pierluigi Zama Ramirez,Giuseppe Lisanti,Samuele Salti,Luigi Di Stefano
机构: CVLAB, University of Bologna (CVLAB, 博洛尼亚大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Under submission. Project page at this https URL

点击查看摘要

[CV-166] Entropy Rectifying Guidance for Diffusion and Flow Models

链接: https://arxiv.org/abs/2504.13987
作者: Tariq Berrada Ifriqi,Adriana Romero-Soriano,Michal Drozdzal,Jakob Verbeek,Karteek Alahari
机构: Meta (Meta)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-167] Multiscale Tensor Summation Factorization as a New Neural Network Layer (MTS Layer) for Multidimensional Data Processing

链接: https://arxiv.org/abs/2504.13975
作者: Mehmet Yamaç,Muhammad Numan Yousaf,Serkan Kiranyaz,Moncef Gabbouj
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: 13 pages

点击查看摘要

[CV-168] Memory-efficient Streaming VideoLLM s for Real-time Procedural Video Understanding

链接: https://arxiv.org/abs/2504.13915
作者: Dibyadip Chatterjee,Edoardo Remelli,Yale Song,Bugra Tekin,Abhay Mittal,Bharat Bhatnagar,Necati Cihan Camgöz,Shreyas Hampali,Eric Sauser,Shugao Ma,Angela Yao,Fadime Sener
机构: Meta Reality Labs (元宇宙研究实验室); FAIR, Meta (Facebook人工智能研究院); National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 13 pages, 5 figures; this https URL

点击查看摘要

[CV-169] owards a Multimodal Document-grounded Conversational AI System for Education

链接: https://arxiv.org/abs/2504.13884
作者: Karan Taneja,Anjali Singh,Ashok K. Goel
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: 15 pages, 4 figures, AIED 2025

点击查看摘要

[CV-170] Skeleton-Based Transformer for Classification of Errors and Better Feedback in Low Back Pain Physical Rehabilitation Exercises

链接: https://arxiv.org/abs/2504.13866
作者: Aleksa Marusic(U2IS),Sao Mai Nguyen(Lab-STICC_RAMBO, U2IS, Flowers),Adriana Tapus(U2IS)
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: ICORR 2025 - 19th IEEE/RAS-EMBS International Conference on Rehabilitation Robotics, INTERNATIONAL CONSORTIUM FOR REHABILITATION ROBOTICS, May 2025, Michigan, USA, United States

点击查看摘要

[CV-171] Revealing the 3D Cosmic Web through Gravitationally Constrained Neural Fields

链接: https://arxiv.org/abs/2504.15262
作者: Brandon Zhao,Aviad Levis,Liam Connor,Pratul P. Srinivasan,Katherine L. Bouman
机构: Department of Computing and Mathematical Sciences, California Institute of Technology (加州理工学院); Department of Computer Science, University of Toronto (多伦多大学); David A. Dunlap Department of Astronomy & Astrophysics, University of Toronto (多伦多大学); Center for Astrophysics, Harvard & Smithsonian (哈佛与史密森学会天体物理中心); Google DeepMind (谷歌深思); Departments of Astronomy and Electrical Engineering, California Institute of Technology (加州理工学院)
类目: Cosmology and Nongalactic Astrophysics (astro-ph.CO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-172] OmniAudio: Generating Spatial Audio from 360-Degree Video

链接: https://arxiv.org/abs/2504.14906
作者: Huadai Liu,Tianyi Luo,Qikai Jiang,Kaicheng Luo,Peiwen Sun,Jialei Wan,Rongjie Huang,Qian Chen,Wen Wang,Xiangtai Li,Shiliang Zhang,Zhijie Yan,Zhou Zhao,Wei Xue
机构: 未知
类目: Audio and Speech Processing (eess.AS); Computer Vision and Pattern Recognition (cs.CV); Sound (cs.SD)
备注: Work in Progress

点击查看摘要

[CV-173] Segmentation with Noisy Labels via Spatially Correlated Distributions

链接: https://arxiv.org/abs/2504.14795
作者: Ryu Tadokoro,Tsukasa Takagi,Shin-ichi Maeda
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Machine Learning (stat.ML)
备注:

点击查看摘要

[CV-174] Data Augmentation Using Neural Acoustic Fields With Retrieval-Augmented Pre-training ICASSP2025

链接: https://arxiv.org/abs/2504.14409
作者: Christopher Ick,Gordon Wichern,Yoshiki Masuyama,François G. Germain,Jonathan Le Roux
机构: 未知
类目: Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Sound (cs.SD)
备注: Presented at ICASSP 2025 GenDA Workshop

点击查看摘要

人工智能

[AI-0] Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning

链接: https://arxiv.org/abs/2504.15275
作者: Jie Cheng,Ruixi Qiao,Lijun Li,Chao Guo,Junle Wang,Gang Xiong,Yisheng Lv,Fei-Yue Wang
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-1] Leverag ing Language Models for Automated Patient Record Linkage

链接: https://arxiv.org/abs/2504.15261
作者: Mohammad Beheshti,Lovedeep Gondara,Iris Zachary
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-2] FlowReason er: Reinforcing Query-Level Meta-Agents

链接: https://arxiv.org/abs/2504.15257
作者: Hongcheng Gao,Yue Liu,Yufei He,Longxu Dou,Chao Du,Zhijie Deng,Bryan Hooi,Min Lin,Tianyu Pang
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-3] A Self-Improving Coding Agent ICLR2025

链接: https://arxiv.org/abs/2504.15228
作者: Maxime Robeyns,Martin Szummer,Laurence Aitchison
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: Published at an ICLR 2025 workshop on Scaling Self-Improving Foundation Models

点击查看摘要

[AI-4] A Genetic Fuzzy-Enabled Framework on Robotic Manipulation for In-Space Servicing

链接: https://arxiv.org/abs/2504.15226
作者: Nathan Steffen,Wilhelm Louw,Nicholas Ernest,Timothy Arnett,Kelly Cohen
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Systems and Control (eess.SY)
备注:

点击查看摘要

[AI-5] M2AD: Multi-Sensor Multi-System Anomaly Detection through Global Scoring and Calibrated Thresholding AISTATS2025

链接: https://arxiv.org/abs/2504.15225
作者: Sarah Alnegheimish,Zelin He,Matthew Reimherr,Akash Chandrayan,Abhinav Pradhan,Luca D’Angelo
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Accepted at AISTATS 2025

点击查看摘要

[AI-6] Position: Bayesian Statistics Facilitates Stakeholder Participation in Evaluation of Generative AI

链接: https://arxiv.org/abs/2504.15211
作者: Yanan Long
机构: 未知
类目: Artificial Intelligence (cs.AI); Applications (stat.AP)
备注: To be presented at ACM CHI 2025 workshop STAIG

点击查看摘要

[AI-7] Integrating Symbolic Execution into the Fine-Tuning of Code-Generating LLM s

链接: https://arxiv.org/abs/2504.15210
作者: Marina Sakharova,Abhinav Anand,Mira Mezini
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-8] A Causal Convolutional Low-rank Representation Model for Imputation of Water Quality Data

链接: https://arxiv.org/abs/2504.15209
作者: Xin Liao,Bing Yang,Tan Dongli,Cai Yu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 9 pages, 3 figures

点击查看摘要

[AI-9] Compute-Optimal LLM s Provably Generalize Better With Scale ICLR2025

链接: https://arxiv.org/abs/2504.15208
作者: Marc Finzi,Sanyam Kapoor,Diego Granziol,Anming Gu,Christopher De Sa,J. Zico Kolter,Andrew Gordon Wilson
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: ICLR 2025

点击查看摘要

[AI-10] Synergistic Weak-Strong Collaboration by Aligning Preferences

链接: https://arxiv.org/abs/2504.15188
作者: Yizhu Jiao,Xuchao Zhang,Zhaoyang Wang,Yubo Ma,Zhun Deng,Rujia Wang,Chetan Bansal,Saravan Rajmohan,Jiawei Han,Huaxiu Yao
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-11] Existing Industry Practice for the EU AI Acts General-Purpose AI Code of Practice Safety and Security Measures

链接: https://arxiv.org/abs/2504.15181
作者: Lily Stelling,Mick Yang,Rokas Gipiškis,Leon Staufer,Ze Shen Chin,Siméon Campos,Michael Chen
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
备注: 158 pages

点击查看摘要

[AI-12] Behavioral Universe Network (BUN): A Behavioral Information-Based Framework for Complex Systems

链接: https://arxiv.org/abs/2504.15146
作者: Wei Zhou,Ailiya Borjigin,Cong He
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: 17 pages, 1 figure

点击查看摘要

[AI-13] C2RUST-BENCH: A Minimized Representative Dataset for C-to-Rust Transpilation Evaluation

链接: https://arxiv.org/abs/2504.15144
作者: Melih Sirlanci,Carter Yagemann,Zhiqiang Lin
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Programming Languages (cs.PL)
备注:

点击查看摘要

[AI-14] Neural ATTF: A Scalable Solution to Lifelong Multi-Agent Path Planning

链接: https://arxiv.org/abs/2504.15130
作者: Kushal Shah,Jihyun Park,Seung-Kyum Choi
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注: 13 Pages, 5 Figures, 5 Tables

点击查看摘要

[AI-15] Contemplative Wisdom for Superalignment

链接: https://arxiv.org/abs/2504.15125
作者: Ruben Laukkonen,Fionn Inglis,Shamil Chandaria,Lars Sandved-Smith,Jakob Hohwy,Jonathan Gold,Adam Elwood
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-16] NeuGaze: Reshaping the future BCI

链接: https://arxiv.org/abs/2504.15101
作者: Yiqian Yang
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET)
备注:

点击查看摘要

[AI-17] Fast-Slow Co-advancing Optimizer: Toward Harmonious Adversarial Training of GAN

链接: https://arxiv.org/abs/2504.15099
作者: Lin Wang,Xiancheng Wang,Rui Wang,Zhibo Zhang,Minghang Zhao
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-18] Federated Latent Factor Model for Bias-Aware Recommendation with Privacy-Preserving

链接: https://arxiv.org/abs/2504.15090
作者: Junxiang Gao,Yixin Ran,Jia Chen
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-19] Empowering AI to Generate Better AI Code: Guided Generation of Deep Learning Projects with LLM s

链接: https://arxiv.org/abs/2504.15080
作者: Chen Xie,Mingsheng Jiao,Xiaodong Gu,Beijun Shen
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-20] Mitigating Degree Bias in Graph Representation Learning with Learnable Structural Augmentation and Structural Self-Attention

链接: https://arxiv.org/abs/2504.15075
作者: Van Thuy Hoang,Hyeon-Ju Jeon,O-Joun Lee
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Accepted at IEEE TNSE

点击查看摘要

[AI-21] Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides

链接: https://arxiv.org/abs/2504.15066
作者: Jinghua Zhao,Yuhang Jia,Shiyao Wang,Jiaming Zhou,Hui Wang,Yong Qin
机构: 未知
类目: Multimedia (cs.MM); Artificial Intelligence (cs.AI)
备注: 6 pages, 7 figures

点击查看摘要

[AI-22] Mining Characteristics of Vulnerable Smart Contracts Across Lifecycle Stages

链接: https://arxiv.org/abs/2504.15063
作者: Hongli Peng,Xiaoqi Li,Wenkai Li
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-23] xt-to-Decision Agent : Learning Generalist Policies from Natural Language Supervision

链接: https://arxiv.org/abs/2504.15046
作者: Shilin Zhang,Zican Hu,Wenhao Wu,Xinyi Xie,Jianxiang Tang,Chunlin Chen,Daoyi Dong,Yu Cheng,Zhenhong Sun,Zhi Wang
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: 18 pages, 8 figures

点击查看摘要

[AI-24] SOLIDO: A Robust Watermarking Method for Speech Synthesis via Low-Rank Adaptation

链接: https://arxiv.org/abs/2504.15035
作者: Yue Li,Weizhi Liu,Dongdong Lin
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Sound (cs.SD)
备注:

点击查看摘要

[AI-25] aiXamine: LLM Safety and Security Simplified

链接: https://arxiv.org/abs/2504.14985
作者: Fatih Deniz,Dorde Popovic,Yazan Boshmaf,Euisuh Jeong,Minhaj Ahmad,Sanjay Chawla,Issa Khalil
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-26] Evaluating Code Generation of LLM s in Advanced Computer Science Problems

链接: https://arxiv.org/abs/2504.14964
作者: Emir Catir,Robin Claesson,Rodothea Myrsini Tsoupidi
机构: 未知
类目: Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注:

点击查看摘要

[AI-27] Generative Semantic Communications: Principles and Practices

链接: https://arxiv.org/abs/2504.14947
作者: Xiaojun Yuan,Haoming Ma,Yinuo Huang,Zhoufan Hua,Yong Zuo,Zhi Ding
机构: 未知
类目: Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV); Signal Processing (eess.SP)
备注:

点击查看摘要

[AI-28] Giving AI a voice: how does AI think it should be treated?

链接: https://arxiv.org/abs/2504.14936
作者: Maria Fay,Frederik F. Flöther
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-29] Latent Bayesian Optimization via Autoregressive Normalizing Flows ICLR2025

链接: https://arxiv.org/abs/2504.14889
作者: Seunghun Lee,Jinyoung Park,Jaewon Chu,Minseo Yoon,Hyunwoo J. Kim
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: ICLR 2025

点击查看摘要

[AI-30] Impact of Latent Space Dimension on IoT Botnet Detection Performance: VAE-Encoder Versus ViT-Encoder

链接: https://arxiv.org/abs/2504.14879
作者: Hassan Wasswa,Aziida Nanyonga,Timothy Lynar
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-31] Exploring ell_0 Sparsification for Inference-free Sparse Retrievers SIGIR2025

链接: https://arxiv.org/abs/2504.14839
作者: Xinjie Shen,Zhichao Geng,Yang Yang
机构: 未知
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
备注: Accepted by SIGIR 2025

点击查看摘要

[AI-32] Establishing Reliability Metrics for Reward Models in Large Language Models

链接: https://arxiv.org/abs/2504.14838
作者: Yizhou Chen,Yawen Liu,Xuesi Wang,Qingtao Yu,Guangda Huzhang,Anxiang Zeng,Han Yu,Zhiming Zhou
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-33] Protecting Your Voice: Temporal-aware Robust Watermarking

链接: https://arxiv.org/abs/2504.14832
作者: Yue Li,Weizhi Liu,Dongdong Lin
机构: 未知
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Sound (cs.SD)
备注:

点击查看摘要

[AI-34] DONOD: Robust and Generalizable Instruction Fine-Tuning for LLM s via Model-Intrinsic Dataset Pruning

链接: https://arxiv.org/abs/2504.14810
作者: Jucheng Hu,Surong Yang,Dongzhan Zhou,Lijun Wu
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-35] Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length Adjustment ICLR2025

链接: https://arxiv.org/abs/2504.14805
作者: Jinwoo Choi,Seung-Woo Seo
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO)
备注: ICLR 2025; 23 pages, 12 figures

点击查看摘要

[AI-36] Automated Duplicate Bug Report Detection in Large Open Bug Repositories

链接: https://arxiv.org/abs/2504.14797
作者: Clare E. Laney,Andrew Barovic,Armin Moin
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注: IEEE COMPSAC 2025

点击查看摘要

[AI-37] Exploring Collaborative GenAI Agents in Synchronous Group Settings: Eliciting Team Perceptions and Design Considerations for the Future of Work

链接: https://arxiv.org/abs/2504.14779
作者: Janet G. Johnson,Macarena Peralta,Mansanjam Kaur,Ruijie Sophia Huang,Sheng Zhao,Ruijia Guan,Shwetha Rajaram,Michael Nebeling
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: To be published in ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW 2025). 33 pages, 11 figures, 1 table

点击查看摘要

[AI-38] A Combinatorial Theory of Dropout: Subnetworks Graph Geometry and Generalization

链接: https://arxiv.org/abs/2504.14762
作者: Sahil Rajesh Dhayalkar
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 17 pages (9 pages main content and remaining pages are references, appendix which includes 7 figures, proofs and derivations)

点击查看摘要

[AI-39] SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs

链接: https://arxiv.org/abs/2504.14757
作者: Minh V.T. Pham,Huy N. Phan,Hoang N. Phan,Cuong Le Chi,Tien N. Nguyen,Nghi D. Q. Bui
机构: 未知
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
备注: Work in progress

点击查看摘要

[AI-40] AI for the Open-World: the Learning Principles

链接: https://arxiv.org/abs/2504.14751
作者: Jianyu Zhang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: PhD thesis. This is not a compilation of published papers, but a new one

点击查看摘要

[AI-41] A Modularized Design Approach for GelSight Family of Vision-based Tactile Sensors

链接: https://arxiv.org/abs/2504.14739
作者: Arpit Agarwal(1),Mohammad Amin Mirzaee(2),Xiping Sun(2),Wenzhen Yuan(2) ((1) Carnegie Mellon University, USA, (2) University of Illinois Urbana-Champaign, USA)
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注: The paper is accepted to International Journal of Robotics Research with DOI https://doi.org/10.1177/02783649251339680

点击查看摘要

[AI-42] AI with Emotions: Exploring Emotional Expressions in Large Language Models NAACL2025

链接: https://arxiv.org/abs/2504.14706
作者: Shin-nosuke Ishikawa,Atsushi Yoshino
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: 14 pages, 8 figures, accepted to the Natural Language Processing for Digital Humanities (NLP4DH) workshop at NAACL 2025

点击查看摘要

[AI-43] Can We Ignore Labels In Out of Distribution Detection?

链接: https://arxiv.org/abs/2504.14704
作者: Hong Yang,Qi Yu,Travis Desel
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Systems and Control (eess.SY)
备注:

点击查看摘要

[AI-44] Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data

链接: https://arxiv.org/abs/2504.14694
作者: Yuting He,Yiqiang Chen,XiaoDong Yang,Hanchao Yu,Yi-Hua Huang,Yang Gu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-45] Uncovering Issues in the Radio Access Network by Looking at the Neighbors

链接: https://arxiv.org/abs/2504.14686
作者: José Suárez-Varela,Andra Lutu
机构: 未知
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 7 pages

点击查看摘要

[AI-46] An LLM -enabled Multi-Agent Autonomous Mechatronics Design Framework CVPR2025

链接: https://arxiv.org/abs/2504.14681
作者: Zeyu Wang,Frank P.-W. Lo,Qian Chen,Yongqi Zhang,Chen Lin,Xu Chen,Zhenhua Yu,Alexander J. Thompson,Eric M. Yeatman,Benny P. L. Lo
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注: Accepted by CVPR 2025 Workshop

点击查看摘要

[AI-47] Evaluating Temporal Plasticity in Foundation Time Series Models for Incremental Fine-tuning IJCNN2025

链接: https://arxiv.org/abs/2504.14677
作者: Jia Liu,Cheng Jinguo,Xia Fang,Zhenyuan Ma,Yuankai Wu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Accepted at IJCNN 2025

点击查看摘要

[AI-48] A Framework for Benchmarking and Aligning Task-Planning Safety in LLM -Based Embodied Agents

链接: https://arxiv.org/abs/2504.14650
作者: Yuting Huang,Leilei Ding,Zhipeng Tang,Tianfu Wang,Xinrui Lin,Wuyang Zhang,Mingxiao Ma,Yanyong Zhang
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: 16 pages, 10 figures

点击查看摘要

[AI-49] Surrogate Fitness Metrics for Interpretable Reinforcement Learning

链接: https://arxiv.org/abs/2504.14645
作者: Philipp Altmann,Céline Davignon,Maximilian Zorn,Fabian Ritz,Claudia Linnhoff-Popien,Thomas Gabor
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 30 pages, 7 figures, under review

点击查看摘要

[AI-50] AlphaZero-Edu: Making AlphaZero Accessible to Everyone

链接: https://arxiv.org/abs/2504.14636
作者: Binjie Guo,Hanyu Zheng,Guowei Su,Ru Zhang,Haohan Jiang,Xurong Lin,Hongyan Wei,Aisheng Mo,Jie Li,Zhiyuan Qian,Zhuhao Zhang,Xiaoyuan Cheng
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-51] owards Optimal Circuit Generation: Multi-Agent Collaboration Meets Collective Intelligence

链接: https://arxiv.org/abs/2504.14625
作者: Haiyan Qin,Jiahao Feng,Xiaotong Feng,Wei W. Xing,Wang Kang
机构: 未知
类目: Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI)
备注: 9 pages, 6 figures

点击查看摘要

[AI-52] Consensus in Motion: A Case of Dynamic Rationality of Sequential Learning in Probability Aggregation

链接: https://arxiv.org/abs/2504.14624
作者: Polina Gordienko,Christoph Jansen,Thomas Augustin,Martin Rechenauer
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: Submitted to the International Conference on Modeling Decisions for Artificial Intelligence (MDAI 2025)

点击查看摘要

[AI-53] UFO2: The Desktop Agent OS MICRO

链接: https://arxiv.org/abs/2504.14603
作者: Chaoyun Zhang,He Huang,Chiming Ni,Jian Mu,Si Qin,Shilin He,Lu Wang,Fangkai Yang,Pu Zhao,Chao Du,Liqun Li,Yu Kang,Zhao Jiang,Suzhen Zheng,Rujia Wang,Jiaxu Qian,Minghua Ma,Jian-Guang Lou,Qingwei Lin,Saravan Rajmohan,Dongmei Zhang
机构: 未知
类目: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Operating Systems (cs.OS)
备注: The source code of UFO2 is publicly available at this https URL , with comprehensive documentation provided at this https URL

点击查看摘要

[AI-54] K2MUSE: A human lower limb multimodal dataset under diverse conditions for facilitating rehabilitation robotics

链接: https://arxiv.org/abs/2504.14602
作者: Jiwei Li,Bi Zhang,Xiaowei Tan,Wanxin Chen,Zhaoyuan Liu,Juanjuan Zhang,Weiguang Huo,Jian Huang,Lianqing Liu,Xingang Zhao
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注: 23 pages, 13 figures,4 tables

点击查看摘要

[AI-55] oward the Axiomatization of Intelligence: Structure Time and Existence

链接: https://arxiv.org/abs/2504.14596
作者: Kei Itoh
机构: 未知
类目: Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE)
备注: 37 pages, 4 tables, in English, in Japanese

点击查看摘要

[AI-56] Modality Selection and Skill Segmentation via Cross-Modality Attention

链接: https://arxiv.org/abs/2504.14573
作者: Jiawei Jiang,Kei Ota,Devesh K. Jha,Asako Kanezaki
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-57] NoWag: A Unified Framework for Shape Preserving Compression of Large Language Models

链接: https://arxiv.org/abs/2504.14569
作者: Lawrence Liu,Inesh Chakrabarti,Yixiao Li,Mengdi Wang,Tuo Zhao,Lin F. Yang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-58] Reasoning V: Efficient Verilog Code Generation with Adaptive Hybrid Reasoning Model

链接: https://arxiv.org/abs/2504.14560
作者: Haiyan Qin,Zhiwei Xie,Jingjing Li,Liangchen Li,Xiaotong Feng,Junzhan Liu,Wang Kang
机构: 未知
类目: Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI)
备注: 9 pages, 4 figures

点击查看摘要

[AI-59] LLM -Enabled In-Context Learning for Data Collection Scheduling in UAV-assisted Sensor Networks

链接: https://arxiv.org/abs/2504.14556
作者: Yousef Emami,Hao Gao,SeyedSina Nabavirazani,Luis Almeida
机构: 未知
类目: Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET); Machine Learning (cs.LG); Robotics (cs.RO)
备注: 8 pages, 7 figures,

点击查看摘要

[AI-60] Learning from Reasoning Failures via Synthetic Data Generation

链接: https://arxiv.org/abs/2504.14523
作者: Gabriela Ben Melech Stan,Estelle Aflalo,Avinash Madasu,Vasudev Lal,Phillip Howard
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-61] Biased by Design: Leverag ing AI Biases to Enhance Critical Thinking of News Readers

链接: https://arxiv.org/abs/2504.14522
作者: Liudmila Zavolokina,Kilian Sprenkamp,Zoya Katashinskaya,Daniel Gordon Jones
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: European Conference on Information Systems (ECIS)

点击查看摘要

[AI-62] SlimPipe: Memory-Thrifty and Efficient Pipeline Parallelism for Long-Context LLM Training

链接: https://arxiv.org/abs/2504.14519
作者: Zhouyang Li,Yuliang Liu,Wei Zhang,Tailing Yuan,Bin Chen,Chengru Song,Di Zhang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-63] On Dimension-Free Transformer: An Application of STP to AI

链接: https://arxiv.org/abs/2504.14514
作者: Daizhan Cheng
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Systems and Control (eess.SY)
备注:

点击查看摘要

[AI-64] FinSage: A Multi-aspect RAG System for Financial Filings Question Answering

链接: https://arxiv.org/abs/2504.14493
作者: Xinyu Wang,Jijun Chi,Zhenghan Tai,Tung Sum Thomas Kwok,Muzhi Li,Zhuhong Li,Hailin He,Yuchen Hua,Peng Lu,Suyuchen Wang,Yihong Wu,Jerry Huang,Ling Zhou
机构: 未知
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-65] Seeing Through Risk: A Symbolic Approximation of Prospect Theory

链接: https://arxiv.org/abs/2504.14448
作者: Ali Arslan Yousaf,Umair Rehman,Muhammad Umair Danish
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Optimization and Control (math.OC); Methodology (stat.ME)
备注:

点击查看摘要

[AI-66] Optimizing SIA Development: A Case Study in User-Centered Design for Estuary a Multimodal Socially Interactive Agent Framework

链接: https://arxiv.org/abs/2504.14427
作者: Spencer Lin,Miru Jun,Basem Rizk,Karen Shieh,Scott Fisher,Sharon Mozgai
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-67] Planet as a Brain: Towards Internet of AgentS ites based on AIOS Server

链接: https://arxiv.org/abs/2504.14411
作者: Xiang Zhang,Yongfeng Zhang
机构: 未知
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-68] ScholarMate: A Mixed-Initiative Tool for Qualitative Knowledge Work and Information Sensemaking

链接: https://arxiv.org/abs/2504.14406
作者: Runlong Ye,Patrick Yung Kang Lee,Matthew Varona,Oliver Huang,Carolina Nobre
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: accepted at CHIWORK 2025

点击查看摘要

[AI-69] he Geometry of Self-Verification in a Task-Specific Reasoning Model

链接: https://arxiv.org/abs/2504.14379
作者: Andrew Lee,Lihao Sun,Chris Wendler,Fernanda Viégas,Martin Wattenberg
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-70] Learning Enhanced Structural Representations with Block-Based Uncertainties for Ocean Floor Mapping

链接: https://arxiv.org/abs/2504.14372
作者: Jose Marie Antonio Minoza
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-71] Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator

链接: https://arxiv.org/abs/2504.14365
作者: Akshat Ramachandran,Souvik Kundu,Arnab Raha,Shamik Kundu,Deepak K. Mathaikutty,Tushar Krishna
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR)
备注:

点击查看摘要

[AI-72] Mathematical Programming Models for Exact and Interpretable Formulation of Neural Networks

链接: https://arxiv.org/abs/2504.14356
作者: Masoud Ataei,Edrin Hasaj,Jacob Gipp,Sepideh Forouzi
机构: 未知
类目: Artificial Intelligence (cs.AI); Optimization and Control (math.OC)
备注:

点击查看摘要

[AI-73] me Up! An Empirical Study of LLM Reasoning Ability Under Output Length Constraint

链接: https://arxiv.org/abs/2504.14350
作者: Yi Sun,Han Wang,Jiaqiang Li,Jiacheng Liu,Xiangyu Li,Hao Wen,Huiwen Zheng,Yan Liang,Yuanchun Li,Yunxin Liu
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-74] FAIRGAME: a Framework for AI Agents Bias Recognition using Game Theory

链接: https://arxiv.org/abs/2504.14325
作者: Alessio Buscemi,Daniele Proverbio,Alessandro Di Stefano, TheAnh Han,German Castignani,Pietro Di Liò
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-75] Expanding the Generative AI Design Space through Structured Prompting and Multimodal Interfaces

链接: https://arxiv.org/abs/2504.14320
作者: Nimisha Karnatak,Adrien Baranes,Rob Marchant,Huinan Zeng,Tríona Butler,Kristen Olson
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: Accepted at CHI’25 Workshop on Designing and Developing User Interfaces with AI

点击查看摘要

[AI-76] Learning to Score

链接: https://arxiv.org/abs/2504.14302
作者: Yogev Kriger,Shai Fine
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-77] Learning and Generating Diverse Residential Load Patterns Using GAN with Weakly-Supervised Training and Weight Selection

链接: https://arxiv.org/abs/2504.14300
作者: Xinyu Liang,Hao Wang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 12 pages

点击查看摘要

[AI-78] RadioDiff-Inverse: Diffusion Enhanced Bayesian Inverse Estimation for ISAC Radio Map Construction

链接: https://arxiv.org/abs/2504.14298
作者: Xiucheng Wang,Zhongsheng Fang,Nan Cheng
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: 12 pages, 7 figures

点击查看摘要

[AI-79] CHAINSFORMER: Numerical Reasoning on Knowledge Graphs from a Chain Perspective ICDE2025

链接: https://arxiv.org/abs/2504.14282
作者: Ze Zhao,Bin Lu,Xiaoying Gan,Gu Tang,Luoyi Fu,Xinbing Wang
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Accepted to ICDE 2025

点击查看摘要

[AI-80] ProtPainter: Draw or Drag Protein via Topology-guided Diffusion ICLR2025

链接: https://arxiv.org/abs/2504.14274
作者: Zhengxi Lu,Shizhuo Cheng,Yuru Jiang,Yan Zhang,Min Zhang
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注: Published as a conference paper at ICLR 2025

点击查看摘要

[AI-81] Experience-based Refinement of Task Planning Knowledge in Autonomous Robots

链接: https://arxiv.org/abs/2504.14259
作者: Hadeel Jazzaa,Thomas McCluskey,David Peebles
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-82] Rethinking Traffic Flow Forecasting: From Transition to Generatation

链接: https://arxiv.org/abs/2504.14248
作者: Li Shijiao,Ma Zhipeng,He Huajun,Chen Haiyue
机构: 未知
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-83] A Knowledge-Informed Deep Learning Paradigm for Generalizable and Stability-Optimized Car-Following Models

链接: https://arxiv.org/abs/2504.14241
作者: Chengming Wang,Dongyao Jia,Wei Wang,Dong Ngoduy,Bei Peng,Jianping Wang
机构: 未知
类目: Artificial Intelligence (cs.AI); Robotics (cs.RO)
备注:

点击查看摘要

[AI-84] Pets: General Pattern Assisted Architecture For Time Series Analysis

链接: https://arxiv.org/abs/2504.14209
作者: Xiangkai Ma,Xiaobin Hong,Wenzhong Li,Sanglu Lu
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-85] Decomposition-based multi-scale transformer framework for time series anomaly detection

链接: https://arxiv.org/abs/2504.14206
作者: Wenxin Zhang,Cuicui Luo
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-86] Dual-channel Heterophilic Message Passing for Graph Fraud Detection

链接: https://arxiv.org/abs/2504.14205
作者: Wenxin Zhang,Jingxing Zhong,Guangzhen Yao,Renda Han,Xiaojian Lin,Zeyu Zhang,Cuicui Luo
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-87] DConAD: A Differencing-based Contrastive Representation Learning Framework for Time Series Anomaly Detection

链接: https://arxiv.org/abs/2504.14204
作者: Wenxin Zhang,Xiaojian Lin,Wenjun Yu,Guangzhen Yao,jingxiang Zhong,Yu Li,Renda Han,Songcheng Xu,Hao Shi,Cuicui Luo
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-88] A Physics-guided Multimodal Transformer Path to Weather and Climate Sciences

链接: https://arxiv.org/abs/2504.14174
作者: Jing Han,Hanting Chen,Kai Han,Xiaomeng Huang,Yongyun Hu,Wenjun Xu,Dacheng Tao,Ping Zhang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Perspective article

点击查看摘要

[AI-89] Adaptation Method for Misinformation Identification

链接: https://arxiv.org/abs/2504.14171
作者: Yangping Chen,Weijie Shi,Mengze Li,Yue Cui,Hao Chen,Jia Zhu,Jiajie Xu
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-90] PipeWeaver: Addressing Data Dynamicity in Large Multimodal Model Training with Dynamic Interleaved Pipeline

链接: https://arxiv.org/abs/2504.14145
作者: Zhenliang Xue,Hanpeng Hu,Xing Chen,Yimin Jiang,Yixin Song,Zeyu Mi,Yibo Zhu,Daxin Jiang,Yubin Xia,Haibo Chen
机构: 未知
类目: Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-91] Personalized News Recommendation with Multi-granularity Candidate-aware User Modeling

链接: https://arxiv.org/abs/2504.14130
作者: Qiang Li,Xinze Lin,Shenghao Lv,Faliang Huang,Xiangju Li
机构: 未知
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-92] Exploring Language Patterns of Prompts in Text-to-Image Generation and Their Impact on Visual Diversity

链接: https://arxiv.org/abs/2504.14125
作者: Maria-Teresa De Rosa Palmini,Eva Cetinic
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注:

点击查看摘要

[AI-93] CODECRASH: Stress Testing LLM Reasoning under Structural and Semantic Perturbations

链接: https://arxiv.org/abs/2504.14119
作者: Man Ho Lam,Chaozheng Wang,Jen-tse Huang,Michael R. Lyu
机构: 未知
类目: Artificial Intelligence (cs.AI); Software Engineering (cs.SE)
备注:

点击查看摘要

[AI-94] Longitudinal Study on Social and Emotional Use of AI Conversational Agent

链接: https://arxiv.org/abs/2504.14112
作者: Mohit Chandra,Javier Hernandez,Gonzalo Ramos,Mahsa Ershadi,Ananya Bhattacharjee,Judith Amores,Ebele Okoli,Ann Paradiso,Shahed Warreth,Jina Suh
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注: 16 pages, 5 figures, 2 tables

点击查看摘要

[AI-95] Amplify Initiative: Building A Localized Data Platform for Globalized AI

链接: https://arxiv.org/abs/2504.14105
作者: Qazi Mamunur Rashid,Erin van Liemt,Tiffany Shih,Amber Ebinama,Karla Barrios Ramos,Madhurima Maji,Aishwarya Verma,Charu Kalia,Jamila Smith-Loud,Joyce Nakatumba-Nabende,Rehema Baguma,Andrew Katumba,Chodrine Mutebi,Jagen Marvin,Eric Peter Wairagala,Mugizi Bruce,Peter Oketta,Lawrence Nderu,Obichi Obiajunwa,Abigail Oppong,Michael Zimba,Data Authors
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-96] Coordinating Spinal and Limb Dynamics for Enhanced Sprawling Robot Mobility ICRA2025

链接: https://arxiv.org/abs/2504.14103
作者: Merve Atasever,Ali Okhovat,Azhang Nazaripouya,John Nisbet,Omer Kurkutlu,Jyotirmoy V. Deshmukh,Yasemin Ozkan Aydin
机构: 未知
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
备注: The manuscript has been accepted for presentation at the Mechanical Intelligence in Robotics workshop at ICRA 2025

点击查看摘要

[AI-97] Enhancing Math Learning in an LMS Using AI-Driven Question Recommendations

链接: https://arxiv.org/abs/2504.14098
作者: Justus Råmunddal
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Information Retrieval (cs.IR)
备注: 15 pages, 9 figures, 4 tables

点击查看摘要

[AI-98] Leakage and Interpretability in Concept-Based Models

链接: https://arxiv.org/abs/2504.14094
作者: Enrico Parisini,Tapabrata Chakraborti,Chris Harbron,Ben D. MacArthur,Christopher R. S. Banerji
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
备注: 38 pages, 27 figures

点击查看摘要

[AI-99] Evaluating Human-AI Interaction via Usability User Experience and Acceptance Measures for MMM-C: A Creative AI System for Music Composition IJCAI2023

链接: https://arxiv.org/abs/2504.14071
作者: Renaud Bougueng Tchemeube,Jeff Ens,Cale Plut,Philippe Pasquier,Maryam Safi,Yvan Grabit,Jean-Baptiste Rolland
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Sound (cs.SD)
备注: 10 pages, 6 figures, 1 table, first published at the 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023), Macao, China

点击查看摘要

[AI-100] A CMOS Probabilistic Computing Chip With In-situ hardware Aware Learning

链接: https://arxiv.org/abs/2504.14070
作者: Jinesh Jhonsa,William Whitehead,David McCarthy,Shuvro Chowdhury,Kerem Camsari,Luke Theogarajan
机构: 未知
类目: Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI)
备注: 3 pages 12 figuewa

点击查看摘要

[AI-101] hink Deep Think Fast: Investigating Efficiency of Verifier-free Inference-time-scaling Methods

链接: https://arxiv.org/abs/2504.14047
作者: Junlin Wang,Shang Zhu,Jon Saad-Falcon,Ben Athiwaratkun,Qingyang Wu,Jue Wang,Shuaiwen Leon Song,Ce Zhang,Bhuwan Dhingra,James Zou
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-102] A synthetic dataset of French electric load curves with temperature conditioning ICLR2025

链接: https://arxiv.org/abs/2504.14046
作者: Tahar Nabil,Ghislain Agoua,Pierre Cauchois,Anne De Moliner,Benoît Grossin
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: Workshop paper at “Tackling Climate Change with Machine Learning”, ICLR 2025

点击查看摘要

[AI-103] Metacognition and Uncertainty Communication in Humans and Large Language Models

链接: https://arxiv.org/abs/2504.14045
作者: Mark Steyvers,Megan A.K. Peters
机构: 未知
类目: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注:

点击查看摘要

[AI-104] Multi-Stage Retrieval for Operational Technology Cybersecurity Compliance Using Large Language Models : A Railway Casestudy

链接: https://arxiv.org/abs/2504.14044
作者: Regan Bolton,Mohammadreza Sheikhfathollahi,Simon Parkinson,Dan Basher,Howard Parkinson
机构: 未知
类目: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
备注:

点击查看摘要

[AI-105] Flowco: Rethinking Data Analysis in the Age of LLM s

链接: https://arxiv.org/abs/2504.14038
作者: Stephen N. Freund,Brooke Simon,Emery D. Berger,Eunice Jun
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Programming Languages (cs.PL); Computation (stat.CO)
备注:

点击查看摘要

[AI-106] Causal pieces: analysing and improving spiking neural networks piece by piece

链接: https://arxiv.org/abs/2504.14015
作者: Dominik Dold,Philipp Christian Petersen
机构: 未知
类目: Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC); Machine Learning (stat.ML)
备注:

点击查看摘要

[AI-107] CPR: Leverag ing LLM s for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews

链接: https://arxiv.org/abs/2504.13993
作者: Ekta Gujral,Apurva Sinha,Lishi Ji,Bijayani Sanghamitra Mishra
机构: 未知
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[AI-108] PC-DeepNet: A GNSS Positioning Error Minimization Framework Using Permutation-Invariant Deep Neural Network

链接: https://arxiv.org/abs/2504.13990
作者: M. Humayun Kabir,Md. Ali Hasan,Md. Shafiqul Islam,Kyeongjun Ko,Wonjae Shin
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Systems and Control (eess.SY)
备注: 31 pages, 14 figures, 6 tables

点击查看摘要

[AI-109] Going Whole Hog: A Philosophical Defense of AI Cognition

链接: https://arxiv.org/abs/2504.13988
作者: Herman Cappelen,Josh Dever
机构: 未知
类目: Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-110] On the redundancy of short and heterogeneous sequences of belief revisions

链接: https://arxiv.org/abs/2504.13986
作者: Paolo Liberatore
机构: 未知
类目: Computational Complexity (cs.CC); Artificial Intelligence (cs.AI)
备注: arXiv admin note: substantial text overlap with arXiv:2402.15445 , arXiv:2305.09200

点击查看摘要

[AI-111] CacheFormer: High Attention-Based Segment Caching

链接: https://arxiv.org/abs/2504.13981
作者: Sushant Singh,Ausif Mahmood
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-112] Framework Standards Applications and Best practices of Responsible AI : A Comprehensive Survey

链接: https://arxiv.org/abs/2504.13979
作者: Thippa Reddy Gadekallu,Kapal Dev,Sunder Ali Khowaja,Weizheng Wang,Hailin Feng,Kai Fang,Sharnil Pandya,Wei Wang
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
备注: Submitted for peer review

点击查看摘要

[AI-113] Gas Station of the Future: A Perspective on AI/ML and IoT in Retail Downstream

链接: https://arxiv.org/abs/2504.13976
作者: Wrick Talukdar
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-114] Enhancing Stroke Diagnosis in the Brain Using a Weighted Deep Learning Approach

链接: https://arxiv.org/abs/2504.13974
作者: Yao Zhiwan,Reza Zarrab,Jean Dubois
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-115] Birds of a Different Feather Flock Together: Exploring Opportunities and Challenges in Animal-Human-Machine Teaming

链接: https://arxiv.org/abs/2504.13973
作者: Myke C. Cohen,David A. Grimm,Reuth Mirsky,Xiaoyun Yin
机构: 未知
类目: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA)
备注:

点击查看摘要

[AI-116] Governance Challenges in Reinforcement Learning from Human Feedback: Evaluator Rationality and Reinforcement Stability

链接: https://arxiv.org/abs/2504.13972
作者: Dana Alsagheer,Abdulrahman Kamal,Mohammad Kamal,Weidong Shi
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-117] he Future of Internet of Things and Multimodal Language Models in 6G Networks: Opportunities and Challenges

链接: https://arxiv.org/abs/2504.13971
作者: Abdelrahman Soliman
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET); Networking and Internet Architecture (cs.NI)
备注: 11 pages

点击查看摘要

[AI-118] nker Tales: Interactive Storytelling Framework for Early Childhood Narrative Development and AI Literacy

链接: https://arxiv.org/abs/2504.13969
作者: Nayoung Choi,Peace Cyebukayire,Jinho D. Choi
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注:

点击查看摘要

[AI-119] CONTINA: Confidence Interval for Traffic Demand Prediction with Coverag e Guarantee

链接: https://arxiv.org/abs/2504.13961
作者: Chao Yang,Xiannan Huang,Shuhan Qiu,Yan Cheng
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
备注:

点击查看摘要

[AI-120] Naming is framing: How cybersecuritys language problems are repeating in AI governance

链接: https://arxiv.org/abs/2504.13957
作者: Liane Potter
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
备注: 20 pages, 2 figures

点击查看摘要

[AI-121] Generative System Dynamics in Recurrent Neural Networks

链接: https://arxiv.org/abs/2504.13951
作者: Michele Casoni,Tommaso Guidi,Alessandro Betti,Stefano Melacci,Marco Gori
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-122] Open-Medical-R1: How to Choose Data for RLVR Training at Medicine Domain

链接: https://arxiv.org/abs/2504.13950
作者: Zhongxi Qiu,Zhang Zhang,Yan Hu,Heng Li,Jiang Liu
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 15 figures

点击查看摘要

[AI-123] On Revealing the Hidden Problem Structure in Real-World and Theoretical Problems Using Walsh Coefficient Influence

链接: https://arxiv.org/abs/2504.13949
作者: M. W. Przewozniczek,F. Chicano,R. Tinós,J. Nalepa,B. Ruszczak,A. M. Wijata
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-124] Using customized GPT to develop prompting proficiency in architectural AI-generated images

链接: https://arxiv.org/abs/2504.13948
作者: Juan David Salazar Rodriguez,Sam Conrad Joyce,Julfendi Julfendi
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-125] From job titles to jawlines: Using context voids to study generative AI systems

链接: https://arxiv.org/abs/2504.13947
作者: Shahan Ali Memon,Soham De,Sungha Kang,Riyan Mujtaba,Bedoor AlShebli,Katie Davis,Jaime Snyder,Jevin D. West
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注: 7 pages, 2 figures

点击查看摘要

[AI-126] Evaluating Menu OCR and Translation: A Benchmark for Aligning Human and Automated Evaluations in Large Vision-Language Models

链接: https://arxiv.org/abs/2504.13945
作者: Zhanglin Wu,Tengfei Song,Ning Xie,Weidong Zhang,Mengli Zhu,Shuang Wu,Shiliang Sun,Hao Yang
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 12 pages, 5 figures, 5 Tables

点击查看摘要

[AI-127] Mixer Metaphors: audio interfaces for non-musical applications

链接: https://arxiv.org/abs/2504.13944
作者: Tace McNamara,Jon McCormack,Maria Teresa Llano
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Sound (cs.SD)
备注: 9 Pages

点击查看摘要

[AI-128] Intelligence of Things: A Spatial Context-Aware Control System for Smart Devices

链接: https://arxiv.org/abs/2504.13942
作者: Sukanth Kalivarathan,Muhmmad Abrar Raja Mohamed,Aswathy Ravikumar,S Harini
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET)
备注: 16 pages, 8 Figures

点击查看摘要

[AI-129] NEMOTRON-CROSSTHINK: Scaling Self-Learning beyond Math Reasoning

链接: https://arxiv.org/abs/2504.13941
作者: Syeda Nahida Akter,Shrimai Prabhumoye,Matvei Novikov,Seungju Han,Ying Lin,Evelina Bakhturi,Eric Nyberg,Yejin Choi,Mostofa Patwary,Mohammad Shoeybi,Bryan Catanzaro
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
备注: 18 pages, 7 figures

点击查看摘要

[AI-130] Hashigo: A Next Generation Sketch Interactive System for Japanese Kanji

链接: https://arxiv.org/abs/2504.13940
作者: Paul Taele,Tracy Hammond
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-131] LLM -Driven NPCs: Cross-Platform Dialogue System for Games and Social Platforms

链接: https://arxiv.org/abs/2504.13928
作者: Li Song
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-132] A Multi-Layered Research Framework for Human-Centered AI: Defining the Path to Explainability and Trust

链接: https://arxiv.org/abs/2504.13926
作者: Chameera De Silva,Thilina Halloluwa,Dhaval Vyas
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-133] Modeling the quantum-like dynamics of human reliability ratings in Human-AI interactions by interaction dependent Hamiltonians

链接: https://arxiv.org/abs/2504.13918
作者: Johan van der Meer,Pamela Hoyte,Luisa Roeder,Peter Bruza
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: 10 pages, 7 figures. Submitted to Phil. Trans. B

点击查看摘要

[AI-134] AI-Assisted Conversational Interviewing: Effects on Data Quality and User Experience

链接: https://arxiv.org/abs/2504.13908
作者: Soubhik Barari,Jarret Angbazo,Natalie Wang,Leah M. Christian,Elizabeth Dean,Zoe Slowinski,Brandon Sepulvado
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Applications (stat.AP)
备注:

点击查看摘要

[AI-135] Supporting Students Reading and Cognition with AI

链接: https://arxiv.org/abs/2504.13900
作者: Yue Fu,Alexis Hiniker
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注:

点击查看摘要

[AI-136] Predicting Satisfaction of Counterfactual Explanations from Human Ratings of Explanatory Qualities

链接: https://arxiv.org/abs/2504.13899
作者: Marharyta Domnich,Rasmus Moorits Veski,Julius Välja,Kadi Tulver,Raul Vicente
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: This work has been accepted to The 3rd World Conference on eXplainable Artificial Intelligence (xAI 2025), July 9-11, 2025 - Istanbul, Turkey

点击查看摘要

[AI-137] he Human Robot Social Interaction (HSRI) Dataset: Benchmarking Foundational Models Social Reasoning

链接: https://arxiv.org/abs/2504.13898
作者: Dong Won Lee,Yubin Kim,Denison Guvenoz,Sooyeon Jeong,Parker Malachowsky,Louis-Philippe Morency,Cynthia Breazeal,Hae Won Park
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: 23 pages, 11 figures

点击查看摘要

[AI-138] Mozualization: Crafting Music and Visual Representation with Multimodal AI

链接: https://arxiv.org/abs/2504.13891
作者: Wanfang Xu,Lixiang Zhao,Haiwen Song,Xinheng Song,Zhaolin Lu,Yu Liu,Min Chen,Eng Gee Lim,Lingyun Yu
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: 7 pages, 5 figures, CHI2025

点击查看摘要

[AI-139] Maestoso: An Intelligent Educational Sketching Tool for Learning Music Theory

链接: https://arxiv.org/abs/2504.13889
作者: Paul Taele,Laura Barreto,Tracy Hammond
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-140] New care pathways for supporting transitional care from hospitals to home using AI and personalized digital assistance

链接: https://arxiv.org/abs/2504.13877
作者: Ionut Anghel,Tudor Cioara,Roberta Bevilacqua,Federico Barbarossa,Terje Grimstad,Riitta Hellman,Arnor Solberg,Lars Thomas Boye,Ovidiu Anchidin,Ancuta Nemes,Camilla Gabrielsen
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: submitted to journal (under review)

点击查看摘要

[AI-141] Human aversion? Do AI Agents Judge Identity More Harshly Than Performance

链接: https://arxiv.org/abs/2504.13871
作者: Yuanjun Feng,Vivek Chodhary,Yash Raj Shrestha
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); General Economics (econ.GN)
备注:

点击查看摘要

[AI-142] Using Generative AI Personas Increases Collective Diversity in Human Ideation

链接: https://arxiv.org/abs/2504.13868
作者: Yun Wan,Yoram M Kalman
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-143] DoYouTrustAI: A Tool to Teach Students About AI Misinformation and Prompt Engineering

链接: https://arxiv.org/abs/2504.13859
作者: Phillip Driscoll,Priyanka Kumar
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注:

点击查看摘要

[AI-144] he Effect of Explainable AI-based Decision Support on Human Task Performance: A Meta-Analysis

链接: https://arxiv.org/abs/2504.13858
作者: Felix Haag
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI)
备注: Published in the Proceedings of the Twenty-Third Annual Pre-ICIS Workshop on HCI Research in MIS, Bangkok, Thailand, December 15th, 2024

点击查看摘要

[AI-145] owards Balancing Preference and Performance through Adaptive Personalized Explainability

链接: https://arxiv.org/abs/2504.13856
作者: Andrew Silva,Pradyumna Tambwekar,Mariah Schrum,Matthew Gombolay
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Robotics (cs.RO)
备注: 20 pages, 19 figures, HRI 2024

点击查看摘要

[AI-146] From Interaction to Collaboration: How Hybrid Intelligence Enhances Chatbot Feedback

链接: https://arxiv.org/abs/2504.13848
作者: Janet Rafner,Ryan Q. Guloy,Eden W. Wen,Catherine M. Chiodo,Jacob Sherson
机构: 未知
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Emerging Technologies (cs.ET)
备注: 14 pages

点击查看摘要

[AI-147] he Model Counting Competitions 2021-2023

链接: https://arxiv.org/abs/2504.13842
作者: Johannes K. Fichte,Markus Hecher
机构: 未知
类目: Artificial Intelligence (cs.AI); Data Structures and Algorithms (cs.DS); Logic in Computer Science (cs.LO)
备注:

点击查看摘要

[AI-148] OPO: Making Decision-Focused Data Acquisition Decisions

链接: https://arxiv.org/abs/2504.15062
作者: Egon Peršak,Miguel F. Anjos
机构: 未知
类目: Optimization and Control (math.OC); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-149] Beyond Terabit/s Integrated Neuromorphic Photonic Processor for DSP-Free Optical Interconnects

链接: https://arxiv.org/abs/2504.15044
作者: Benshan Wang,Qiarong Xiao,Tengji Xu,Li Fan,Shaojie Liu,Jianji Dong,Junwen Zhang,Chaoran Huang
机构: 未知
类目: Optics (physics.optics); Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET)
备注: 22 pages, 6 figures

点击查看摘要

[AI-150] rainable Quantum Neural Network for Multiclass Image Classification with the Power of Pre-trained Tree Tensor Networks

链接: https://arxiv.org/abs/2504.14995
作者: Keisuke Murota,Takumi Kobori
机构: 未知
类目: Quantum Physics (quant-ph); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 11 pages, 12 figures, 2 tables. This work has been submitted to the IEEE for possible publication

点击查看摘要

[AI-151] StableQuant: Layer Adaptive Post-Training Quantization for Speech Foundation Models ICASSP2025

链接: https://arxiv.org/abs/2504.14915
作者: Yeona Hong,Hyewon Han,Woo-jin Chung,Hong-Goo Kang
机构: 未知
类目: Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI)
备注: Accepted at ICASSP 2025

点击查看摘要

[AI-152] LBM-GNN: Graph Neural Network Enhanced Lattice Boltzmann Method

链接: https://arxiv.org/abs/2504.14494
作者: Yue Li
机构: 未知
类目: Fluid Dynamics (physics.flu-dyn); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[AI-153] Integrating LLM -Generated Views into Mean-Variance Optimization Using the Black-Litterman Model ICLR25 ICLR2025

链接: https://arxiv.org/abs/2504.14345
作者: Youngbin Lee,Yejin Kim,Suin Kim,Yongjae Lee
机构: 未知
类目: Portfolio Management (q-fin.PM); Artificial Intelligence (cs.AI)
备注: Presented at the ICLR 2025 Workshop on Financial AI ( this https URL )

点击查看摘要

[AI-154] Breaking the Diffraction Barrier for Passive Sources: Parameter-Decoupled Superresolution Assisted by Physics-Informed Machine Learning

链接: https://arxiv.org/abs/2504.14156
作者: Abdelali Sajia,Bilal Benzimoun,Pawan Khatiwada,Guogan Zhao,Xiao-Feng Qian
机构: 未知
类目: Optics (physics.optics); Artificial Intelligence (cs.AI); Quantum Physics (quant-ph)
备注: 12 pages, 3 figures

点击查看摘要

[AI-155] 6G WavesFM: A Foundation Model for Sensing Communication and Localization

链接: https://arxiv.org/abs/2504.14100
作者: Ahmed Aboulfotouh,Elsayed Mohammed,Hatem Abou-Zeid
机构: 未知
类目: ignal Processing (eess.SP); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

机器学习

[LG-0] On Learning Parallel Pancakes with Mostly Uniform Weights

链接: https://arxiv.org/abs/2504.15251
作者: Ilias Diakonikolas,Daniel M. Kane,Sushrut Karmalkar,Jasper C.H. Lee,Thanasis Pittas
类目: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS); Statistics Theory (math.ST); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-1] Faster Algorithms for Agnostically Learning Disjunctions and their Implications

链接: https://arxiv.org/abs/2504.15244
作者: Ilias Diakonikolas,Daniel M. Kane,Lisheng Ren
类目: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-2] Single-loop Algorithms for Stochastic Non-convex Optimization with Weakly-Convex Constraints

链接: https://arxiv.org/abs/2504.15243
作者: Ming Yang,Gang Li,Quanqi Hu,Qihang Lin,Tianbao Yang
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-3] Conformalized-KANs: Uncertainty Quantification with Coverag e Guarantees for Kolmogorov-Arnold Networks (KANs) in Scientific Machine Learning

链接: https://arxiv.org/abs/2504.15240
作者: Amirhossein Mollaali,Christian Bolivar Moya,Amanda A. Howard,Alexander Heinlein,Panos Stinis,Guang Lin
类目: Machine Learning (cs.LG)
*备注: 17 pages, 8 figures,

点击查看摘要

[LG-4] A Deep Learning Framework for Sequence Mining with Bidirectional LSTM and Multi-Scale Attention

链接: https://arxiv.org/abs/2504.15223
作者: Tao Yang,Yu Cheng,Yaokun Ren,Yujia Lou,Minggu Wei,Honghui Xin
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-5] DRAG ON: Distributional Rewards Optimize Diffusion Generative Models

链接: https://arxiv.org/abs/2504.15217
作者: Yatong Bai,Jonah Casebeer,Somayeh Sojoudi,Nicholas J. Bryan
类目: ound (cs.SD); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-6] Histogram-based Parameter-efficient Tuning for Passive Sonar Classification

链接: https://arxiv.org/abs/2504.15214
作者: Amirmohammad Mohammadi,Davelle Carreiro,Alexandra Van Dine,Joshua Peeples
类目: Machine Learning (cs.LG); Sound (cs.SD)
*备注: 5 pages, 4 figures. Submitted to IEEE WASPAA 2025 for possible publication

点击查看摘要

[LG-7] How Global Calibration Strengthens Multiaccuracy

链接: https://arxiv.org/abs/2504.15206
作者: Sílvia Casacuberta,Parikshit Gopalan,Varun Kanade,Omer Reingold
类目: Machine Learning (cs.LG); Computational Complexity (cs.CC)
*备注:

点击查看摘要

[LG-8] Audio-Visual Class-Incremental Learning for Fish Feeding intensity Assessment in Aquaculture

链接: https://arxiv.org/abs/2504.15171
作者: Meng Cui,Xianghu Yue,Xinyuan Qian,Jinzheng Zhao,Haohe Liu,Xubo Liu,Daoliang Li,Wenwu Wang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-9] Survey of Loss Augmented Knowledge Tracing

链接: https://arxiv.org/abs/2504.15163
作者: Altun Shukurlu
类目: Machine Learning (cs.LG)
*备注: 14 pages, no figures

点击查看摘要

[LG-10] Kolmogorov-Arnold Networks: Approximation and Learning Guarantees for Functions and their Derivatives

链接: https://arxiv.org/abs/2504.15110
作者: Anastasis Kratsios,Takashi Furuya
类目: Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Functional Analysis (math.FA); Numerical Analysis (math.NA); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-11] Application of Sensitivity Analysis Methods for Studying Neural Network Models

链接: https://arxiv.org/abs/2504.15100
作者: Jiaxuan Miao,Sergey Matveev
类目: Numerical Analysis (math.NA); Machine Learning (cs.LG)
*备注: 11 pages, 16 figures, 32 references

点击查看摘要

[LG-12] hink2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL

链接: https://arxiv.org/abs/2504.15077
作者: Simone Papicchio,Simone Rossi,Luca Cagliero,Paolo Papotti
类目: Machine Learning (cs.LG); Databases (cs.DB)
*备注: 15 pages

点击查看摘要

[LG-13] A Call for New Recipes to Enhance Spatial Reasoning in MLLM s

链接: https://arxiv.org/abs/2504.15037
作者: Huanyu Zhang,Chengzu Li,Wenshan Wu,Shaoguang Mao,Yan xia,Ivan Vulić,Zhang Zhang,Liang Wang,Tieniu Tan,Furu Wei
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-14] Is Intelligence the Right Direction in New OS Scheduling for Multiple Resources in Cloud Environments?

链接: https://arxiv.org/abs/2504.15021
作者: Xinglei Dou,Lei Liu,Limin Xiao
类目: Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG); Performance (cs.PF)
*备注: 25 pages, 14 figures, to be published in ACM Transactions on Storage

点击查看摘要

[LG-15] Learning Compositional Transferability of Time Series for Source-Free Domain Adaptation

链接: https://arxiv.org/abs/2504.14994
作者: Hankang Sun(1),Guiming Li(1),Su Yang(1),Baoqi Li(2) ((1) Fudan University, (2) Chinese Academy of Sciences, Institute of Acoustics)
类目: Machine Learning (cs.LG)
*备注: Corresponding author: Su Yang

点击查看摘要

[LG-16] MoE Parallel Folding: Heterogeneous Parallelism Mappings for Efficient Large-Scale MoE Model Training with Megatron Core

链接: https://arxiv.org/abs/2504.14960
作者: Dennis Liu,Zijie Yan,Xin Yao,Tong Liu,Vijay Korthikanti,Evan Wu,Shiqing Fan,Gao Deng,Hongxiao Bai,Ashwath Aithal,Michael Andersch,Mohammad Shoeybi,Jiajie Yao,Chandler Zhou,David Wu,Xipeng Li,June Yang
类目: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注:

点击查看摘要

[LG-17] Efficient Document Retrieval with G-Retriever NEURIPS2024

链接: https://arxiv.org/abs/2504.14955
作者: Manthankumar Solanki
类目: Machine Learning (cs.LG)
*备注: Extended version of a paper presented at NeurIPS 2024 ( arXiv:2402.07630 )

点击查看摘要

[LG-18] Symmetry-Preserving Architecture for Multi-NUMA Environments (SPANE): A Deep Reinforcement Learning Approach for Dynamic VM Scheduling

链接: https://arxiv.org/abs/2504.14946
作者: Tin Ping Chan,Yunlong Cheng,Yizhan Zhu,Xiaofeng Gao,Guihai Chen
类目: Machine Learning (cs.LG)
*备注: 10 pages, 7 figures. Accepted to IEEE INFOCOM 2025

点击查看摘要

[LG-19] Causal DAG Summarization (Full Version)

链接: https://arxiv.org/abs/2504.14937
作者: Anna Zeng,Michael Cafarella,Batya Kenig,Markos Markakis,Brit Youngmann,Babak Salimi
类目: Machine Learning (cs.LG); Databases (cs.DB); Methodology (stat.ME)
*备注:

点击查看摘要

[LG-20] POLYRAG : Integrating Polyviews into Retrieval-Augmented Generation for Medical Applications

链接: https://arxiv.org/abs/2504.14917
作者: Chunjing Gan,Dan Yang,Binbin Hu,Ziqi Liu,Yue Shen,Zhiqiang Zhang,Jian Wang,Jun Zhou
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-21] Dynamic Graph-Like Learning with Contrastive Clustering on Temporally-Factored Ship Motion Data for Imbalanced Sea State Estimation in Autonomous Vessel

链接: https://arxiv.org/abs/2504.14907
作者: Kexin Wang,Mengna Liu,Xu Cheng,Fan Shi,Shanshan Qi,Shengyong Chen
类目: Machine Learning (cs.LG)
*备注: 13 pages,15 figures

点击查看摘要

[LG-22] Uncertainty quantification of neural network models of evolving processes via Langevin sampling

链接: https://arxiv.org/abs/2504.14854
作者: Cosmin Safta,Reese E. Jones,Ravi G. Patel,Raelynn Wonnacot,Dan S. Bolintineanu,Craig M. Hamel,Sharlotte L.B. Kramer
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 23 pages, 15 figures

点击查看摘要

Abstract:We propose a scalable, approximate inference hypernetwork framework for a general model of history-dependent processes. The flexible data model is based on a neural ordinary differential equation (NODE) representing the evolution of internal states together with a trainable observation model subcomponent. The posterior distribution corresponding to the data model parameters (weights and biases) follows a stochastic differential equation with a drift term related to the score of the posterior that is learned jointly with the data model parameters. This Langevin sampling approach offers flexibility in balancing the computational budget between the evaluation cost of the data model and the approximation of the posterior density of its parameters. We demonstrate performance of the hypernetwork on chemical reaction and material physics data and compare it to mean-field variational inference.

[LG-23] A Basic Evaluation of Neural Networks Trained with the Error Diffusion Learning Algorithm

链接: https://arxiv.org/abs/2504.14814
作者: Kazuhisa Fujita
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-24] Edge-boosted graph learning for functional brain connectivity analysis

链接: https://arxiv.org/abs/2504.14796
作者: David Yang,Mostafa Abdelmegeed,John Modl,Minjeong Kim
类目: Machine Learning (cs.LG); Image and Video Processing (eess.IV)
*备注: Accepted at IEEE International Symposium on Biomedical Imaging (ISBI) 2025, 4 pages

点击查看摘要

[LG-25] Enhanced Data-driven Topology Design Methodology with Multi-level Mesh and Correlation-based Mutation for Stress-related Multi-objective Optimization

链接: https://arxiv.org/abs/2504.14790
作者: Jun Yang,Shintaro Yamasaki
类目: Machine Learning (cs.LG); Numerical Analysis (math.NA)
*备注: 23 pages, 22 figures

点击查看摘要

[LG-26] Novel Concept-Oriented Synthetic Data approach for Training Generative AI-Driven Crystal Grain Analysis Using Diffusion Model

链接: https://arxiv.org/abs/2504.14782
作者: Ahmed Sobhi Saleh,Kristof Croes,Hajdin Ceric,Ingrid De Wolf,Houman Zahedmanesh
类目: Machine Learning (cs.LG); Materials Science (cond-mat.mtrl-sci)
*备注: 19 Pages, 5 Figures

点击查看摘要

[LG-27] AltGDmin: Alternating GD and Minimization for Partly-Decoupled (Federated) Optimization

链接: https://arxiv.org/abs/2504.14741
作者: Namrata Vaswani
类目: Machine Learning (cs.LG); Optimization and Control (math.OC); Methodology (stat.ME)
*备注: To appear in Foundations and Trends in Optimization (NOW publishers)

点击查看摘要

[LG-28] Reinforcement Learning from Multi-level and Episodic Human Feedback

链接: https://arxiv.org/abs/2504.14732
作者: Muhammad Qasim Elahi,Somtochukwu Oguchienti,Maheed H. Ahmed,Mahsa Ghasemi
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-29] Geometric Learning Dynamics

链接: https://arxiv.org/abs/2504.14728
作者: Vitaly Vanchurin
类目: Machine Learning (cs.LG); Populations and Evolution (q-bio.PE); Quantum Physics (quant-ph)
*备注: 15 pages

点击查看摘要

[LG-30] Video QoE Metrics from Encrypted Traffic: Application-agnostic Methodology

链接: https://arxiv.org/abs/2504.14720
作者: Tamir Berger,Jonathan Sterenson,Raz Birman,Ofer Hadar
类目: Networking and Internet Architecture (cs.NI); Machine Learning (cs.LG); Multimedia (cs.MM)
*备注: 8 pages, 7 figures

点击查看摘要

[LG-31] Pairwise or Pointwise? Evaluating Feedback Protocols for Bias in LLM -Based Evaluation

链接: https://arxiv.org/abs/2504.14716
作者: Tuhina Tripathi,Manya Wadhwa,Greg Durrett,Scott Niekum
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-32] Connecting Parameter Magnitudes and Hessian Eigenspaces at Scale using Sketched Methods

链接: https://arxiv.org/abs/2504.14701
作者: Andres Fernandez,Frank Schneider,Maren Mahsereci,Philipp Hennig
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: Accepted at TMLR 2025

点击查看摘要

[LG-33] Quantitative Clustering in Mean-Field Transformer Models

链接: https://arxiv.org/abs/2504.14697
作者: Shi Chen,Zhengjiang Lin,Yury Polyanskiy,Philippe Rigollet
类目: Machine Learning (cs.LG); Analysis of PDEs (math.AP); Dynamical Systems (math.DS); Machine Learning (stat.ML)
*备注: 47 pages, 4 figures

点击查看摘要

[LG-34] Reveal-or-Obscure: A Differentially Private Sampling Algorithm for Discrete Distributions

链接: https://arxiv.org/abs/2504.14696
作者: Naima Tasnim,Atefeh Gilani,Lalitha Sankar,Oliver Kosut
类目: Information Theory (cs.IT); Cryptography and Security (cs.CR); Data Structures and Algorithms (cs.DS); Machine Learning (cs.LG)
*备注: 8 pages, 3 figures

点击查看摘要

[LG-35] Efficient Federated Split Learning for Large Language Models over Communication Networks

链接: https://arxiv.org/abs/2504.14667
作者: Kai Zhao,Zhaohui Yang
类目: Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI)
*备注:

点击查看摘要

[LG-36] GENE-FL: Gene-Driven Parameter-Efficient Dynamic Federated Learning

链接: https://arxiv.org/abs/2504.14628
作者: Shunxin Guo,Jiaqi Lv,Qiufeng Wang,Xin Geng
类目: Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-37] No Imputation of Missing Values In Tabular Data Classification Using Incremental Learning

链接: https://arxiv.org/abs/2504.14610
作者: Manar D. Samad,Kazi Fuad B. Akhter,Shourav B. Rabbani,Ibna Kowsar
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-38] Generalized Derangetropy Functionals for Modeling Cyclical Information Flow

链接: https://arxiv.org/abs/2504.14605
作者: Masoud Ataei,Xiaogang Wang
类目: Information Theory (cs.IT); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-39] Generative Auto-Bidding with Value-Guided Explorations

链接: https://arxiv.org/abs/2504.14587
作者: Jingtong Gao,Yewen Li,Shuai Mao,Peng Jiang,Nan Jiang,Yejing Wang,Qingpeng Cai,Fei Pan,Peng Jiang,Kun Gai,Bo An,Xiangyu Zhao
类目: Machine Learning (cs.LG); Information Retrieval (cs.IR)
*备注:

点击查看摘要

[LG-40] Data Selection for ERMs

链接: https://arxiv.org/abs/2504.14572
作者: Steve Hanneke,Shay Moran,Alexander Shlimovich,Amir Yehudayoff
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-41] rustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Data

链接: https://arxiv.org/abs/2504.14545
作者: Fei Zhu,Zhaoxiang Zhang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-42] Less is More: Adaptive Coverag e for Synthetic Training Data

链接: https://arxiv.org/abs/2504.14508
作者: Sasan Tavakkol,Max Springer,Mohammadhossein Bateni,Neslihan Bulut,Vincent Cohen-Addad,MohammadTaghi Hajiaghayi
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-43] A computational framework for longitudinal medication adherence prediction in breast cancer survivors: A social cognitive theory based approach

链接: https://arxiv.org/abs/2504.14469
作者: Navreet Kaur,Manuel Gonzales IV,Cristian Garcia Alcaraz,Jiaqi Gong,Kristen J. Wells,Laura E. Barnes
类目: Machine Learning (cs.LG); Human-Computer Interaction (cs.HC)
*备注:

点击查看摘要

[LG-44] Exploring Pseudo-Token Approaches in Transformer Neural Processes

链接: https://arxiv.org/abs/2504.14416
作者: Jose Lara-Rangel,Nanze Chen,Fengzhe Zhang
类目: Machine Learning (cs.LG)
*备注: 7th Symposium on Advances in Approximate Bayesian Inference

点击查看摘要

[LG-45] Quantum-Enhanced Reinforcement Learning for Power Grid Security Assessment

链接: https://arxiv.org/abs/2504.14412
作者: Benjamin M. Peter,Mert Korkali
类目: ystems and Control (eess.SY); Machine Learning (cs.LG)
*备注: 6 pages, 6 figures, 3 tables. Submitted to the 2025 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)

点击查看摘要

[LG-46] Balancing Fairness and Performance in Healthcare AI: A Gradient Reconciliation Approach

链接: https://arxiv.org/abs/2504.14388
作者: Xiaoyang Wang,Christopher C. Yang
类目: Machine Learning (cs.LG); Computers and Society (cs.CY)
*备注: Accepted to the 23rd International Conference on Artificial Intelligence in Medicine (AIME 2025)

点击查看摘要

[LG-47] Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts NAACL2025

链接: https://arxiv.org/abs/2504.14375
作者: Kun Qian,Maximillian Chen,Siyan Li,Arpit Sharma,Zhou Yu
类目: Machine Learning (cs.LG)
*备注: Accepted by NAACL 2025

点击查看摘要

[LG-48] Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data

链接: https://arxiv.org/abs/2504.14368
作者: Shlomi Hod,Lucas Rosenblatt,Julia Stoyanovich
类目: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
*备注:

点击查看摘要

[LG-49] Local distribution-based adaptive oversampling for imbalanced regression

链接: https://arxiv.org/abs/2504.14316
作者: Shayan Alahyari,Mike Domaratzki
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-50] Learning from Stochastic Teacher Representations Using Student-Guided Knowledge Distillation

链接: https://arxiv.org/abs/2504.14307
作者: Muhammad Haseeb Aslam,Clara Martinez,Marco Pedersoli,Alessandro Koerich,Ali Etemad,Eric Granger
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-51] SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM

链接: https://arxiv.org/abs/2504.14286
作者: Xiaojiang Zhang,Jinghui Wang,Zifei Cheng,Wenhao Zhuang,Zheng Lin,Minglei Zhang,Shaojie Wang,Yinghan Cui,Chao Wang,Junyi Peng,Shimiao Jiang,Shiqi Kuang,Shouyu Yin,Chaohang Wen,Haotian Zhang,Bin Chen,Bing Yu
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-52] Mixed-Precision Conjugate Gradient Solvers with RL-Driven Precision Tuning

链接: https://arxiv.org/abs/2504.14268
作者: Xinye Chen
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-53] Generative emulation of chaotic dynamics with coherent prior

链接: https://arxiv.org/abs/2504.14264
作者: Juan Nathaniel,Pierre Gentine
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 41 pages, 25 figures

点击查看摘要

[LG-54] A Pre-Training and Adaptive Fine-Tuning Framework for Graph Anomaly Detection

链接: https://arxiv.org/abs/2504.14250
作者: Yunhui Liu,Jiashun Cheng,Jia Li,Fugee Tsung,Hongzhi Yin,Tieke He
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-55] A Novel Frequency-Spatial Domain Aware Network for Fast Thermal Prediction in 2.5D ICs DATE’25

链接: https://arxiv.org/abs/2504.14237
作者: Dekang Zhang,Dan Niu,Zhou Jin,Yichao Dong,Jingweijia Tan,Changyin Sun
类目: Machine Learning (cs.LG)
*备注: 7 pages, 5 figures, 22nd Design, Automation and Test in Europe Conference (DATE '25)

点击查看摘要

[LG-56] FedC4: Graph Condensation Meets Client-Client Collaboration for Efficient and Private Federated Graph Learning

链接: https://arxiv.org/abs/2504.14188
作者: Zekai Chen,Xunkai Li,Yinlin Zhu,Rong-Hua Li,Guoren Wang
类目: Machine Learning (cs.LG)
*备注: 10 pages, 7 figures; references added

点击查看摘要

[LG-57] FGMP: Fine-Grained Mixed-Precision Weight and Activation Quantization for Hardware-Accelerated LLM Inference

链接: https://arxiv.org/abs/2504.14152
作者: Coleman Hooper,Charbel Sakr,Ben Keller,Rangharajan Venkatesan,Kurt Keutzer,Sophia Shao,Brucek Khailany
类目: Hardware Architecture (cs.AR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-58] Predicting Stress and Damage in Carbon Fiber-Reinforced Composites Deformation Process using Composite U-Net Surrogate Model

链接: https://arxiv.org/abs/2504.14143
作者: Zeping Chen,Marwa Yacouti,Maryam Shakiba,Jian-Xun Wang,Tengfei Luo,Vikas Varshney
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-59] Visualization Tasks for Unlabelled Graphs

链接: https://arxiv.org/abs/2504.14115
作者: Matt I. B. Oddo,Ryan Smith,Stephen Kobourov,Tamara Munzner
类目: Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-60] Personalizing Exposure Therapy via Reinforcement Learning AAAI2025

链接: https://arxiv.org/abs/2504.14095
作者: Athar Mahmoudi-Nejad,Matthew Guzdial,Pierre Boulanger
类目: Machine Learning (cs.LG)
*备注: AAAI 2025 Bridge (Collaborative AI and Modelling of Humans Bridge Program)

点击查看摘要

[LG-61] ransformation of audio embeddings into interpretable concept-based representations IJCNN

链接: https://arxiv.org/abs/2504.14076
作者: Alice Zhang,Edison Thomaz,Lie Lu
类目: ound (cs.SD); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS)
*备注: Accepted to International Joint Conference on Neural Networks (IJCNN) 2025

点击查看摘要

[LG-62] Contextual Embedding-based Clustering to Identify Topics for Healthcare Service Improvement

链接: https://arxiv.org/abs/2504.14068
作者: K M Sajjadul Islam,Ravi Teja Karri,Srujan Vegesna,Jiawei Wu,Praveen Madiraju
类目: Machine Learning (cs.LG); Human-Computer Interaction (cs.HC)
*备注: Full version of the paper accepted at the 2025 IEEE COMPSAC, Toronto, Canada

点击查看摘要

[LG-63] Calliope: An Online Generative Music System for Symbolic Multi-Track Composition

链接: https://arxiv.org/abs/2504.14058
作者: Renaud Bougueng Tchemeube,Jeff Ens,Philippe Pasquier
类目: Human-Computer Interaction (cs.HC); Machine Learning (cs.LG); Sound (cs.SD)
*备注: 5 pages, 5 figures, first published at the 13th International Conference on Computational Creativity (ICCC 2022), Bozen-Bolzano, Italy

点击查看摘要

[LG-64] Apollo: An Interactive Environment for Generating Symbolic Musical Phrases using Corpus-based Style Imitation

链接: https://arxiv.org/abs/2504.14055
作者: Renaud Bougueng Tchemeube,Jeff Ens,Philippe Pasquier
类目: Human-Computer Interaction (cs.HC); Machine Learning (cs.LG); Sound (cs.SD)
*备注: 7 pages, 5 figures, Published as a paper at the 7th International Workshop on Musical Metacreation (MUME 2019), UNC Charlotte, North Carolina

点击查看摘要

[LG-65] CAOTE: KV Caching through Attention Output Error based Token Eviction

链接: https://arxiv.org/abs/2504.14051
作者: Raghavv Goel,Junyoung Park,Mukul Gagrani,Dalton Jones,Matthew Morse,Harper Langston,Mingu Lee,Chris Lott
类目: Machine Learning (cs.LG)
*备注: 14 pages, 2 figures

点击查看摘要

[LG-66] Prioritizing Security Practice Adoption: Empirical Insights on Software Security Outcomes in the npm Ecosystem

链接: https://arxiv.org/abs/2504.14026
作者: Nusrat Zahan,Laurie Williams
类目: oftware Engineering (cs.SE); Machine Learning (cs.LG)
*备注: 12 pages, 3 figures, 5 tables

点击查看摘要

[LG-67] Large Language Bayes

链接: https://arxiv.org/abs/2504.14025
作者: Justin Domke
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-68] Knitting Robots: A Deep Learning Approach for Reverse-Engineering Fabric Patterns

链接: https://arxiv.org/abs/2504.14007
作者: Haoliang Sheng,Songpu Cai,Xingyu Zheng,Meng Cheng Lau
类目: Robotics (cs.RO); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-69] First and Second Order Approximations to Stochastic Gradient Descent Methods with Momentum Terms

链接: https://arxiv.org/abs/2504.13992
作者: Eric Lu
类目: Machine Learning (cs.LG); Optimization and Control (math.OC)
*备注:

点击查看摘要

[LG-70] Deep Learning on Graphs for Mobile Network Topology Generation

链接: https://arxiv.org/abs/2504.13991
作者: Felix Nannesson Meli,Johan Tell,Shirwan Piroti,Tahar Zanouda,Elias Jarlebring
类目: Machine Learning (cs.LG)
*备注: 5 pages, 6 figures, submitted to IEEE Networking Letters

点击查看摘要

[LG-71] QuatE-D: A Distance-Based Quaternion Model for Knowledge Graph Embedding

链接: https://arxiv.org/abs/2504.13983
作者: Hamideh-Sadat Fazael-Ardakani,Hamid Soltanian-Zadeh
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-72] When Machine Learning Meets Importance Sampling: A More Efficient Rare Event Estimation Approach

链接: https://arxiv.org/abs/2504.13982
作者: Ruoning Zhao,Xinyun Chen
类目: Machine Learning (cs.LG); Optimization and Control (math.OC); Probability (math.PR)
*备注:

点击查看摘要

[LG-73] Adversarial Resilience against Clean-Label Attacks in Realizable and Noisy Settings

链接: https://arxiv.org/abs/2504.13966
作者: Carolin Heinzler
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: Master’s thesis

点击查看摘要

[LG-74] A Collaborative Platform for Soil Organic Carbon Inference Based on Spatiotemporal Remote Sensing Data

链接: https://arxiv.org/abs/2504.13962
作者: Jose Manuel Aroca-Fernandez,Jose Francisco Diez-Pastor,Pedro Latorre-Carmona,Victor Elvira,Gustau Camps-Valls,Rodrigo Pascual,Cesar Garcia-Osorio
类目: Computers and Society (cs.CY); Machine Learning (cs.LG)
*备注: 28 pages, 11 figures

点击查看摘要

[LG-75] Prognosis Of Lithium-Ion Battery Health with Hybrid EKF-CNNLSTM Model Using Differential Capacity

链接: https://arxiv.org/abs/2504.13956
作者: Md Azizul Hoque,Babul Salam,Mohd Khair Hassan,Abdulkabir Aliyu,Abedalmuhdi Almomany,Muhammed Sutcu
类目: Machine Learning (cs.LG); Systems and Control (eess.SY); Applications (stat.AP)
*备注: 20pages, 19 figures

点击查看摘要

[LG-76] he Balancing Act of Policies in Developing Machine Learning Explanations

链接: https://arxiv.org/abs/2504.13946
作者: Jacob Tjaden
类目: Human-Computer Interaction (cs.HC); Computers and Society (cs.CY); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-77] ViMo: A Generative Visual GUI World Model for App Agent

链接: https://arxiv.org/abs/2504.13936
作者: Dezhao Luo,Bohan Tang,Kang Li,Georgios Papoudakis,Jifei Song,Shaogang Gong,Jianye Hao,Jun Wang,Kun Shao
类目: Human-Computer Interaction (cs.HC); Machine Learning (cs.LG); Systems and Control (eess.SY)
*备注:

点击查看摘要

[LG-78] Ising Models with Hidden Markov Structure: Applications to Probabilistic Inference in Machine Learning

链接: https://arxiv.org/abs/2504.13927
作者: F. Herrera,U.A. Rozikov,M. V. Velasco
类目: Machine Learning (cs.LG); Mathematical Physics (math-ph)
*备注: 15 pages, 2 figures

点击查看摘要

[LG-79] Hybrid Deep Learning Model to Estimate Cognitive Effort from fNIRS Signals in Educational Game Playing

链接: https://arxiv.org/abs/2504.13883
作者: Shayla Sharmin,Roghayeh Leila Barmaki
类目: Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-80] A discrete physics-informed training for projection-based reduced order models with neural networks

链接: https://arxiv.org/abs/2504.13875
作者: N. Sibuet,S. Ares de Parga,J.R. Bravo,R. Rossi
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-81] ranslating Multimodal AI into Real-World Inspection: TEMAI Evaluation Framework and Pathways for Implementation

链接: https://arxiv.org/abs/2504.13873
作者: Zehan Li,Jinzhi Deng,Haibing Ma,Chi Zhang,Dan Xiao
类目: Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-82] Resource Utilization Optimized Federated Learning

链接: https://arxiv.org/abs/2504.13850
作者: Zihan Zhang,Leon Wong,Blesson Varghese
类目: Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-83] Advanced posterior analyses of hidden Markov models: finite Markov chain imbedding and hybrid decoding

链接: https://arxiv.org/abs/2504.15156
作者: Zenia Elise Damgaard Bæk,Moisès Coll Macià,Laurits Skov,Asger Hobolth
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: 23 pages, 14 figures

点击查看摘要

[LG-84] Integrating Response Time and Attention Duration in Bayesian Preference Learning for Multiple Criteria Decision Aiding

链接: https://arxiv.org/abs/2504.14938
作者: Jiaxuan Jiang,Jiapeng Liu,Miłosz Kadziński,Xiuwu Liao,Jingyu Dong
类目: Applications (stat.AP); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-85] Expected Free Energy-based Planning as Variational Inference

链接: https://arxiv.org/abs/2504.14898
作者: Bert de Vries,Wouter Nuijten,Thijs van de Laar,Wouter Kouw,Sepideh Adamiat,Tim Nisslbeck,Mykola Lukashchuk,Hoang Minh Huu Nguyen,Marco Hidalgo Araya,Raphael Tresor,Thijs Jenneskens,Ivana Nikoloska,Raaja Subramanian,Bart van Erp,Dmitry Bagaev,Albert Podusenko
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: 16 pages

点击查看摘要

[LG-86] On the Tunability of Random Survival Forests Model for Predictive Maintenance

链接: https://arxiv.org/abs/2504.14744
作者: Yigitcan Yardımcı,Mustafa Cavus
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-87] Quantum-Enhanced Weight Optimization for Neural Networks Using Grovers Algorithm

链接: https://arxiv.org/abs/2504.14568
作者: Stefan-Alexandru Jura,Mihai Udrescu
类目: Quantum Physics (quant-ph); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-88] Guess SWAP Repeat : Capturing Quantum Snapshots in Classical Memory

链接: https://arxiv.org/abs/2504.14459
作者: Debarshi Kundu,Avimita Chatterjee,Swaroop Ghosh
类目: Quantum Physics (quant-ph); Machine Learning (cs.LG)
*备注: 11 Pages, 8 figures

点击查看摘要

[LG-89] Optimal Scheduling of Dynamic Transport

链接: https://arxiv.org/abs/2504.14425
作者: Panos Tsimpos,Zhi Ren,Jakob Zech,Youssef Marzouk
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Classical Analysis and ODEs (math.CA); Functional Analysis (math.FA)
*备注:

点击查看摘要

[LG-90] Optimal Lattice Boltzmann Closures through Multi-Agent Reinforcement Learning

链接: https://arxiv.org/abs/2504.14422
作者: Paul Fischer,Sebastian Kaltenbach,Sergey Litvinov,Sauro Succi,Petros Koumoutsakos
类目: Fluid Dynamics (physics.flu-dyn); Machine Learning (cs.LG); Computational Physics (physics.comp-ph); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-91] Machine learning enhanced atom probe tomography analysis: a snapshot review

链接: https://arxiv.org/abs/2504.14378
作者: Yue Li,Ye Wei,Alaukik Saxena,Markus Kühbach,Christoph Freysoldt,Baptiste Gault
类目: Materials Science (cond-mat.mtrl-sci); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-92] Learning over von Mises-Fisher Distributions via a Wasserstein-like Geometry

链接: https://arxiv.org/abs/2504.14164
作者: Kisung You,Dennis Shung,Mauro Giuffrè
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Methodology (stat.ME)
*备注:

点击查看摘要

[LG-93] DeepPD: Joint Phase and Object Estimation from Phase Diversity with Neural Calibration of a Deformable Mirror

链接: https://arxiv.org/abs/2504.14157
作者: Magdalena C. Schneider,Courtney Johnson,Cedric Allier,Larissa Heinrich,Diane Adjavon,Joren Husic,Patrick La Rivière,Stephan Saalfeld,Hari Shroff
类目: Optics (physics.optics); Machine Learning (cs.LG)
*备注:

点击查看摘要

信息检索

[IR-0] Linear Item-Item Model with Neural Knowledge for Session-based Recommendation SIGIR2025

链接: https://arxiv.org/abs/2504.15057
作者: Minjin Choi,Sunkyung Lee,Seongmin Park,Jongwuk Lee
类目: Information Retrieval (cs.IR)
*备注: SIGIR 2025, 9 pages

点击查看摘要

[IR-1] Understanding Accuracy-Fairness Trade-offs in Re-ranking through Elasticity in Economics SIGIR2025

链接: https://arxiv.org/abs/2504.14991
作者: Chen Xu,Jujia Zhao,Wenjie Wang,Liang Pang,Jun Xu,Tat-Seng Chua,Maarten de Rijke
类目: Information Retrieval (cs.IR)
*备注: Accepted in SIGIR2025

点击查看摘要

[IR-2] ColBERT-serve: Efficient Multi-Stage Memory-Mapped Scoring ECIR2025

链接: https://arxiv.org/abs/2504.14903
作者: Kaili Huang,Thejas Venkatesh,Uma Dingankar,Antonio Mallia,Daniel Campos,Jian Jiao,Christopher Potts,Matei Zaharia,Kwabena Boahen,Omar Khattab,Saarthak Sarup,Keshav Santhanam
类目: Information Retrieval (cs.IR)
*备注: Accepted by ECIR 2025

点击查看摘要

[IR-3] Stitching Inner Product and Euclidean Metrics for Topology-aware Maximum Inner Product Search SIGIR2025

链接: https://arxiv.org/abs/2504.14861
作者: Tingyang Chen,Cong Fu,Xiangyu Ke,Yunjun Gao,Yabo Ni,Anxiang Zeng
类目: Databases (cs.DB); Information Retrieval (cs.IR)
*备注: Accepted by SIGIR 2025

点击查看摘要

[IR-4] Enhancing the Patent Matching Capability of Large Language Models via the Memory Graph

链接: https://arxiv.org/abs/2504.14845
作者: Qiushi Xiong,Zhipeng Xu,Zhenghao Liu,Mengjia Wang,Zulong Chen,Yue Sun,Yu Gu,Xiaohua Li,Ge Yu
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-5] he 1st EReL@MIR Workshop on Efficient Representation Learning for Multimodal Information Retrieval WWW2025

链接: https://arxiv.org/abs/2504.14788
作者: Junchen Fu,Xuri Ge,Xin Xin,Haitao Yu,Yue Feng,Alexandros Karatzoglou,Ioannis Arapakis,Joemon M. Jose
类目: Information Retrieval (cs.IR)
*备注: WWW2025 Workshop Summary

点击查看摘要

[IR-6] Matrix Factorization with Dynamic Multi-view Clustering for Recommender System

链接: https://arxiv.org/abs/2504.14565
作者: Shangde Gao,Ke Liu,Yichao Fu,Hongxia Xu,Jian Wu
类目: Information Retrieval (cs.IR); Social and Information Networks (cs.SI)
*备注:

点击查看摘要

[IR-7] Regret-aware Re-ranking for Guaranteeing Two-sided Fairness and Accuracy in Recommender Systems

链接: https://arxiv.org/abs/2504.14550
作者: Xiaopeng Ye,Chen Xu,Jun Xu,Xuyang Xie,Gang Wang,Zhenhua Dong
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-8] LLM -Driven Usefulness Judgment for Web Search Evaluation

链接: https://arxiv.org/abs/2504.14401
作者: Mouly Dewan,Jiqun Liu,Aditya Gautam,Chirag Shah
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-9] Unconstrained Monotonic Calibration of Predictions in Deep Ranking Systems SIGIR’25

链接: https://arxiv.org/abs/2504.14243
作者: Yimeng Bai,Shunyu Zhang,Yang Zhang,Hu Liu,Wentian Bao,Enyun Yu,Fuli Feng,Wenwu Ou
类目: Information Retrieval (cs.IR)
*备注: Accepted by SIGIR’25

点击查看摘要

[IR-10] mplate-Based Financial Report Generation in Agent ic and Decomposed Information Retrieval SIGIR2025

链接: https://arxiv.org/abs/2504.14233
作者: Yong-En Tian,Yu-Chien Tang,Kuang-Da Wang,An-Zi Yen,Wen-Chih Peng
类目: Information Retrieval (cs.IR)
*备注: 5 pages; 3 figures. Accepted by SIGIR 2025 short paper track. Code available at this https URL

点击查看摘要

[IR-11] ach Me How to Denoise: A Universal Framework for Denoising Multi-modal Recommender Systems via Guided Calibration WSDM

链接: https://arxiv.org/abs/2504.14214
作者: Hongji Li,Hanwen Du,Youhua Li,Junchen Fu,Chunxiao Li,Ziyi Zhuang,Jiakang Li,Yongxin Ni
类目: Information Retrieval (cs.IR)
*备注: Accepted to ACM Web Search and Data Mining (WSDM) 2025

点击查看摘要

[IR-12] FedCIA: Federated Collaborative Information Aggregation for Privacy-Preserving Recommendation

链接: https://arxiv.org/abs/2504.14208
作者: Mingzhe Han,Dongsheng Li,Jiafeng Xia,Jiahao Liu,Hansu Gu,Peng Zhang,Ning Gu,Tun Lu
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

附件下载

点击下载今日全部论文列表

Arxiv今日论文 | 2025-04-22

目录

概览 (2025-04-22)

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