Arxiv今日论文 | 2025-03-04

本篇博文主要内容为 2025-03-04 从Arxiv.org论文网站获取的最新论文列表，自动更新，按照NLP、CV、ML、AI、IR五个大方向区分，若需要邮件定时接收，请在评论区留下你的邮箱号。

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

友情提示: 如何您需要邮箱接收每日论文数据，请在评论处留下你的邮箱。

链接: https://arxiv.org/abs/2503.01844
作者: Miriam Havin,Timna Wharton Kleinman,Moran Koren,Yaniv Dover,Ariel Goldstein
机构: Department of Cognitive and Brain Sciences, The Hebrew University of Jerusalem (耶路撒冷希伯来大学); The Federmann Center for the Study of Rationality, The Hebrew University of Jerusalem (耶路撒冷希伯来大学); School of Computer Science and Engineering, The Hebrew University of Jerusalem (耶路撒冷希伯来大学); Industrial Engineering and Management Department at Ben Gurion Univeristy (本古里安大学); The Hebrew University Business School (耶路撒冷希伯来大学商学院)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-1] EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

链接: https://arxiv.org/abs/2503.01840
作者: Yuhui Li,Fangyun Wei,Chao Zhang,Hongyang Zhang
机构: Peking University (北京大学); Microsoft Research (微软研究); University of Waterloo (滑铁卢大学); Vector Institute (向量研究所)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-2] Jailbreaking Safeguarded Text-to-Image Models via Large Language Models

链接: https://arxiv.org/abs/2503.01839
作者: Zhengyuan Jiang,Yuepeng Hu,Yuchen Yang,Yinzhi Cao,Neil Zhenqiang Gong
机构: 未知
类目: Cryptography and Security (cs.CR); 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-3] CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom

链接: https://arxiv.org/abs/2503.01836
作者: Yisen Li,Lingfeng Yang,Wenxuan Shen,Pan Zhou,Yao Wan,Weiwei Lin,Dongping Chen
机构: Huazhong University of Science and Technology (华中科技大学); South China University of Technology (华南理工大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-4] Rotary Outliers and Rotary Offset Features in Large Language Models

链接: https://arxiv.org/abs/2503.01832
作者: André Jonasson
机构: 未知
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-5] From Language to Cognition: How LLM s Outgrow the Human Language Network

链接: https://arxiv.org/abs/2503.01830
作者: Badr AlKhamissi,Greta Tuckute,Yingtian Tang,Taha Binhuraib,Antoine Bosselut,Martin Schrimpf
机构: EPFL; MIT; Georgia Institute of Technology
类目: Computation and Language (cs.CL)
备注: Preprint

点击查看摘要

[NLP-6] Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models

链接: https://arxiv.org/abs/2503.01829
作者: Nimet Beyza Bozdag,Shuhaib Mehri,Gokhan Tur,Dilek Hakkani-Tür
机构: University of Illinois Urbana-Champaign (伊利诺伊大学厄巴纳-香槟分校)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
备注:

点击查看摘要

[NLP-7] RSQ: Learning from Important Tokens Leads to Better Quantized LLM s

链接: https://arxiv.org/abs/2503.01820
作者: Yi-Lin Sung,Prateek Yadav,Jialu Li,Jaehong Yoon,Mohit Bansal
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Our code is available at this https URL

点击查看摘要

[NLP-8] Do GFlowNets Transfer? Case Study on the Game of 24/42

链接: https://arxiv.org/abs/2503.01819
作者: Adesh Gupta,Abhinav Kumar,Mansi Gupta,Paras Chopra
机构: Indian Institute of Technology, Roorkee (印度理工学院鲁尔基); Lossfunk
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-9] LLM Init: A Free Lunch from Large Language Models for Selective Initialization of Recommendation

链接: https://arxiv.org/abs/2503.01814
作者: Weizhi Zhang,Liangwei Yang,Wooseong Yang,Henry Peng Zou,Yuqing Liu,Ke Xu,Sourav Medya,Philip S. Yu
机构: University of Illinois Chicago(芝加哥伊利诺伊大学); Salesforce AI Research(销售force人工智能研究院)(Palo Alto)(帕洛阿尔托)
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-10] Large-Scale Data Selection for Instruction Tuning

【速读】：该论文试图解决在大规模数据池（数百万样本）中，如何有效选择高质量训练数据以优化指令微调语言模型性能的问题。论文指出，现有的自动化数据选择方法通常仅在小规模数据集（约10k样本，从10万至20万样本池中选取）上进行评估，而实际部署的指令微调模型往往需要从更大的数据池（数百万至千万样本）中子采样数十万到数百万样本。论文的关键解决方案在于提出了一种基于表示的数据选择变体（RDS+），通过预训练语言模型隐藏状态的加权均值池化来实现数据选择。实验结果表明，RDS+不仅在所有测试设置中始终优于其他复杂方法，同时更具计算效率，揭示了现有自动化选择方法在扩展性方面的不足。

链接: https://arxiv.org/abs/2503.01807
作者: Hamish Ivison,Muru Zhang,Faeze Brahman,Pang Wei Koh,Pradeep Dasigi
机构: University of Washington (华盛顿大学); Allen Institute for AI (艾伦人工智能研究所); University of Southern California (南加州大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

Abstract:Selecting high-quality training data from a larger pool is a crucial step when instruction-tuning language models, as carefully curated datasets often produce models that outperform those trained on much larger, noisier datasets. Automated data selection approaches for instruction-tuning are typically tested by selecting small datasets (roughly 10k samples) from small pools (100-200k samples). However, popular deployed instruction-tuned models often train on hundreds of thousands to millions of samples, subsampled from even larger data pools. We present a systematic study of how well data selection methods scale to these settings, selecting up to 2.5M samples from pools of up to 5.8M samples and evaluating across 7 diverse tasks. We show that many recently proposed methods fall short of random selection in this setting (while using more compute), and even decline in performance when given access to larger pools of data to select over. However, we find that a variant of representation-based data selection (RDS+), which uses weighted mean pooling of pretrained LM hidden states, consistently outperforms more complex methods across all settings tested – all whilst being more compute-efficient. Our findings highlight that the scaling properties of proposed automated selection methods should be more closely examined. We release our code, data, and models at this https URL.
zh

[NLP-11] Depth-Width tradeoffs in Algorithmic Reasoning of Graph Tasks with Transformers

链接: https://arxiv.org/abs/2503.01805
作者: Gilad Yehudai,Clayton Sanford,Maya Bechler-Speicher,Orr Fischer,Ran Gilad-Bachrach,Amir Globerson
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-12] textttSEM-CTRL: Semantically Controlled Decoding

链接: https://arxiv.org/abs/2503.01804
作者: Mohammad Albinhassan,Pranava Madhyastha,Alessandra Russo
机构: Department of Computing (计算系), Imperial College London (帝国理工学院); Department of Computer Science (计算机科学系), City, University of London (伦敦城市大学); Department of Computing (计算系), Imperial College London (帝国理工学院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-13] Cats Confuse Reasoning LLM Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models

链接: https://arxiv.org/abs/2503.01781
作者: Meghana Rajeev,Rajkumar Ramamurthy,Prapti Trivedi,Vikas Yadav,Oluwanifemi Bamgbose,Sathwik Tejaswi Madhusudan,James Zou,Nazneen Rajani
机构: Collinear AI; ServiceNow; Stanford University (斯坦福大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-14] Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas

链接: https://arxiv.org/abs/2503.01773
作者: Shiqi Chen,Tongyao Zhu,Ruochen Zhou,Jinghan Zhang,Siyang Gao,Juan Carlos Niebles,Mor Geva,Junxian He,Jiajun Wu,Manling Li
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-15] Retrieval Models Arent Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models

链接: https://arxiv.org/abs/2503.01763
作者: Zhengliang Shi,Yuhan Wang,Lingyong Yan,Pengjie Ren,Shuaiqiang Wang,Dawei Yin,Zhaochun Ren
机构: Shandong University, Qingdao, China (山东大学，青岛，中国); Baidu Inc., Beijing, China (百度公司，北京，中国); Leiden University, Leiden, The Netherlands (莱顿大学，荷兰莱顿)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
备注:

点击查看摘要

[NLP-16] Boolean-aware Attention for Dense Retrieval

链接: https://arxiv.org/abs/2503.01753
作者: Quan Mai,Susan Gauch,Douglas Adams
机构: University of Arkansas (阿肯色大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-17] SAKE: Steering Activations for Knowledge Editing

链接: https://arxiv.org/abs/2503.01751
作者: Marco Scialanga,Thibault Laugel,Vincent Grari,Marcin Detyniecki
机构: AXA(安盛, 法国巴黎); EPFL(洛桑联邦理工学院, 瑞士洛桑); TRAIL, LIP6, Sorbonne Université(图AIL, LIP6,索邦大学, 法国巴黎); Polish Academy of Science, IBS PAN(波兰科学院, 波兰华沙)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-18] Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs

链接: https://arxiv.org/abs/2503.01743
作者: Abdelrahman Abouelenin,Atabak Ashfaq,Adam Atkinson,Hany Awadalla,Nguyen Bach,Jianmin Bao,Alon Benhaim,Martin Cai,Vishrav Chaudhary,Congcong Chen,Dong Chen,Dongdong Chen,Junkun Chen,Weizhu Chen,Yen-Chun Chen,Yi-ling Chen,Qi Dai,Xiyang Dai,Ruchao Fan,Mei Gao,Min Gao,Amit Garg,Abhishek Goswami,Junheng Hao,Amr Hendy,Yuxuan Hu,Xin Jin,Mahmoud Khademi,Dongwoo Kim,Young Jin Kim,Gina Lee,Jinyu Li,Yunsheng Li,Chen Liang,Xihui Lin,Zeqi Lin,Mengchen Liu,Yang Liu,Gilsinia Lopez,Chong Luo,Piyush Madan,Vadim Mazalov,Ali Mousavi,Anh Nguyen,Jing Pan,Daniel Perez-Becker,Jacob Platin,Thomas Portet,Kai Qiu,Bo Ren,Liliang Ren,Sambuddha Roy,Ning Shang,Yelong Shen,Saksham Singhal,Subhojit Som,Xia Song,Tetyana Sych,Praneetha Vaddamanu,Shuohang Wang,Yiming Wang,Zhenghao Wang,Haibin Wu,Haoran Xu,Weijian Xu,Yifan Yang,Ziyi Yang,Donghan Yu,Ishmam Zabir,Jianwen Zhang,Li Lyna Zhang,Yunan Zhang,Xiren Zhou
机构: Microsoft (微软)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 39 pages

点击查看摘要

[NLP-19] Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models

链接: https://arxiv.org/abs/2503.01742
作者: Alberto Purpura,Sahil Wadhwa,Jesse Zymet,Akshay Gupta,Andy Luo,Melissa Kazemi Rad,Swapnil Shinde,Mohammad Shahed Sorower
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-20] Syntactic Learnability of Echo State Neural Language Models at Scale

链接: https://arxiv.org/abs/2503.01724
作者: Ryo Ueda,Tatsuki Kuribayashi,Shunsuke Kando,Kentaro Inui
机构: The University of Tokyo (东京大学); MBZUAI (穆罕默德·本·扎耶德人工智能大学); Tohoku University (东北大学); RIKEN
类目: Computation and Language (cs.CL)
备注: 10 pages

点击查看摘要

[NLP-21] Word Form Matters: LLM s Semantic Reconstruction under Typoglycemia ACL

链接: https://arxiv.org/abs/2503.01714
作者: Chenxi Wang,Tianle Gu,Zhongyu Wei,Lang Gao,Zirui Song,Xiuying Chen
机构: Mohamed bin Zayed University of Artificial Intelligence (MBZUAI); Fudan University
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 14 pages, 10 figures, submitted to ACL Rolling Review, February 2025 cycle, see this https URL

点击查看摘要

[NLP-22] MAPS: Motivation-Aware Personalized Search via LLM -Driven Consultation Alignment

链接: https://arxiv.org/abs/2503.01711
作者: Weicong Qin,Yi Xu,Weijie Yu,Chenglei Shen,Ming He,Jianping Fan,Xiao Zhang,Jun Xu
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); University of International Business and Economics (对外经济贸易大学); AI Lab at Lenovo Research, Lenovo Group Limited (联想研究院，联想集团); Lenovo Inc.
类目: Information Retrieval (cs.IR); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-23] Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation

链接: https://arxiv.org/abs/2503.01700
作者: Yongchao Chen,Yilun Hao,Yang Zhang,Chuchu Fan
机构: Massachusetts Institute of Technology (麻省理工学院); Harvard University (哈佛大学); MIT-IBM Watson AI Lab (麻省理工学院-IBM 沃森人工智能实验室)
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 7 pages, 7 figures, 3 tables

点击查看摘要

[NLP-24] Generate Discriminate Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution

链接: https://arxiv.org/abs/2503.01695
作者: Kun Li,Tianhua Zhang,Yunxiang Li,Hongyin Luo,Abdalla Moustafa,Xixin Wu,James Glass,Helen Meng
机构: The Chinese University of Hong Kong (香港中文大学); 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-25] When an LLM is apprehensive about its answers – and when its uncertainty is justified

链接: https://arxiv.org/abs/2503.01688
作者: Petr Sychev,Andrey Goncharov,Daniil Vyazhev,Edvard Khalafyan,Alexey Zaytsev
机构: Skolkovo Institute of Science and Technology (Skoltech) / Moscow, Russia; National Research University Higher School of Economics / Moscow, Russia; Moscow Institute of Physics and Technology / Moscow, Russia
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-26] Using (Not so) Large Language Models for Generating Simulation Models in a Formal DSL – A Study on Reaction Networks

链接: https://arxiv.org/abs/2503.01675
作者: Justin N. Kreikemeyer,Miłosz Jankowski,Pia Wilsdorf,Adelinde M. Uhrmacher
机构: University of Rostock(罗斯特克大学)
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注: 18 pages, 5 figures

点击查看摘要

[NLP-27] Automated Annotation of Evolving Corpora for Augmenting Longitudinal Network Data: A Framework Integrating Large Language Models and Expert Knowledge

链接: https://arxiv.org/abs/2503.01672
作者: Xiao Liu,Zirui Wu,Jiayi Li,Zhicheng Shao,Xun Pang,Yansong Feng
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 International Studies and Institute for Carbon Neutrality, Peking University (国际关系学院与碳中和研究院，北京大学); Analytics Lab for Global Risk Politics, Peking University (全球风险政治分析实验室，北京大学)
类目: Computation and Language (cs.CL); Social and Information Networks (cs.SI)
备注: Work in progress, presented at the 2025 Asian PolMeth Conference

点击查看摘要

[NLP-28] Evaluating LLM s Assessment of Mixed-Context Hallucination Through the Lens of Summarization

链接: https://arxiv.org/abs/2503.01670
作者: Siya Qi,Rui Cao,Yulan He,Zheng Yuan
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Information Retrieval (cs.IR); Machine Learning (cs.LG)
备注: 8 pages, 5 figures for main body

点击查看摘要

[NLP-29] Detecting Stylistic Fingerprints of Large Language Models

链接: https://arxiv.org/abs/2503.01659
作者: Yehonatan Bitton,Elad Bitton,Shai Nisan
机构: Copyleaks
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-30] he Emergence of Grammar through Reinforcement Learning

链接: https://arxiv.org/abs/2503.01635
作者: Stephen Wechsler,James W. Shearer,Katrin Erk
机构: 未知
类目: Computation and Language (cs.CL); Information Theory (cs.IT)
备注: 49 pages, 8 figures

点击查看摘要

[NLP-31] Annotating and Inferring Compositional Structures in Numeral Systems Across Languages

链接: https://arxiv.org/abs/2503.01625
作者: Arne Rubehn,Christoph Rzymski,Luca Ciucci,Kellen Parker van Dam,Alžběta Kučerová,Katja Bocklage,David Snee,Abishek Stephen,Johann-Mattis List
机构: Chair for Multilingual Computational Linguistics, University of Passau (多语言计算语言学主席职位, 帕绍大学); Department of Linguistic and Cultural Evolution, Max Planck Institute for Evolutionary Anthropology (语言与文化进化系, 马克斯·普朗克进化人类学研究所); Institute of Formal and Applied Linguistics, Charles University (形式与应用语言学研究所, 查理大学)
类目: Computation and Language (cs.CL)
备注: Submitted to the 7th Workshop on Research in Computational Linguistic Typology and Multilingual NLP (SIGTYP)

点击查看摘要

[NLP-32] Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations

链接: https://arxiv.org/abs/2503.01623
作者: David Hartmann,Amin Oueslati,Dimitri Staufer,Lena Pohlmann,Simon Munzert,Hendrik Heuer
机构: TU Berlin (柏林工业大学); Weizenbaum Institute for the Networked Society (魏岑贝格社会网络研究所); Hertie School (赫梯学校); Center for Advanced Internet Studies (CAIS) gGmbH (高级互联网研究中心); University of Wuppertal (伍珀塔尔大学)
类目: Human-Computer Interaction (cs.HC); Computation and Language (cs.CL)
备注: This is the author’s version of the paper accepted at CHI Conference on Human Factors in Computing Systems (CHI '25), April 26-May 1, 2025, Yokohama, Japan

点击查看摘要

[NLP-33] DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation

链接: https://arxiv.org/abs/2503.01622
作者: Eliya Habba,Ofir Arviv,Itay Itzhak,Yotam Perlitz,Elron Bandel,Leshem Choshen,Michal Shmueli-Scheuer,Gabriel Stanovsky
机构: The Hebrew University of Jerusalem (耶路撒冷希伯来大学); IBM Research AI (IBM 研究 AI); Technion - Israel Institute of Technology (以色列理工学院); Allen Institute for AI (艾伦人工智能研究所)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-34] Advancing vision-language models in front-end development via data synthesis

链接: https://arxiv.org/abs/2503.01619
作者: Tong Ge,Yashu Liu,Jieping Ye,Tianyi Li,Chao Wang
机构: KE Holdings Inc. (贝壳控股有限公司); Alibaba Group (阿里巴巴集团)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-35] In-context Learning vs. Instruction Tuning: The Case of Small and Multilingual Language Models

链接: https://arxiv.org/abs/2503.01611
作者: David Ponce,Thierry Etchegoyhen
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-36] Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering

链接: https://arxiv.org/abs/2503.01606
作者: Zhanghao Hu,Hanqi Yan,Qingling Zhu,Zhenyi Shen,Yulan He,Lin Gui
机构: King’s College London (伦敦国王学院); The Alan Turing Institute (阿兰·图灵研究所)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-37] EliteKV: Scalable KV Cache Compression via RoPE Frequency Selection and Joint Low-Rank Projection

链接: https://arxiv.org/abs/2503.01586
作者: Yuhao Zhou,Sirui Song,Boyang Liu,Zhiheng Xi,Senjie Jin,Xiaoran Fan,Zhihao Zhang,Wei Li,Xuanjing Huang
机构: Fudan University (复旦大学)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 13 pages, 8 figures

点击查看摘要

[NLP-38] Attention Condensation via Sparsity Induced Regularized Training

链接: https://arxiv.org/abs/2503.01564
作者: Eli Sason,Darya Frolova,Boris Nazarov,Felix Goldberd
机构: Huawei (华为)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-39] Co-creation for Sign Language Processing and Machine Translation

链接: https://arxiv.org/abs/2503.01553
作者: Lisa Lepp,Dimitar Shterionov,Mirella De Sisto,Grzegorz Chrupała
机构: 未知
类目: Computation and Language (cs.CL)
备注: Submitted to the MDPI special issue “Human and Machine Translation: Recent Trends and Foundations”

点击查看摘要

[NLP-40] None of the Above Less of the Right: Parallel Patterns between Humans and LLM s on Multi-Choice Questions Answering

链接: https://arxiv.org/abs/2503.01550
作者: Zhi Rui Tam,Cheng-Kuang Wu,Chieh-Yen Lin,Yun-Nung Chen
机构: Appier AI Research; National Taiwan University
类目: Computers and Society (cs.CY); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-41] Compositional Reasoning with Transformers RNNs and Chain of Thought

链接: https://arxiv.org/abs/2503.01544
作者: Gilad Yehudai,Noah Amsel,Joan Bruna
机构: Courant Institute of Mathematical Sciences, New York University (库朗数学科学研究所，纽约大学); Center for Data Science, New York University (数据科学中心，纽约大学); Flatiron Institute (弗莱彻研究院)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-42] Revisiting Large Language Model Pruning using Neuron Semantic Attribution

链接: https://arxiv.org/abs/2503.01542
作者: Yizhuo Ding,Xinwei Sun,Yanwei Fu,Guosheng Hu
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-43] Prag matic Inference Chain (PIC) Improving LLM s Reasoning of Authentic Implicit Toxic Language

链接: https://arxiv.org/abs/2503.01539
作者: Xi Chen,Shuo Wang
机构: Nanyang Technological University (南洋理工大学); University of Macau (澳门大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 12 pages, 4 figures, 2 tables

点击查看摘要

[NLP-44] Evaluation and Facilitation of Online Discussions in the LLM Era: A Survey

链接: https://arxiv.org/abs/2503.01513
作者: Katerina Korre,Dimitris Tsirmpas,Nikos Gkoumas,Emma Cabalé,Dionysis Kontarinis,Danai Myrtzani,Theodoros Evgeniou,Ion Androutsopoulos,John Pavlopoulos
机构: Archimedes/Athena RC (雅典娜国家研究中心), Greece; Athens University of Economics and Business (雅典经济与商业大学), Greece; École Normale Supérieure Paris-Saclay (巴黎萨克雷高等师范学校), France; INSEAD, Technology and Business (英士国际商学院), France; Università di Bologna (博洛尼亚大学), Italy
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-45] KoWit-24: A Richly Annotated Dataset of Wordplay in News Headlines

链接: https://arxiv.org/abs/2503.01510
作者: Alexander Baranov,Anna Palatkina,Yulia Makovka,Pavel Braslavski
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-46] SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity

链接: https://arxiv.org/abs/2503.01506
作者: Xiangyu Xi,Deyang Kong,Jian Yang,Jiawei Yang,Zhengyu Chen,Wei Wang,Jingang Wang,Xunliang Cai,Shikun Zhang,Wei Ye
机构: Meituan Group (美团集团); National Engineering Research Center for Software Engineering, Peking University (北京大学软件工程国家工程研究中心)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-47] Liger: Linearizing Large Language Models to Gated Recurrent Structures

链接: https://arxiv.org/abs/2503.01496
作者: Disen Lan,Weigao Sun,Jiaxi Hu,Jusen Du,Yu Cheng
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: Technical report, 13 pages

点击查看摘要

[NLP-48] Llama-3.1-Sherkala-8B-Chat: An Open Large Language Model for Kazakh

链接: https://arxiv.org/abs/2503.01493
作者: Fajri Koto,Rituraj Joshi,Nurdaulet Mukhituly,Yuxia Wang,Zhuohan Xie,Rahul Pal,Daniil Orel,Parvez Mullah,Diana Turmakhan,Maiya Goloburda,Mohammed Kamran,Samujjwal Ghosh,Bokang Jia,Jonibek Mansurov,Mukhammed Togmanov,Debopriyo Banerjee,Nurkhan Laiyk,Akhmed Sakip,Xudong Han,Ekaterina Kochmar,Alham Fikri Aji,Aaryamonvikram Singh,Alok Anil Jadhav,Satheesh Katipomu,Samta Kamboj,Monojit Choudhury,Gurpreet Gosal,Gokul Ramakrishnan,Biswajit Mishra,Sarath Chandran,Avraham Sheinin,Natalia Vassilieva,Neha Sengupta,Larry Murray,Preslav Nakov
机构: Mohamed bin Zayed University of Artificial Intelligence (阿联酋人工智能大学), UAE; Inception (英佩启程), UAE; Cerebras Systems (赛普拉斯系统公司)
类目: Computation and Language (cs.CL)
备注: Technical Report

点击查看摘要

[NLP-49] Improving Retrospective Language Agents via Joint Policy Gradient Optimization NAACL2025

链接: https://arxiv.org/abs/2503.01490
作者: Xueyang Feng,Bo Lan,Quanyu Dai,Lei Wang,Jiakai Tang,Xu Chen,Zhenhua Dong,Ji-Rong Wen
机构: 未知
类目: Computation and Language (cs.CL)
备注: NAACL2025

点击查看摘要

[NLP-50] SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction ICLR2025

链接: https://arxiv.org/abs/2503.01478
作者: Lu Dai,Yijie Xu,Jinhui Ye,Hao Liu,Hui Xiong
机构: The Hong Kong University of Science and Technology (香港科技大学); The Hong Kong University of Science and Technology (Guangzhou) (香港科技大学（广州）); Carnegie Mellon University (卡内基梅隆大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: ICLR 2025 Spotlight

点击查看摘要

[NLP-51] Rethinking Data: Towards Better Performing Domain-Specific Small Language Models

链接: https://arxiv.org/abs/2503.01464
作者: Boris Nazarov,Darya Frolova,Yackov Lubarsky,Alexei Gaissinski,Pavel Kisilev
机构: Huawei (华为), Israel
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-52] owards Widening The Distillation Bottleneck for Reasoning Models

链接: https://arxiv.org/abs/2503.01461
作者: Huifeng Yin,Yu Zhao,Minghao Wu,Xuanfan Ni,Bo Zeng,Hao Wang,Tianqi Shi,Liangying Shao,Chenyang Lyu,Longyue Wang,Weihua Luo,Kaifu Zhang
机构: Alibaba International Digital Commerce (阿里巴巴国际数字商业); Tsinghua University (清华大学); Monash University (蒙纳士大学)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-53] Structural Deep Encoding for Table Question Answering

链接: https://arxiv.org/abs/2503.01457
作者: Raphaël Mouravieff,Benjamin Piwowarski,Sylvain Lamprier
机构: Sorbonne Université (索邦大学), CNRS (法国国家科学研究中心), ISIR (智能系统研究所), F-75005 Paris, France; LERIA, Université d’Angers (昂热大学), France
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 8 pages, 4 figures

点击查看摘要

[NLP-54] AC-Lite : A Lightweight Image Captioning Model for Low-Resource Assamese Language

链接: https://arxiv.org/abs/2503.01453
作者: Pankaj Choudhury,Yogesh Aggarwal,Prithwijit Guha,Sukumar Nandi
机构: Indian Institute of Technology Guwahati (印度理工学院焦亚蒂亚普尔)
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-55] From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems

链接: https://arxiv.org/abs/2503.01424
作者: Zekun Zhou,Xiaocheng Feng,Lei Huang,Xiachong Feng,Ziyun Song,Ruihan Chen,Liang Zhao,Weitao Ma,Yuxuan Gu,Baoxin Wang,Dayong Wu,Guoping Hu,Ting Liu,Bing Qin
机构: Harbin Institute of Technology (哈尔滨工业大学); Peng Cheng Laboratory (鹏城实验室); The University of Hong Kong (香港大学); iFLYTEK Research (科大讯飞研究院)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-56] Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding

链接: https://arxiv.org/abs/2503.01422
作者: Yiming Wang,Pei Zhang,Siyuan Huang,Baosong Yang,Zhuosheng Zhang,Fei Huang,Rui Wang
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 23 pages, 14 figures, 8 tables

点击查看摘要

[NLP-57] Parameter-Efficient Fine-Tuning of Large Language Models via Deconvolution in Subspace COLING2025

链接: https://arxiv.org/abs/2503.01419
作者: Jia-Chen Zhang,Yu-Jie Xiong,Chun-Ming Xia,Dong-Hai Zhu,Xi-He Qiu
机构: School of Electronic and Electrical Engineering, Shanghai University of Engineering Science (上海工程技术大学电子电气工程学院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: COLING 2025 main conference

点击查看摘要

[NLP-58] Geo-Semantic-Parsing: AI-powered geoparsing by traversing semantic knowledge graphs

链接: https://arxiv.org/abs/2503.01386
作者: Leonardo Nizzoli,Marco Avvenuti,Maurizio Tesconi,Stefano Cresci
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Social and Information Networks (cs.SI)
备注: Postprint of the article published in the Decision Support Systems journal. Please, cite accordingly

点击查看摘要

[NLP-59] Q-NL Verifier: Leverag ing Synthetic Data for Robust Knowledge Graph Question Answering

链接: https://arxiv.org/abs/2503.01385
作者: Tim Schwabe,Louisa Siebel,Patrik Valach,Maribel Acosta
机构: Technical University of Munich (慕尼黑工业大学)
类目: Computation and Language (cs.CL); Databases (cs.DB); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-60] SwiLTra-Bench: The Swiss Legal Translation Benchmark

链接: https://arxiv.org/abs/2503.01372
作者: Joel Niklaus,Jakob Merane,Luka Nenadic,Sina Ahmadi,Yingqiang Gao,Cyrill A. H. Chevalley,Claude Humbel,Christophe Gösken,Lorenzo Tanzi,Thomas Lüthi,Stefan Palombo,Spencer Poff,Boling Yang,Nan Wu,Matthew Guillod,Robin Mamié,Daniel Brunner,Julio Pereyra,Niko Grupen
机构: EETH Zurich (苏黎世联邦理工学院); Swiss Federal Supreme Court (瑞士联邦最高法院); University of Zurich (苏黎世大学); University of Basel (巴塞尔大学); University of Geneva (日内瓦大学); University of Lausanne (洛桑大学); Canton of Solothurn (索洛图恩州); Max Planck Institute for Research on Collective Goods (马克斯·普朗克集体货物研究所)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-61] SRAG : Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph

链接: https://arxiv.org/abs/2503.01346
作者: Teng Lin,Yizhang Zhu,Yuyu Luo,Nan Tang
机构: DSA, HKUST(GZ); HKUST
类目: Computation and Language (cs.CL); Information Retrieval (cs.IR)
备注:

点击查看摘要

[NLP-62] Same Question Different Words: A Latent Adversarial Framework for Prompt Robustness

链接: https://arxiv.org/abs/2503.01345
作者: Tingchen Fu,Fazl Barez
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-63] Answer Refuse or Guess? Investigating Risk-Aware Decision Making in Language Models

链接: https://arxiv.org/abs/2503.01332
作者: Cheng-Kuang Wu,Zhi Rui Tam,Chieh-Yen Lin,Yun-Nung Chen,Hung-yi Lee
机构: Appier AI Research (Appier AI 研究院); National Taiwan University (台湾大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: preprint

点击查看摘要

[NLP-64] WeightedKV: Attention Scores Weighted Key-Value Cache Merging for Large Language Models ICASSP2025

链接: https://arxiv.org/abs/2503.01330
作者: Jian Yuan,Ziwei He,Haoli Bai,Jingwen Leng,Bo Jiang
机构: Shanghai Jiao Tong University (上海交通大学); Huawei Noah’s Ark Lab (华为诺亚方舟实验室)
类目: Computation and Language (cs.CL)
备注: Accepted by ICASSP 2025

点击查看摘要

[NLP-65] Explainable Depression Detection in Clinical Interviews with Personalized Retrieval-Augmented Generation

链接: https://arxiv.org/abs/2503.01315
作者: Linhai Zhang,Ziyang Gao,Deyu Zhou,Yulan He
机构: King’s College London (伦敦国王学院); Southeast University (东南大学); The Alan Turing Institute (图灵研究所)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-66] Cognitive Behaviors that Enable Self-Improving Reason ers or Four Habits of Highly Effective STaRs

链接: https://arxiv.org/abs/2503.01307
作者: Kanishk Gandhi,Ayush Chakravarthy,Anikait Singh,Nathan Lile,Noah D. Goodman
机构: Stanford University (斯坦福大学); SynthLabs (SynthLabs)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-67] PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation

链接: https://arxiv.org/abs/2503.01303
作者: Linhai Zhang,Jialong Wu,Deyu Zhou,Yulan He
机构: King’s College London (伦敦国王学院); Southeast University (东南大学); The Alan Turing Institute (图灵研究所)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-68] Causal Tree Extraction from Medical Case Reports: A Novel Task for Experts-like Text Comprehension

链接: https://arxiv.org/abs/2503.01302
作者: Sakiko Yahata,Zhen Wan,Fei Cheng,Sadao Kurohashi,Hisahiko Sato,Ryozo Nagai
机构: Kyoto University (京都大学); Precision Inc. (精密股份有限公司); Jichi Medical University (自治医科大学)
类目: Computation and Language (cs.CL)
备注: Work in progress

点击查看摘要

[NLP-69] Enhancing Non-English Capabilities of English-Centric Large Language Models through Deep Supervision Fine-Tuning AAAI2025

链接: https://arxiv.org/abs/2503.01275
作者: Wenshuai Huo,Xiaocheng Feng,Yichong Huang,Chengpeng Fu,Baohang Li,Yangfan Ye,Zhirui Zhang,Dandan Tu,Duyu Tang,Yunfei Lu,Hui Wang,Bing Qin
机构: 未知
类目: Computation and Language (cs.CL)
备注: Accepted at AAAI 2025

点击查看摘要

[NLP-70] ChatGPT for President! Presupposed content in politicians versus GPT -generated texts

链接: https://arxiv.org/abs/2503.01269
作者: Davide Garassino,Nicola Brocca,Viviana Masia
机构: 未知
类目: Computation and Language (cs.CL); Computers and Society (cs.CY)
备注: 36 pages, 6 figures

点击查看摘要

[NLP-71] Generalizable Prompt Learning of CLIP: A Brief Overview

链接: https://arxiv.org/abs/2503.01263
作者: Fangming Cui,Yonggang Zhang,Xuan Wang,Xule Wang,Liang Xiao
机构: Shanghai Jiao Tong University (上海交通大学); Hong Kong Baptist University (香港浸会大学); Meituan Inc. (美团); Liang Xiao (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-72] Your Model is Overconfident and Other Lies We Tell Ourselves

链接: https://arxiv.org/abs/2503.01235
作者: Timothee Mickus,Aman Sinha,Raúl Vázquez
机构: University of Helsinki (赫尔辛基大学); Université de Lorraine (洛林大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-73] PEO: Improving Bi-Factorial Preference Alignment with Post-Training Policy Extrapolation

链接: https://arxiv.org/abs/2503.01233
作者: Yuxuan Liu
机构: Peking University (北京大学)
类目: Computation and Language (cs.CL)
备注: Technical report, work in progress

点击查看摘要

[NLP-74] Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG

链接: https://arxiv.org/abs/2503.01222
作者: Wenbin Wang,Yongcheng Jing,Liang Ding,Yingjie Wang,Li Shen,Yong Luo,Bo Du,Dacheng Tao
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-75] HREB-CRF: Hierarchical Reduced-bias EMA for Chinese Named Entity Recognition

链接: https://arxiv.org/abs/2503.01217
作者: Sijin Sun,Ming Deng,Xinrui Yu,Liangbin Zhao
机构: 未知
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: 18 pages, 10 figures, under Review

点击查看摘要

[NLP-76] Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models

链接: https://arxiv.org/abs/2503.01208
作者: Tianjie Ju,Yi Hua,Hao Fei,Zhenyu Shao,Yubin Zheng,Haodong Zhao,Mong-Li Lee,Wynne Hsu,Zhuosheng Zhang,Gongshen Liu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注: Working in progress

点击查看摘要

[NLP-77] Cancer Type Stage and Prognosis Assessment from Pathology Reports using LLM s

链接: https://arxiv.org/abs/2503.01194
作者: Rachit Saluja,Jacob Rosenthal,Yoav Artzi,David J. Pisapia,Benjamin L. Liechty,Mert R. Sabuncu
机构: 未知
类目: Computation and Language (cs.CL); Information Retrieval (cs.IR)
备注:

点击查看摘要

[NLP-78] alking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics ICLR2025

链接: https://arxiv.org/abs/2503.01174
作者: Siddhant Arora,Zhiyun Lu,Chung-Cheng Chiu,Ruoming Pang,Shinji Watanabe
机构: Carnegie Mellon University (卡内基梅隆大学); Apple (苹果公司)
类目: Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)
备注: Accepted at ICLR 2025

点击查看摘要

[NLP-79] Bandit-Based Prompt Design Strategy Selection Improves Prompt Optimizers

链接: https://arxiv.org/abs/2503.01163
作者: Rin Ashizawa,Yoichi Hirose,Nozomu Yoshinari,Kento Uchida,Shinichi Shirakawa
机构: Yokohama National University (横滨国立大学)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
备注:

点击查看摘要

[NLP-80] Large Language Models for Healthcare Text Classification: A Systematic Review

链接: https://arxiv.org/abs/2503.01159
作者: Hajar Sakai,Sarah S. Lam
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-81] Nature-Inspired Population-Based Evolution of Large Language Models

链接: https://arxiv.org/abs/2503.01155
作者: Yiqun Zhang,Peng Ye,Xiaocui Yang,Shi Feng,Shufei Zhang,Lei Bai,Wanli Ouyang,Shuyue Hu
机构: Northeastern University, China (东北大学, 中国); Shanghai Artificial Intelligence Laboratory (上海人工智能实验室)
类目: Computation and Language (cs.CL)
备注: preprint

点击查看摘要

[NLP-82] ReaderLM-v2: Small Language Model for HTML to Markdown and JSON

链接: https://arxiv.org/abs/2503.01151
作者: Feng Wang,Zesheng Shi,Bo Wang,Nan Wang,Han Xiao
机构: Jina AI GmbH (Jina AI有限公司)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
备注: 9 pages, 10-12 refs

点击查看摘要

[NLP-83] MiLiC-Eval: Benchmarking Multilingual LLM s for Chinas Minority Languages

链接: https://arxiv.org/abs/2503.01150
作者: Chen Zhang,Mingxu Tao,Zhiyuan Liao,Yansong Feng
机构: Peking University (北京大学)
类目: Computation and Language (cs.CL)
备注: Code and data available at this https URL

点击查看摘要

[NLP-84] How Well do LLM s Compress Their Own Chain-of-Thought? A Token Complexity Approach

链接: https://arxiv.org/abs/2503.01141
作者: Ayeong Lee,Ethan Che,Tianyi Peng
机构: Columbia Business School (哥伦比亚商学院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-85] Beyond QA Pairs: Assessing Parameter-Efficient Fine-Tuning for Fact Embedding in LLM s AAAI2025

链接: https://arxiv.org/abs/2503.01131
作者: Shivam Ratnakar,Abhiroop Talasila,Raghav Chamadiya,Nikhil Agarwal,Vinayak K Doifode
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Presented at the Workshop on Preparing Good Data for Generative AI: Challenges and Approaches (Good-Data) in conjunction with AAAI 2025. The authors retain the copyright

点击查看摘要

[NLP-86] SolBench: A Dataset and Benchmark for Evaluating Functional Correctness in Solidity Code Completion and Repair

链接: https://arxiv.org/abs/2503.01098
作者: Zaoyu Chen,Haoran Qin,Nuo Chen,Xiangyu Zhao,Lei Xue,Xiapu Luo,Xiao-Ming Wu
机构: The Hong Kong Polytechnic University (香港理工大学); Sun Yat-sen University (中山大学)
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-87] Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLM s ICLR2025

链接: https://arxiv.org/abs/2503.01090
作者: Haowen Pan,Xiaozhi Wang,Yixin Cao,Zenglin Shi,Xun Yang,Juanzi Li,Meng Wang
机构: University of Science and Technology of China (中国科学技术大学); Department of Computer Science and Technology, BNRist, Tsinghua University (清华大学计算机科学与技术系, 类脑智能技术及应用国家工程实验室); School of Computer Science, Fudan University (复旦大学计算机学院); Hefei University of Technology (合肥工业大学)
类目: Computation and Language (cs.CL)
备注: ICLR 2025

点击查看摘要

[NLP-88] Efficient or Powerful? Trade-offs Between Machine Learning and Deep Learning for Mental Illness Detection on Social Media

链接: https://arxiv.org/abs/2503.01082
作者: Zhanyi Ding,Zhongyan Wang,Yeyubei Zhang,Yuchen Cao,Yunchong Liu,Xiaorui Shen,Yexin Tian,Jianglai Dai
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-89] Alchemist: Towards the Design of Efficient Online Continual Learning System

链接: https://arxiv.org/abs/2503.01066
作者: Yuyang Huang,Yuhan Liu,Haryadi S. Gunawi,Beibin Li,Changho Hwang
机构: The University of Chicago (芝加哥大学); Microsoft Research (微软研究院); Microsoft Research (微软研究院); The University of Chicago (芝加哥大学); The University of Chicago (芝加哥大学); Microsoft Research (微软研究院); Microsoft Research (微软研究院)
类目: Machine Learning (cs.LG); Computation and Language (cs.CL); Distributed, Parallel, and Cluster Computing (cs.DC)
备注:

点击查看摘要

[NLP-90] Scientific Reasoning : Assessment of Multimodal Generative LLM s

链接: https://arxiv.org/abs/2503.01064
作者: Florian Dreyer,Ekaterina Kolos,Daria Matiash
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[NLP-91] AI-Invented Tonal Languages: Preventing a Machine Lingua Franca Beyond Human Understanding

链接: https://arxiv.org/abs/2503.01063
作者: David Noever
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-92] Language-agnostic automated assessment of listeners speech recall using large language models

链接: https://arxiv.org/abs/2503.01045
作者: Björn Herrmann
机构: 未知
类目: Computation and Language (cs.CL)
备注: 37 pages, 5 figure, 1 table

点击查看摘要

[NLP-93] Variance reduction in output from generative AI

链接: https://arxiv.org/abs/2503.01033
作者: Yu Xie,Yueqi Xie
机构: Paul and Marcia Center on Contemporary China, Princeton University (保罗与玛丽亚当代中国中心，普林斯顿大学); Center for Social Research, Guanghua School of Management, Peking University (社会研究中心，光华管理学院，北京大学); Hong Kong University of Science and Technology (香港科技大学)
类目: Computers and Society (cs.CY); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-94] Language Models Predict Empathy Gaps Between Social In-groups and Out-groups NAACL2025

链接: https://arxiv.org/abs/2503.01030
作者: Yu Hou,Hal Daumé III,Rachel Rudinger
机构: University of Maryland (马里兰大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: NAACL 2025

点击查看摘要

[NLP-95] A Semantic Search Pipeline for Causality-driven Adhoc Information Retrieval

链接: https://arxiv.org/abs/2503.01003
作者: Dhairya Dalal,Sharmi Dev Gupta,Bentolhoda Binaei
机构: SFI Centre for Research and Training in Artificial Intelligence (SFI 人工智能研究中心), National University of Ireland Galway (爱尔兰国立高威大学); SFI Centre for Research and Training in Artificial Intelligence (SFI 人工智能研究中心), School of Computer Science and Information Technology (计算机科学与信息技术学院), University College Cork
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-96] Evaluating Polish linguistic and cultural competency in large language models

链接: https://arxiv.org/abs/2503.00995
作者: Sławomir Dadas,Małgorzata Grębowiec,Michał Perełkiewicz,Rafał Poświata
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-97] Evidence of conceptual mastery in the application of rules by Large Language Models

链接: https://arxiv.org/abs/2503.00992
作者: José Luiz Nunes,Guilherme FCF Almeida,Brian Flanagan
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-98] Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study

链接: https://arxiv.org/abs/2503.00985
作者: Bashar Alhafni,Nizar Habash
机构: Computational Approaches to Modeling Language Lab (计算建模语言实验室); New York University Abu Dhabi (纽约大学阿布扎比分校)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-99] Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLM s

链接: https://arxiv.org/abs/2503.00979
作者: Ravi Ghadia,Avinash Kumar,Gaurav Jain,Prashant Nair,Poulami Das
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-100] Layered Insights: Generalizable Analysis of Authorial Style by Leverag ing All Transformer Layers

链接: https://arxiv.org/abs/2503.00958
作者: Milad Alshomary,Nikhil Reddy Varimalla,Vishal Anand,Kathleen McKeown
机构: Columbia University (哥伦比亚大学); Microsoft (微软)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-101] SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking

链接: https://arxiv.org/abs/2503.00955
作者: Nam V. Nguyen,Dien X. Tran,Thanh T. Tran,Anh T. Hoang,Tai V. Duong,Di T. Le,Phuc-Lu Le
机构: FPT Software AI Center (FPT 软件人工智能中心); Faculty of Information Technology, Industrial University of Ho Chi Minh City (工业大学胡志明市信息技术学院); Faculty of Information Technology, University of Science, VNU-HCM (大学科学学院，VNU-HCM); FPT Telecom (FPT 电信)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 18 pages

点击查看摘要

[NLP-102] HiBench: Benchmarking LLM s Capability on Hierarchical Structure Reasoning

链接: https://arxiv.org/abs/2503.00912
作者: Zhuohang Jiang,Pangjing Wu,Ziran Liang,Peter Q. Chen,Xu Yuan,Ye Jia,Jiancheng Tu,Chen Li,Peter H.F. Ng,Qing Li
机构: The Hong Kong Polytechnic University (香港理工大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-103] Unveiling Biases while Embracing Sustainability: Assessing the Dual Challenges of Automatic Speech Recognition Systems INTERSPEECH2024

链接: https://arxiv.org/abs/2503.00907
作者: Ajinkya Kulkarni,Atharva Kulkarni,Miguel Couceiro,Isabel Trancoso
机构: 未知
类目: Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)
备注: Interspeech 2024

点击查看摘要

[NLP-104] Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction NAACL2025

链接: https://arxiv.org/abs/2503.00902
作者: Liping Liu,Chunhong Zhang,Likang Wu,Chuang Zhao,Zheng Hu,Ming He,Jianping Fan
机构: Beijing University of Posts and Telecommunications (北京邮电大学); AI Lab of Lenovo Research (联想研究AI实验室); Tianjin University (天津大学); The Hong Kong University of Science and Technology (香港科技大学)
类目: Computation and Language (cs.CL)
备注: 23 pages, 5 figures, accepted by NAACL2025

点击查看摘要

[NLP-105] DUAL: Diversity and Uncertainty Active Learning for Text Summarization

链接: https://arxiv.org/abs/2503.00867
作者: Petros Stylianos Giouroukis,Alexios Gidiotis,Grigorios Tsoumakas
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-106] Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers

链接: https://arxiv.org/abs/2503.00865
作者: Yiran Zhao,Chaoqun Liu,Yue Deng,Jiahao Ying,Mahani Aljunied,Zhaodonghui Li,Lidong Bing,Hou Pong Chan,Yu Rong,Deli Zhao,Wenxuan Zhang
机构: DAMO Academy, Alibaba Group (达摩院, 阿里巴巴集团)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-107] Argument Summarization and its Evaluation in the Era of Large Language Models

链接: https://arxiv.org/abs/2503.00847
作者: Moritz Altemeyer,Steffen Eger,Johannes Daxenberger,Tim Altendorf,Philipp Cimiano,Benjamin Schiller
机构: Natural Language Learning & Generation (NLLG), Summetix; Bielefeld University (比勒费尔德大学); University of Technology Nuremberg (纽伦堡技术大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-108] Rewarding Graph Reasoning Process makes LLM s more Generalized Reason ers

链接: https://arxiv.org/abs/2503.00845
作者: Miao Peng,Nuo Chen,Zongrui Suo,Jia Li
机构: The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学（广州）); The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学（广州)); The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学（广州)); The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学（广州）)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-109] Waste Not Want Not; Recycled Gumbel Noise Improves Consistency in Natural Language Generation NEURIPS NAACL2025

链接: https://arxiv.org/abs/2503.00831
作者: Damien de Mijolla,Hannan Saddiq,Kim Moore
机构: Faculty Science Ltd (Faculty Science Ltd)
类目: Computation and Language (cs.CL)
备注: Accepted to NAACL 2025 main conference; Presented at Neurips Safe Generative AI workshop

点击查看摘要

[NLP-110] Predictive Data Selection: The Data That Predicts Is the Data That Teaches

链接: https://arxiv.org/abs/2503.00808
作者: Kashun Shum,Yuzhen Huang,Hongjian Zou,Ding Qi,Yixuan Liao,Xiaoxin Chen,Qian Liu,Junxian He
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-111] DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting

链接: https://arxiv.org/abs/2503.00784
作者: Kai Lv,Honglin Guo,Qipeng Guo,Xipeng Qiu
机构: Fudan University (复旦大学); Shanghai AI Laboratory (上海人工智能实验室)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-112] Evaluating Personalized Tool-Augmented LLM s from the Perspectives of Personalization and Proactivity

链接: https://arxiv.org/abs/2503.00771
作者: Yupu Hao,Pengfei Cao,Zhuoran Jin,Huanxuan Liao,Yubo Chen,Kang Liu,Jun Zhao
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-113] RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery

链接: https://arxiv.org/abs/2503.00751
作者: Hongchao Gu,Dexun Li,Kuicai Dong,Hao Zhang,Hang Lv,Hao Wang,Defu Lian,Yong Liu,Enhong Chen
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: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-114] Unmasking Digital Falsehoods: A Comparative Analysis of LLM -Based Misinformation Detection Strategies

链接: https://arxiv.org/abs/2503.00724
作者: Tianyi Huang,Jingyuan Yi,Peiyang Yu,Xiaochuan Xu
机构: Department of Electrical Engineering and Computer Sciences (电气工程与计算机科学系), University of California, Berkeley (加州大学伯克利分校); The Information Networking Institute (信息网络研究院), Carnegie Mellon University (卡内基梅隆大学), Pittsburgh, PA, USA
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-115] owards hyperparameter-free optimization with differential privacy ICLR2025

链接: https://arxiv.org/abs/2503.00703
作者: Zhiqi Bu,Ruixuan Liu
机构: Amazon (亚马逊); Emory University (埃默里大学)
类目: Machine Learning (cs.LG); Computation and Language (cs.CL); Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to ICLR 2025 spotlight

点击查看摘要

[NLP-116] How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code

链接: https://arxiv.org/abs/2503.00691
作者: Seonghyeon Lee,Heejae Chon,Joonwon Jang,Dongha Lee,Hwanjo Yu
机构: School of Computer Science and Engineering, Kyungpook National University (国立庆北大学); Department of Computer Science and Engineering, POSTECH (浦项工科大学); Department of Artificial Intelligence, Yonsei University (延世大学)
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-117] An evaluation of DeepSeek Models in Biomedical Natural Language Processing

链接: https://arxiv.org/abs/2503.00624
作者: Zaifu Zhan,Shuang Zhou,Huixue Zhou,Jiawen Deng,Yu Hou,Jeremy Yeung,Rui Zhang
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Plan to submit to AMIA 2025 Annual Symposium. 10 pages

点击查看摘要

[NLP-118] Semantic Integrity Constraints: Declarative Guardrails for AI-Augmented Data Processing Systems

链接: https://arxiv.org/abs/2503.00600
作者: Alexander W. Lee,Justin Chan,Michael Fu,Nicolas Kim,Akshay Mehta,Deepti Raghavan,Ugur Cetintemel
机构: Brown University (布朗大学)
类目: Databases (cs.DB); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-119] Zero-Shot Keyphrase Generation: Investigating Specialized Instructions and Multi-Sample Aggregation on Large Language Models NAACL2025

链接: https://arxiv.org/abs/2503.00597
作者: Jayanth Mohan,Jishnu Ray Chowdhury,Tomas Malik,Cornelia Caragea
机构: University of Illinois Chicago (芝加哥大学伊利诺伊分校)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Accepted at NAACL 2025

点击查看摘要

[NLP-120] BadJudge: Backdoor Vulnerabilities of LLM -as-a-Judge ICLR2025

链接: https://arxiv.org/abs/2503.00596
作者: Terry Tong,Fei Wang,Zhe Zhao,Muhao Chen
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
备注: Published to ICLR 2025

点击查看摘要

[NLP-121] LoR2C : Low-Rank Residual Connection Adaptation for Parameter-Efficient Fine-Tuning

链接: https://arxiv.org/abs/2503.00572
作者: Jiancheng Zhao,Xingda Yu,Yuxiang Zhang,Zhen Yang
机构: School of Computer Science and Technology (计算机科学与技术学院), Shandong University (山东大学), Qingdao, China (中国)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-122] Instructor-Worker Large Language Model System for Policy Recommendation: a Case Study on Air Quality Analysis of the January 2025 Los Angeles Wildfires

链接: https://arxiv.org/abs/2503.00566
作者: Kyle Gao,Dening Lu,Liangzhi Li,Nan Chen,Hongjie He,Linlin Xu,Jonathan Li
机构: 未知
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-123] oolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models ICLR2025

链接: https://arxiv.org/abs/2503.00564
作者: Jeonghoon Shim,Gyuhyeon Seo,Cheongsu Lim,Yohan Jo
机构: Graduate School of Data Science, Seoul National University (首尔国立大学数据科学研究生院); Department of Industrial and Management Engineering, Korea University (韩国大学工业与管理工程系)
类目: Computation and Language (cs.CL)
备注: Accepted to ICLR 2025

点击查看摘要

[NLP-124] Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions

链接: https://arxiv.org/abs/2503.00501
作者: Jia Chen,Qian Dong,Haitao Li,Xiaohui He,Yan Gao,Shaosheng Cao,Yi Wu,Ping Yang,Chen Xu,Yao Hu,Qingyao Ai,Yiqun Liu
机构: Xiaohongshu Inc.; Tsinghua University (清华大学)
类目: Information Retrieval (cs.IR); Computation and Language (cs.CL)
备注: 11 pages

点击查看摘要

[NLP-125] utorial Proposal: Speculative Decoding for Efficient LLM Inference COLING2025

链接: https://arxiv.org/abs/2503.00491
作者: Heming Xia,Cunxiao Du,Yongqi Li,Qian Liu,Wenjie Li
机构: The Hong Kong Polytechnic University (香港理工大学); Sea AI Lab (海洋人工智能实验室)
类目: Computation and Language (cs.CL)
备注: COLING 2025 Tutorial. Our homepage: this https URL

点击查看摘要

[NLP-126] Embracing Diversity: A Multi-Perspective Approach with Soft Labels

链接: https://arxiv.org/abs/2503.00489
作者: Benedetta Muscato,Praveen Bushipaka,Gizem Gezici,Lucia Passaro,Fosca Giannotti,Tommaso Cucinotta
机构: Scuola Normale Superiore (高等师范学校); Scuola Superiore Sant’Anna (圣安娜高等学院); University of Pisa (比萨大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
备注:

点击查看摘要

[NLP-127] Unstable Grounds for Beautiful Trees? Testing the Robustness of Concept Translations in the Compilation of Multilingual Wordlists

链接: https://arxiv.org/abs/2503.00464
作者: David Snee,Luca Ciucci,Arne Rubehn,Kellen Parker van Dam,Johann-Mattis List
机构: Chair for Multilingual Computational Linguistics, University of Passau (多语言计算语言学讲席，帕绍大学)
类目: Computation and Language (cs.CL)
备注: Submitted to the 7th Workshop on Research in Computational Linguistic Typology and Multilingual NLP (SIGTYP)

点击查看摘要

[NLP-128] Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Models

链接: https://arxiv.org/abs/2503.00449
作者: Yanyue Zhang,Yulan He,Deyu Zhou
机构: School of Computer Science and Engineering, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University (东南大学), China; Department of Informatics, King’s College London (伦敦国王学院); The Alan Turing Institute (图灵研究所)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 17 pages, 3 figures

点击查看摘要

[NLP-129] Figurative Archive: an open dataset and web-based application for the study of metaphor

链接: https://arxiv.org/abs/2503.00444
作者: Maddalena Bressler,Veronica Mangiaterra,Paolo Canal,Federico Frau,Fabrizio Luciani,Biagio Scalingi,Chiara Barattieri di San Pietro,Chiara Battaglini,Chiara Pompei,Fortunata Romeo,Luca Bischetti,Valentina Bambini
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-130] AILS-NTUA at SemEval-2025 Task 8: Language-to-Code prompting and Error Fixing for Tabular Question Answering

链接: https://arxiv.org/abs/2503.00435
作者: Andreas Evangelatos,Giorgos Filandrianos,Maria Lymperaiou,Athanasios Voulodimos,Giorgos Stamou
机构: National Technical University of Athens (国立雅典技术大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-131] A Multi-Labeled Dataset for Indonesian Discourse: Examining Toxicity Polarization and Demographics Information

链接: https://arxiv.org/abs/2503.00417
作者: Lucky Susanto,Musa Wijanarko,Prasetia Pratama,Zilu Tang,Fariz Akyas,Traci Hong,Ika Idris,Alham Aji,Derry Wijaya
机构: Monash University Indonesia (Monash University 印尼校区); Boston University (波士顿大学); MBZUAI (穆罕默德·本·扎耶德人工智能大学); Independent Researcher (独立研究员)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-132] Smoothing Grounding and Reasoning for MLLM -Powered GUI Agents with Query-Oriented Pivot Tasks

链接: https://arxiv.org/abs/2503.00401
作者: Zongru Wu,Pengzhou Cheng,Zheng Wu,Tianjie Ju,Zhuosheng Zhang,Gongshen Liu
机构: School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University (上海交通大学电子信息技术与电气工程学院)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Human-Computer Interaction (cs.HC)
备注:

点击查看摘要

[NLP-133] Approaching the Limits to EFL Writing Enhancement with AI-generated Text and Diverse Learners

链接: https://arxiv.org/abs/2503.00367
作者: David James Woo,Hengky Susanto,Chi Ho Yeung,Kai Guo,Yilin Huang
机构: 未知
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-134] BERT-based model for Vietnamese Fact Verification Dataset

链接: https://arxiv.org/abs/2503.00356
作者: Bao Tran,T. N. Khanh,Khang Nguyen Tuong,Thien Dang,Quang Nguyen,Nguyen T. Thinh,Vo T. Hung
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: accepted for Oral Presentation in CITA 2024 (The 13th Conference on Information Technology and Its Applications) and will be published in VOLUME 1 OF CITA 2024 (Volume of the Lecture Notes in Network and Systems, Springer)

点击查看摘要

[NLP-135] Structured Reasoning for Fairness: A Multi-Agent Approach to Bias Detection in Textual Data AAAI2025

链接: https://arxiv.org/abs/2503.00355
作者: Tianyi Huang,Elsa Fan
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Accepted Paper (Oral Presentation) in the Workshop on the Social Impact of AI: Research, Diversity and Inclusion Frameworks at AAAI 2025

点击查看摘要

[NLP-136] U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack

链接: https://arxiv.org/abs/2503.00353
作者: Yunfan Gao,Yun Xiong,Wenlong Wu,Zijing Huang,Bohan Li,Haofen Wang
机构: Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University (同济大学); Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University (复旦大学); College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics (南京航空航天大学); College of Design and Innovation, Tongji University (同济大学)
类目: Computation and Language (cs.CL); Information Retrieval (cs.IR)
备注:

点击查看摘要

[NLP-137] Hierarchical Multi-Stage BERT Fusion Framework with Dual Attention for Enhanced Cyberbullying Detection in Social Media

链接: https://arxiv.org/abs/2503.00342
作者: Jiani Wang,Xiaochuan Xu,Peiyang Yu,Zeqiu Xu
机构: Stanford University (斯坦福大学); 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-138] More of the Same: Persistent Representational Harms Under Increased Representation

链接: https://arxiv.org/abs/2503.00333
作者: Jennifer Mickel,Maria De-Arteaga,Leqi Liu,Kevin Tian
机构: The University of Texas at Austin (德克萨斯大学奥斯汀分校); The University of Texas at Austin (德克萨斯大学奥斯汀分校); The University of Texas at Austin (德克萨斯大学奥斯汀分校)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 26 pages, 7 figures, 6 tables, pre-print

点击查看摘要

[NLP-139] How Deep is Love in LLM s Hearts? Exploring Semantic Size in Human-like Cognition

链接: https://arxiv.org/abs/2503.00330
作者: Yao Yao,Yifei Yang,Xinbei Ma,Dongjie Yang,Zhuosheng Zhang,Zuchao Li,Hai Zhao
机构: Shanghai Jiao Tong University (上海交通大学); Wuhan University (武汉大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-140] Unlocking Efficient Scalable and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning ICLR2025

链接: https://arxiv.org/abs/2503.00306
作者: Tianci Liu,Ruirui Li,Yunzhe Qi,Hui Liu,Xianfeng Tang,Tianqi Zheng,Qingyu Yin,Monica Xiao Cheng,Jun Huan,Haoyu Wang,Jing Gao
机构: Department of Computer Science (计算机科学系), Cranberry-Lemon University (Cranberry-Lemon 大学); Department of Computational Neuroscience (计算神经科学系), University of the Witwatersrand (约翰内斯堡大学)
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: ICLR 2025

点击查看摘要

[NLP-141] Robust Multi-Objective Preference Alignment with Online DPO AAAI2025

链接: https://arxiv.org/abs/2503.00295
作者: Raghav Gupta,Ryan Sullivan,Yunxuan Li,Samrat Phatale,Abhinav Rastogi
机构: Google(谷歌)
类目: Computation and Language (cs.CL); Machine Learning (cs.LG)
备注: AAAI 2025 - AI Alignment Track

点击查看摘要

[NLP-142] Reducing Large Language Model Safety Risks in Womens Health using Semantic Entropy

链接: https://arxiv.org/abs/2503.00269
作者: Jahan C. Penny-Dimri,Magdalena Bachmann,William R. Cooke,Sam Mathewlynn,Samuel Dockree,John Tolladay,Jannik Kossen,Lin Li,Yarin Gal,Gabriel Davis Jones
机构: unknown
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computers and Society (cs.CY)
备注: 15 pages, 6 tables

点击查看摘要

[NLP-143] Decoupling Content and Expression: Two-Dimensional Detection of AI-Generated Text

链接: https://arxiv.org/abs/2503.00258
作者: Guangsheng Bao,Lihua Rong,Yanbin Zhao,Qiji Zhou,Yue Zhang
机构: Zhejiang University (浙江大学); School of Engineering, Westlake University (西湖大学工学院); Zhejiang University of Technology (浙江工业大学); Shanghai Polytechnic University (上海第二工业大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
备注: 8 pages, 8 tables, 8 figures

点击查看摘要

[NLP-144] CoSMoEs: Compact Sparse Mixture of Experts

链接: https://arxiv.org/abs/2503.00245
作者: Patrick Huber,Akshat Shrivastava,Ernie Chang,Chinnadhurai Sankar,Ahmed Aly,Adithya Sagar
机构: 未知
类目: Machine Learning (cs.LG); Computation and Language (cs.CL)
备注: 11 pages, 8 figures

点击查看摘要

[NLP-145] Jawaher: A Multidialectal Dataset of Arabic Proverbs for LLM Benchmarking

链接: https://arxiv.org/abs/2503.00231
作者: Samar M. Magdy,Sang Yun Kwon,Fakhraddin Alwajih,Safaa Abdelfadil,Shady Shehata,Muhammad Abdul-Mageed
机构: The University of British Columbia (不列颠哥伦比亚大学); MBZUAI (穆罕默德 bin扎耶德人工智能大学); Invertible AI (可逆AI)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: Project GitHub page is accessible at: this https URL

点击查看摘要

[NLP-146] À la recherche du sens perdu: your favourite LLM might have more to say than you can understand

链接: https://arxiv.org/abs/2503.00224
作者: K. O. T. Erziev
机构: 未知
类目: Computation and Language (cs.CL)
备注: 22 pages

点击查看摘要

[NLP-147] Autoencoder-Based Framework to Capture Vocabulary Quality in NLP

链接: https://arxiv.org/abs/2503.00209
作者: Vu Minh Hoang Dang,Rakesh M. Verma
机构: 未知
类目: Computation and Language (cs.CL)
备注: Extended version of “Vocabulary Quality in NLP Datasets: An Autoencoder-Based Framework Across Domains and Languages” in IDA 2025

点击查看摘要

[NLP-148] Llamarine: Open-source Maritime Industry-specific Large Language Model

链接: https://arxiv.org/abs/2503.00203
作者: William Nguyen,An Phan,Konobu Kimura,Hitoshi Maeno,Mika Tanaka,Quynh Le,William Poucher,Christopher Nguyen
机构: 未知
类目: Computation and Language (cs.CL)
备注: Work in progress

点击查看摘要

[NLP-149] Zero-Shot and Efficient Clarification Need Prediction in Conversational Search

链接: https://arxiv.org/abs/2503.00179
作者: Lili Lu,Chuan Meng,Federico Ravenda,Mohammad Aliannejadi,Fabio Crestani
机构: 未知
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-150] A Survey of Uncertainty Estimation Methods on Large Language Models

链接: https://arxiv.org/abs/2503.00172
作者: Zhiqiu Xia,Jinxuan Xu,Yuqian Zhang,Hang Liu
机构: Rutgers University (罗格斯大学)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-151] PreMind: Multi-Agent Video Understanding for Advanced Indexing of Presentation-style Videos

链接: https://arxiv.org/abs/2503.00162
作者: Kangda Wei,Zhengyu Zhou,Bingqing Wang,Jun Araki,Lukas Lange,Ruihong Huang,Zhe Feng
机构: Bosch Research North America (博世北美研究院); Bosch Center for Artificial Intelligence (BCAI) (博世人工智能中心); Department of Computer Science and Engineering, Texas A&M University (德克萨斯农工大学计算机科学与工程系)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA)
备注:

点击查看摘要

[NLP-152] Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLM s

链接: https://arxiv.org/abs/2503.00151
作者: Fakhraddin Alwajih,Abdellah El Mekki,Samar Mohamed Magdy,Abdelrahim A. Elmadany,Omer Nacar,El Moatez Billah Nagoudi,Reem Abdel-Salam,Hanin Atwany,Youssef Nafea,Abdulfattah Mohammed Yahya,Rahaf Alhamouri,Hamzah A. Alsayadi,Hiba Zayed,Sara Shatnawi,Serry Sibaee,Yasir Ech-Chammakhy,Walid Al-Dhabyani,Marwa Mohamed Ali,Imen Jarraya,Ahmed Oumar El-Shangiti,Aisha Alraeesi,Mohammed Anwar Al-Ghrawi,Abdulrahman S. Al-Batati,Elgizouli Mohamed,Noha Taha Elgindi,Muhammed Saeed,Houdaifa Atou,Issam Ait Yahia,Abdelhak Bouayad,Mohammed Machrouh,Amal Makouar,Dania Alkawi,Mukhtar Mohamed,Safaa Taher Abdelfadil,Amine Ziad Ounnoughene,Rouabhia Anfel,Rwaa Assi,Ahmed Sorkatti,Mohamedou Cheikh Tourad,Anis Koubaa,Ismail Berrada,Mustafa Jarrar,Shady Shehata,Muhammad Abdul-Mageed
机构: The University of British Columbia; MBZUAI; Invertible AI; Birzeit University; Prince Sultan University; UM6P; Cairo University; Ain Shams University; Damascus University; University of Khartoum; Menoufiya University; University of Nouakchott; National Polytechnic School of Algiers; Full Sail University; University of British Columbia; University of British Columbia; University of British Columbia; University of British Columbia; University of British Columbia; University of British Columbia
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: More information about our dataset is available at our project page: this https URL

点击查看摘要

[NLP-153] SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models

链接: https://arxiv.org/abs/2503.00137
作者: Grigor Nalbandyan,Rima Shahbazyan,Evelina Bakhturina
机构: NVIDIA
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-154] Personalized Causal Graph Reasoning for LLM s: A Case Study on Dietary Recommendations

链接: https://arxiv.org/abs/2503.00134
作者: Zhongqi Yang,Amir Rahmani
机构: Department of Computer Science (计算机科学系), University of California, Irvine (加州大学欧文分校); School of Nursing (护理学院), University of California, Irvine (加州大学欧文分校)
类目: Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-155] AnnoCaseLaw: A Richly-Annotated Dataset For Benchmarking Explainable Legal Judgment Prediction

链接: https://arxiv.org/abs/2503.00128
作者: Magnus Sesodia,Alina Petrova,John Armour,Thomas Lukasiewicz,Oana-Maria Camburu,Puneet K. Dokania,Philip Torr,Christian Schroeder de Witt
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-156] Evaluation of LLM s-based Hidden States as Author Representations for Psychological Human-Centered NLP Tasks NAACL2025

链接: https://arxiv.org/abs/2503.00124
作者: Nikita Soni,Pranav Chitale,Khushboo Singh,Niranjan Balasubramanian,H. Andrew Schwartz
机构: Stony Brook University (石溪大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
备注: To appear in Findings of NAACL 2025

点击查看摘要

[NLP-157] InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation

链接: https://arxiv.org/abs/2503.00084
作者: Chong Zhang,Yukun Ma,Qian Chen,Wen Wang,Shengkui Zhao,Zexu Pan,Hao Wang,Chongjia Ni,Trung Hieu Nguyen,Kun Zhou,Yidi Jiang,Chaohong Tan,Zhifu Gao,Zhihao Du,Bin Ma
机构: Tongyi Lab, Alibaba Group (通义实验室，阿里巴巴集团)
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Audio and Speech Processing (eess.AS)
备注: Work in progress. Correspondence regarding this technical report should be directed to { this http URL , this http URL }@alibaba this http URL . Online demo available on this https URL and this https URL

点击查看摘要

[NLP-158] I see what you mean: Co-Speech Gestures for Reference Resolution in Multimodal Dialogue

链接: https://arxiv.org/abs/2503.00071
作者: Esam Ghaleb,Bulat Khaertdinov,Aslı Özyürek,Raquel Fernández
机构: Multimodal Language Department, Max Planck Institute for Psycholinguistics (马克斯·普朗克心理语言学研究所); Donders Institute for Brain, Cognition and Behaviour, Radboud University (拉德堡德大学); Department of Advanced Computing Sciences, Maastricht University (马斯特里赫特大学); Institute for Logic, Language and Computation, University of Amsterdam (阿姆斯特丹大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL); Multimedia (cs.MM)
备注:

点击查看摘要

[NLP-159] Societal Alignment Frameworks Can Improve LLM Alignment

链接: https://arxiv.org/abs/2503.00069
作者: Karolina Stańczak,Nicholas Meade,Mehar Bhatia,Hattie Zhou,Konstantin Böttinger,Jeremy Barnes,Jason Stanley,Jessica Montgomery,Richard Zemel,Nicolas Papernot,Nicolas Chapados,Denis Therien,Timothy P. Lillicrap,Ana Marasović,Sylvie Delacroix,Gillian K. Hadfield,Siva Reddy
机构: 未知
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-160] Improved YOLOv12 with LLM -Generated Synthetic Data for Enhanced Apple Detection and Benchmarking Against YOLOv11 and YOLOv10

链接: https://arxiv.org/abs/2503.00057
作者: Ranjan Sapkota,Manoj Karkee
机构: Cornell University (康奈尔大学); Cornell University (康奈尔大学); Washington State University (华盛顿州立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
备注: 10 pages, 5 Figures, 2 Tables

点击查看摘要

[NLP-161] VOILA: Evaluation of MLLM s For Perceptual Understanding and Analogical Reasoning ICLR2025

链接: https://arxiv.org/abs/2503.00043
作者: Nilay Yilmaz,Maitreya Patel,Yiran Lawrence Luo,Tejas Gokhale,Chitta Baral,Suren Jayasuriya,Yezhou Yang
机构: Arizona State University (亚利桑那州立大学); University of Maryland, Baltimore County (马里兰大学巴尔的摩郡分校)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: Accepted at ICLR 2025. Code and data: this https URL

点击查看摘要

[NLP-162] from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors

链接: https://arxiv.org/abs/2503.00038
作者: Yu Yan,Sheng Sun,Zenghao Duan,Teli Liu,Min Liu,Zhiyi Yin,Qi Li,Jiangyu Lei
机构: Institute of Computing Technology, Chinese Academy of Sciences (中国科学院计算技术研究所), University of Chinese Academy of Sciences (中国科学院大学); People’s Public Security University of China (中国人民公安大学); Tsinghua University (清华大学); Zhongguancun Laboratory (中关村实验室)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
备注: arXiv admin note: substantial text overlap with arXiv:2412.12145

点击查看摘要

[NLP-163] Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs

链接: https://arxiv.org/abs/2503.00037
作者: Wei Zhao,Zhe Li,Yige Li,Jun Sun
机构: Singapore Management University (新加坡管理大学)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[NLP-164] Constraining Sequential Model Editing with Editing Anchor Compression

链接: https://arxiv.org/abs/2503.00035
作者: Hao-Xiang Xu,Jun-Yu Ma,Zhen-Hua Ling,Ningyu Zhang,Jia-Chen Gu
机构: National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China (中国科学技术大学), Hefei, China; Zhejiang University (浙江大学); 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)
备注:

点击查看摘要

[NLP-165] Detecting LLM -Generated Korean Text through Linguistic Feature Analysis

链接: https://arxiv.org/abs/2503.00032
作者: Shinwoo Park,Shubin Kim,Do-Kyung Kim,Yo-Sub Han
机构: Yonsei University (延世大学)(首尔, 大韩民国)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-166] Efficient Test-Time Scaling via Self-Calibration

链接: https://arxiv.org/abs/2503.00031
作者: Chengsong Huang,Langlin Huang,Jixuan Leng,Jiacheng Liu,Jiaxin Huang
机构: Washington Univeristy in St. Louis (圣路易斯华盛顿大学); Carnegie Mellon University (卡内基梅隆大学); 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-167] Evaluating Large Language Models on the Spanish Medical Intern Resident (MIR) Examination 2024/2025:A Comparative Analysis of Clinical Reasoning and Knowledge Application

链接: https://arxiv.org/abs/2503.00025
作者: Carlos Luengo Vera,Ignacio Ferro Picon,M. Teresa del Val Nunez,Jose Andres Gomez Gandia,Antonio de Lucas Ancillo,Victor Ramos Arroyo,Carlos Milan Figueredo
机构: 未知
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注: 26 pages, 1 table, 7 figures

点击查看摘要

[NLP-168] Do Emotions Really Affect Argument Convincingness? A Dynamic Approach with LLM -based Manipulation Checks

链接: https://arxiv.org/abs/2503.00024
作者: Yanran Chen,Steffen Eger
机构: NLLG, University of Technology Nuremberg (UTN)
类目: Computation and Language (cs.CL)
备注: Initial submit

点击查看摘要

[NLP-169] KVCrush: Key value cache size-reduction using similarity in head-behaviour

链接: https://arxiv.org/abs/2503.00022
作者: Gopi Krishna Jha,Sameh Gobriel,Liubov Talamanova,Alexander Kozlov,Nilesh Jain
机构: Intel Corporation
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注:

点击查看摘要

[NLP-170] A Systematic Review of Open Datasets Used in Text-to-Image (T2I) Gen AI Model Safety

链接: https://arxiv.org/abs/2503.00020
作者: Rakeen Rouf,Trupti Bavalatti,Osama Ahmed,Dhaval Potdar,Faraz Jawed
机构: Meta (Meta); Duke University (杜克大学); University of North Carolina at Charlotte (北卡罗来纳大学夏洛特分校)
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted for publication in IEEE Access, DOI: https://doi.org/10.1109/ACCESS.2025.3539933

点击查看摘要

[NLP-171] Eeyore: Realistic Depression Simulation via Supervised and Preference Optimization

链接: https://arxiv.org/abs/2503.00018
作者: Siyang Liu,Bianca Brie,Wenda Li,Laura Biester,Andrew Lee,James Pennebaker,Rada Mihalcea
机构: The LIT Group, Department of Computer Science and Engineering, University of Michigan (密歇根大学), Ann Arbor; Middlebury College (米德尔伯里学院); Harvard University (哈佛大学); Department of Psychology, University of Texas at Austin (德克萨斯大学奥斯汀分校), Austin
类目: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[NLP-172] DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking

链接: https://arxiv.org/abs/2502.20730
作者: Zhuoqun Li,Haiyang Yu,Xuanang Chen,Hongyu Lin,Yaojie Lu,Fei Huang,Xianpei Han,Yongbin Li,Le Sun
机构: Chinese Information Processing Laboratory (中国信息处理实验室), Institute of Software, Chinese Academy of Sciences (中国科学院软件研究所); University of Chinese Academy of Sciences (中国科学院大学); Tongyi Lab (通义实验室)
类目: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注:

点击查看摘要

[NLP-173] Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents

链接: https://arxiv.org/abs/2502.18509
作者: Ivoline Ngong,Swanand Kadhe,Hao Wang,Keerthiram Murugesan,Justin D. Weisz,Amit Dhurandhar,Karthikeyan Natesan Ramamurthy
机构: IBM Research (IBM研究); University of Vermont (佛蒙特大学)
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
备注: 22 pages, 2 figures

点击查看摘要

[NLP-174] Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation ICLR2025

链接: https://arxiv.org/abs/2410.20724
作者: Mufei Li,Siqi Miao,Pan Li
机构: Georgia Institute of Technology (乔治亚理工学院)
类目: Computation and Language (cs.CL); Information Retrieval (cs.IR); Machine Learning (cs.LG)
备注: Accepted by ICLR 2025; Code available at this https URL

点击查看摘要

[NLP-175] UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation ICLR2025

链接: https://arxiv.org/abs/2503.00733
作者: Alexander H. Liu,Sang-gil Lee,Chao-Han Huck Yang,Yuan Gong,Yu-Chiang Frank Wang,James R. Glass,Rafael Valle,Bryan Catanzaro
机构: MIT CSAIL (麻省理工学院计算机科学与人工智能实验室); NVIDIA (英伟达)
类目: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)
备注: ICLR 2025; demo page at this https URL

点击查看摘要

[NLP-176] Causal Inference on Outcomes Learned from Text

链接: https://arxiv.org/abs/2503.00725
作者: Iman Modarressi,Jann Spiess,Amar Venugopal
机构: 未知
类目: Econometrics (econ.EM); Computation and Language (cs.CL); Machine Learning (cs.LG); Methodology (stat.ME)
备注:

点击查看摘要

[NLP-177] Statistical Mechanics of Semantic Compression

链接: https://arxiv.org/abs/2503.00612
作者: Tankut Can
机构: Department of Physics, Emory University (埃默里大学)
类目: Disordered Systems and Neural Networks (cond-mat.dis-nn); Statistical Mechanics (cond-mat.stat-mech); Computation and Language (cs.CL); Neurons and Cognition (q-bio.NC)
备注: 20 pages (including appendix), 3 figures

点击查看摘要

[NLP-178] LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement

链接: https://arxiv.org/abs/2503.00493
作者: Boyi Kang,Xinfa Zhu,Zihan Zhang,Zhen Ye,Mingshuai Liu,Ziqian Wang,Yike Zhu,Guobin Ma,Jun Chen,Longshuai Xiao,Chao Weng,Wei Xue,Lei Xie
机构: Northwestern Polytechnical University (西北工业大学); The Hong Kong University of Science and Technology (香港科技大学); Huawei Technologies Co., Ltd. (华为技术有限公司)
类目: Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Sound (cs.SD)
备注: 13 pages, 2 figures, 8 tables

点击查看摘要

计算机视觉

[CV-0] Denoising Functional Maps: Diffusion Models for Shape Correspondence CVPR2025

链接: https://arxiv.org/abs/2503.01845
作者: Aleksei Zhuravlev,Zorah Lähner,Vladislav Golyanik
机构: University of Bonn (波恩大学); MPI for Informatics, SIC (马克斯·普朗克计算机科学研究所)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at CVPR 2025; Project page: this https URL

点击查看摘要

[CV-1] Multi-Stage Manipulation with Demonstration-Augmented Reward Policy and World Model Learning

链接: https://arxiv.org/abs/2503.01837
作者: Adrià López Escoriza,Nicklas Hansen,Stone Tao,Tongzhou Mu,Hao Su
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: Project page can be found at this https URL

点击查看摘要

[CV-2] Primus: Enforcing Attention Usage for 3D Medical Image Segmentation

链接: https://arxiv.org/abs/2503.01835
作者: Tassilo Wald,Saikat Roy,Fabian Isensee,Constantin Ulrich,Sebastian Ziegler,Dasha Trofimova,Raphael Stock,Michael Baumgartner,Gregor Köhler,Klaus Maier-Hein
机构: Division of Medical Image Computing, German Cancer Research Center (DKFZ)(德国癌症研究中心), Heidelberg, Germany ; Helmholtz Imaging, DKFZ(德国癌症研究中心); Faculty of Mathematics and Computer Science, University of Heidelberg(海德堡大学); National Center for Tumor Diseases (NCT)(国家肿瘤疾病中心), Heidelberg; Pattern Analysis and Learning Group, Department of Radiation Oncology
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Preprint

点击查看摘要

[CV-3] OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-Adjustment

链接: https://arxiv.org/abs/2503.01794
作者: Junhyun Park,Chanyu Moon,Donghwan Lee,Kyungsu Kim,Minho Hwang
机构: Department of Robotics and Mechatronics Engineering, DGIST, Republic of Korea (DGIST, 大邱科技大学); Department of Electrical Engineering and Computer Science, DGIST, Republic of Korea (DGIST, 大邱科技大学); Seoul National University, Republic of Korea (首尔国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 3 figures, and 5 tables

点击查看摘要

[CV-4] Visual-RFT: Visual Reinforcement Fine-Tuning

链接: https://arxiv.org/abs/2503.01785
作者: Ziyu Liu,Zeyi Sun,Yuhang Zang,Xiaoyi Dong,Yuhang Cao,Haodong Duan,Dahua Lin,Jiaqi Wang
机构: Shanghai Jiaotong University (上海交通大学); Shanghai Artificial Intelligence Laboratory (上海人工智能实验室); The Chinese University of Hong Kong (香港中文大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: project page: this https URL

点击查看摘要

[CV-5] vS-Graphs: Integrating Visual SLAM and Situational Graphs through Multi-level Scene Understanding

链接: https://arxiv.org/abs/2503.01783
作者: Ali Tourani,Saad Ejaz,Hriday Bavle,David Morilla-Cabello,Jose Luis Sanchez-Lopez,Holger Voos
机构: Automation and Robotics Research Group, Interdisciplinary Centre for Security, Reliability, and Trust (SnT)(跨学科安全、可靠性和信任中心), University of Luxembourg(卢森堡大学), Luxembourg(卢森堡); Instituto de Investigación en Ingeniería de Aragón (I3A)(阿拉贡工程研究研究所), Universidad de Zaragoza(萨拉戈萨大学), Spain(西班牙)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注: 13 pages, 8 figures, 2 tables

点击查看摘要

[CV-6] Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation

链接: https://arxiv.org/abs/2503.01776
作者: Tiansheng Wen,Yifei Wang,Zequn Zeng,Zhong Peng,Yudi Su,Xinyang Liu,Bo Chen,Hongwei Liu,Stefanie Jegelka,Chenyu You
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Information Retrieval (cs.IR)
备注: A novel sparse coding framework designed for learning adaptive representation

点击查看摘要

[CV-7] Difix3D: Improving 3D Reconstructions with Single-Step Diffusion Models CVPR2025

链接: https://arxiv.org/abs/2503.01774
作者: Jay Zhangjie Wu,Yuxuan Zhang,Haithem Turki,Xuanchi Ren,Jun Gao,Mike Zheng Shou,Sanja Fidler,Zan Gojcic,Huan Ling
机构: NVIDIA(英伟达); National University of Singapore(新加坡国立大学); University of Toronto(多伦多大学); Vector Institute(向量研究所)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: CVPR 2025

点击查看摘要

[CV-8] SHADE-AD: An LLM -Based Framework for Synthesizing Activity Data of Alzheimers Patients

链接: https://arxiv.org/abs/2503.01768
作者: Heming Fu,Hongkai Chen,Shan Lin,Guoliang Xing
机构: Stony Brook University (石溪大学); The Chinese University of Hong Kong (香港中文大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: 7 pages, 6 figures, ACM SenSys’25

点击查看摘要

[CV-9] Enhancing Multi-hop Reasoning in Vision-Language Models via Self-Distillation with Multi-Prompt Ensembling

链接: https://arxiv.org/abs/2503.01754
作者: Guande Wu,Huan Song,Yawei Wang,Qiaojing Yan,Yijun Tian,Lin Lee Cheong,Panpan Xu
机构: New York University (纽约大学); Amazon (亚马逊)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-10] VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation

链接: https://arxiv.org/abs/2503.01739
作者: Wenhao Wang,Yi Yang
机构: University of Technology Sydney (悉尼科技大学); Zhejiang University (浙江大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-11] DISCOVER: Data-driven Identification of Sub-activities via Clustering and Visualization for Enhanced Activity Recognition in Smart Homes

链接: https://arxiv.org/abs/2503.01733
作者: Alexander Karpekov,Sonia Chernova,Thomas Plötz
机构: Georgia Institute of Technology(乔治亚理工学院) Atlanta(亚特兰大) Georgia(乔治亚州) USA(美国)
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: v1: Initial submission. Under review at IMWUT

点击查看摘要

[CV-12] HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization CVPR2025

链接: https://arxiv.org/abs/2503.01725
作者: Zitang Zhou,Ke Mei,Yu Lu,Tianyi Wang,Fengyun Rao
机构: WeChat, Tencent Inc. (微信，腾讯公司); Beijing University of Posts and Telecommunications (北京邮电大学); Zhejiang University (浙江大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at CVPR 2025. Project page: this https URL

点击查看摘要

[CV-13] KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation CVPR2025

链接: https://arxiv.org/abs/2503.01715
作者: Antoni Bigata,Michał Stypułkowski,Rodrigo Mira,Stella Bounareli,Konstantinos Vougioukas,Zoe Landgraf,Nikita Drobyshev,Maciej Zieba,Stavros Petridis,Maja Pantic
机构: Imperial College London, UK (帝国理工学院, 英国); University of Wrocław, Poland (弗罗茨瓦夫大学, 波兰); Technical University of Wroclaw, Poland (弗罗茨瓦夫科技大学, 波兰)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: CVPR 2025

点击查看摘要

[CV-14] Open-Set Recognition of Novel Species in Biodiversity Monitoring

链接: https://arxiv.org/abs/2503.01691
作者: Yuyan Chen,Nico Lang,B. Christian Schmidt,Aditya Jain,Yves Basset,Sara Beery,Maxim Larrivée,David Rolnick
机构: McGill University (麦吉尔大学); Mila - Quebec AI Institute (魁北克人工智能研究所); University of Copenhagen (哥本哈根大学); Agriculture and Agri-food Canada (加拿大农业与农业食品部); Massachusetts Institute of Technology (麻省理工学院); Smithsonian Tropical Research Institute, Biology Center, Czech Academy of Sciences & University of Panama (史密森尼热带研究中心，捷克科学院生物中心&巴拿马大学); Montreal Insectarium (蒙特利尔昆虫馆); David Rolnick (未提供机构信息)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-15] oLo: A Two-Stage Training-Free Layout-To-Image Generation Framework For High-Overlap Layouts

链接: https://arxiv.org/abs/2503.01667
作者: Linhao Huang,Jing Yu
机构: Beijing University of Technology (北京工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-16] MUSt3R: Multi-view Network for Stereo 3D Reconstruction CVPR2025

链接: https://arxiv.org/abs/2503.01661
作者: Yohann Cabon,Lucas Stoffl,Leonid Antsfeld,Gabriela Csurka,Boris Chidlovskii,Jerome Revaud,Vincent Leroy
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at CVPR 2025

点击查看摘要

[CV-17] Enhancing Object Detection Accuracy in Underwater Sonar Images through Deep Learning-based Denoising

链接: https://arxiv.org/abs/2503.01655
作者: Ziyu Wang(1),Tao Xue(1),Yanbin Wang(1),Jingyuan Li(1),Haibin Zhang(1),Zhiqiang Xu(2),Gaofei Xu(3) ((1) Xidian University, (2) Jiangxi University of Science and Technology, (3) Institute of Deep-sea Science and Engineering)
机构: Xidian University (西安电子科技大学); Jiangxi University of Science and Technology (江西理工大学); Institute of Deep-sea Science and Engineering (深海科学与工程研究所)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-18] A Shared Encoder Approach to Multimodal Representation Learning

链接: https://arxiv.org/abs/2503.01654
作者: Shuvendu Roy,Franklin Ogidi,Ali Etemad,Elham Dolatabadi,Arash Afkanpour
机构: Vector Institute (向量研究所); Queen’s University (女王大学); York University (约克大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-19] Distilled Prompt Learning for Incomplete Multimodal Survival Prediction CVPR2025

链接: https://arxiv.org/abs/2503.01653
作者: Yingxue Xu,Fengtao Zhou,Chenyu Zhao,Yihui Wang,Can Yang,Hao Chen
机构: The Hong Kong University of Science and Technology (香港科技大学)
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR2025

点击查看摘要

[CV-20] OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding

链接: https://arxiv.org/abs/2503.01646
作者: Dianyi Yang,Yu Gao,Xihan Wang,Yufeng Yue,Yi Yang,Mengyin Fu
机构: School of Automation, Beijing Institute of Technology (北京理工大学自动化学院); National Key Lab of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology (北京理工大学自主智能无人系统全国重点实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-21] DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models CVPR2025

链接: https://arxiv.org/abs/2503.01645
作者: Zhendong Wang,Jianmin Bao,Shuyang Gu,Dong Chen,Wengang Zhou,Houqiang Li
机构: CAS Key Laboratory of GIPAS, EEIS Department, University of Science and Technology of China (中国科学技术大学); Microsoft Research Asia (微软亚洲研究院); 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所)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025

点击查看摘要

[CV-22] SparseMamba-PCL: Scribble-Supervised Medical Image Segmentation via SAM-Guided Progressive Collaborative Learning

链接: https://arxiv.org/abs/2503.01633
作者: Luyi Qiu,Tristan Till,Xiaobao Guo,Adams Wai-Kin Kong
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-23] A General Purpose Spectral Foundational Model for Both Proximal and Remote Sensing Spectral Imaging

链接: https://arxiv.org/abs/2503.01628
作者: William Michael Laprade,Jesper Cairo Westergaard,Svend Christensen,Mads Nielsen,Anders Bjorholm Dahl
机构: Department of Applied Mathematics and Computer Science, Technical University of Denmark (丹麦技术大学应用数学与计算机科学系); Department of Computer Science, University of Copenhagen (哥本哈根大学计算机科学系); Department of Plant and Environmental Sciences, University of Copenhagen (哥本哈根大学植物与环境科学系)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-24] Robust Palm-Vein Recognition Using the MMD Filter: Improving SIFT-Based Feature Matching

链接: https://arxiv.org/abs/2503.01612
作者: Kaveen Perera,Fouad Khelifi,Ammar Belatreche
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Our previous work, presented at the 2022 International Conference on Digital Image Computing: Techniques and Applications (DICTA) and published in IEEE Xplore. The code for the MMD filter is available at this https URL under Mozilla Public License Version 2.0

点击查看摘要

[CV-25] Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior

链接: https://arxiv.org/abs/2503.01610
作者: Chen Guo,Junxuan Li,Yash Kant,Yaser Sheikh,Shunsuke Saito,Chen Cao
机构: Meta; ETH Zürich; University of Toronto
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-26] A Leaf-Level Dataset for Soybean-Cotton Detection and Segmentation

链接: https://arxiv.org/abs/2503.01605
作者: Thiago H. Segreto,Juliano Negri,Paulo H. Polegato,João Manoel Herrera Pinheiro,Ricardo Godoy,Marcelo Becker
机构: Mechanical Engineering Department, São Carlos School of Engineering, University of São Paulo (圣保罗大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-27] riple-Stream Deep Feature Selection with Metaheuristic Optimization and Machine Learning for Multi-Stage Hypertensive Retinopathy Diagnosis

链接: https://arxiv.org/abs/2503.01603
作者: Suleyman Burcin Suyun,Mustafa Yurdakul,Sakir Tasdemir,Serkan Bilic
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-28] Evaluating Stenosis Detection with Grounding DINO YOLO and DINO-DETR

链接: https://arxiv.org/abs/2503.01601
作者: Muhammad Musab Ansari
机构: FAU Erlangen-Nürnberg (埃尔朗根-纽伦堡弗里德里希·亚历山大大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-29] STAR: Stability-Inducing Weight Perturbation for Continual Learning

链接: https://arxiv.org/abs/2503.01595
作者: Masih Eskandar,Tooba Imtiaz,Davin Hill,Zifeng Wang,Jennifer Dy
机构: Department of Electrical & Computer Engineering, Northeastern University (东北大学电气与计算机工程学院); Google Cloud AI Research (谷歌云人工智能研究院)
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-30] Category-level Meta-learned NeRF Priors for Efficient Object Mapping

链接: https://arxiv.org/abs/2503.01582
作者: Saad Ejaz,Hriday Bavle,Laura Ribeiro,Holger Voos,Jose Luis Sanchez-Lopez
机构: Automation and Robotics Research Group, Interdisciplinary Centre for Security, Reliability, and Trust (SnT)(安全、可靠性和信任跨学科中心), University of Luxembourg(卢森堡大学), Luxembourg(卢森堡); Faculty of Science, Technology, and Medicine(科学、技术和医学学院), University of Luxembourg(卢森堡大学), Luxembourg(卢森堡)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-31] MRI super-resolution reconstruction using efficient diffusion probabilistic model with residual shifting

链接: https://arxiv.org/abs/2503.01576
作者: Mojtaba Safari,Shansong Wang,Zach Eidex,Qiang Li,Erik H. Middlebrooks,David S. Yu,Xiaofeng Yang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Medical Physics (physics.med-ph)
备注:

点击查看摘要

[CV-32] Meta Learning-Driven Iterative Refinement for Robust Anomaly Detection in Industrial Inspection ECCV2024

链接: https://arxiv.org/abs/2503.01569
作者: Muhammad Aqeel,Shakiba Sharifi,Marco Cristani,Francesco Setti
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Accepted in the VISION workshop at ECCV 2024

点击查看摘要

[CV-33] AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning

链接: https://arxiv.org/abs/2503.01565
作者: Yuheng Xu,Shijie Yang,Xin Liu,Jie Liu,Jie Tang,Gangshan Wu
机构: State Key Laboratory for Novel Software Technology, Nanjing University (南京大学), China
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-34] AI-Driven Relocation Tracking in Dynamic Kitchen Environments

链接: https://arxiv.org/abs/2503.01547
作者: Arash Nasr Esfahani,Hamed Hosseini,Mehdi Tale Masouleh,Ahmad Kalhor,Hedieh Sajedi
机构: Human and Robot Interaction Lab, School of Electrical and Computer Engineering, University of Tehran ( Tehran, Iran ); School of Mathematics, Statistics, and Computer Science, University of Tehran ( Tehran, Iran )
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Conference: 2024 14th International Conference on Computer and Knowledge Engineering (ICCKE) Publisher: IEEE

点击查看摘要

[CV-35] Diversity Covariance-Aware Prompt Learning for Vision-Language Models

链接: https://arxiv.org/abs/2503.01531
作者: Songlin Dong,Zhengdong Zhou,Chenhao Ding,Xinyuan Gao,Alex Kot,Yihong Gong
机构: School of Software Engineering, Xi’an Jiaotong University (西安交通大学软件学院); College of Artificial Intelligence, Xi’an Jiaotong University (西安交通大学人工智能学院); 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-36] An Approach for Air Drawing Using Background Subtraction and Contour Extraction

链接: https://arxiv.org/abs/2503.01497
作者: Ramkrishna Acharya
机构: Friedrich-Alexander-Universität Erlangen-Nürnberg (弗里德里希-亚历山大-埃尔兰根-纽伦堡大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-37] MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism CVPR2025

链接: https://arxiv.org/abs/2503.01463
作者: Zhixiong Nan,Xianghong Li,Jifeng Dai,Tao Xiang
机构: College of Computer Science, Chongqing University (重庆大学); Department of Electronic Engineering, Tsinghua University (清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 14 pages,9 figures,accepted to CVPR2025

点击查看摘要

[CV-38] Generative Human Geometry Distribution

链接: https://arxiv.org/abs/2503.01448
作者: Xiangjun Tang,Biao Zhang,Peter Wonka
机构: King Abdullah University of Science and Technology (国王阿卜杜拉科学技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-39] Fall Detection from Indoor Videos using MediaPipe and Handcrafted Feature

链接: https://arxiv.org/abs/2503.01436
作者: Fatima Ahmed,Parag Biswas,Abdur Rashid,Md. Khaliluzzaman
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-40] DLF: Extreme Image Compression with Dual-generative Latent Fusion

链接: https://arxiv.org/abs/2503.01428
作者: Naifu Xue,Zhaoyang Jia,Jiahao Li,Bin Li,Yuan Zhang,Yan Lu
机构: Communication University of China (中国传媒大学); University of Science and Technology of China (中国科学技术大学); Microsoft Research Asia (微软亚洲研究院)
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-41] MeshPad: Interactive Sketch Conditioned Artistic-designed Mesh Generation and Editing

链接: https://arxiv.org/abs/2503.01425
作者: Haoxuan Li,Ziya Erkoc,Lei Li,Daniele Sirigatti,Vladyslav Rozov,Angela Dai,Matthias Nießner
机构: 未知
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL Video: this https URL

点击查看摘要

[CV-42] Learning to Generate Long-term Future Narrations Describing Activities of Daily Living

链接: https://arxiv.org/abs/2503.01416
作者: Ramanathan Rajendiran,Debaditya Roy,Basura Fernando
机构: Centre for Frontier AI Research (前沿人工智能研究中心), Agency for Science, Technology and Research (ASTAR)(新加坡科学技术研究局), Singapore(新加坡); Institute of High Performance Computing (高性能计算研究所), Agency for Science, Technology and Research (ASTAR)(新加坡科学技术研究局), Singapore(新加坡); Centre for Frontier AI Research (前沿人工智能研究中心), Agency for Science, Technology and Research (A*STAR)(新加坡科学技术研究局), Singapore(新加坡)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-43] Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification

链接: https://arxiv.org/abs/2503.01407
作者: Gaozheng Pei,Shaojie Lyu,Gong Chen,Ke Ma,Qianqian Xu,Yingfei Sun,Qingming Huang
机构: UCAS; Tencent Corporate (腾讯); CAS (中国科学院); UCAS; ICT (中国科学院计算技术研究所); UCAS
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-44] Blind Augmentation: Calibration-free Camera Distortion Model Estimation for Real-time Mixed-reality Consistency

链接: https://arxiv.org/abs/2503.01387
作者: Siddhant Prakash,David R. Walton,Rafael K. dos Anjos,Anthony Steed,Tobias Ritschel
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR); Human-Computer Interaction (cs.HC)
备注: To appear in IEEE Transactions on Visualization and Computer Graphics (IEEEVR 2025). Project page can be found at this https URL

点击查看摘要

[CV-45] Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation

链接: https://arxiv.org/abs/2503.01370
作者: Jiantao Lin,Xin Yang,Meixi Chen,Yingjie Xu,Dongyu Yan,Leyi Wu,Xinli Xu,Lie XU,Shunsi Zhang,Ying-Cong Chen
机构: HKUST(GZ)(香港科技大学(广州)); HKUST(香港科技大学); Guangzhou Quwan Network Technology(广州趣玩网络技术有限公司)
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注: The first three authors contributed equally to this work

点击查看摘要

[CV-46] Spatial Transcriptomics Analysis of Spatially Dense Gene Expression Prediction

链接: https://arxiv.org/abs/2503.01347
作者: Ruikun Zhang,Yan Yang,Liyuan Pan
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-47] UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface

链接: https://arxiv.org/abs/2503.01342
作者: Hao Tang,Chenwei Xie,Haiyang Wang,Xiaoyi Bao,Tingyu Weng,Pandeng Li,Yun Zheng,Liwei Wang
机构: Center for Data Science, Peking University (北京大学数据科学中心); Alibaba Group (阿里巴巴集团); Institute of Automation, Chinese Academy of Sciences (中国科学院自动化研究所)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-48] Wavelet-Enhanced Desnowing: A Novel Single Image Restoration Approach for Traffic Surveillance under Adverse Weather Conditions

链接: https://arxiv.org/abs/2503.01339
作者: Zihan Shen,Yu Xuan,Qingyu Yang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-49] Composed Multi-modal Retrieval: A Survey of Approaches and Applications

链接: https://arxiv.org/abs/2503.01334
作者: Kun Zhang,Jingyu Li,Zhe Li,Jingjing Zhang
机构: Georgia Institute of Technology (乔治亚理工学院); Anonymous University (匿名大学)
类目: Information Retrieval (cs.IR); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-50] Group Relative Policy Optimization for Image Captioning

链接: https://arxiv.org/abs/2503.01333
作者: Xu Liang
机构: School of Software Engineering (软件工程学院), Xi’an Jiaotong University (西安交通大学), Xi’an, China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-51] CacheQuant: Comprehensively Accelerated Diffusion Models CVPR2025

链接: https://arxiv.org/abs/2503.01323
作者: Xuewen Liu,Zhikai Li,Qingyi Gu
机构: Institute of Automation, Chinese Academy of Sciences (自动化研究所，中国科学院); School of Artificial Intelligence, University of Chinese Academy of Sciences (人工智能学院，中国科学院大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: CVPR 2025

点击查看摘要

[CV-52] OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging

链接: https://arxiv.org/abs/2503.01309
作者: Yijie Tang,Jiazhao Zhang,Yuqing Lan,Yulan Guo,Dezun Dong,Chenyang Zhu,Kai Xu
机构: National University of Defense Technology (国防科技大学); CFCS, School of CS, Peking University (北京大学计算机学院中心实验室); 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-53] MINT: Multi-modal Chain of Thought in Unified Generative Models for Enhanced Image Generation

链接: https://arxiv.org/abs/2503.01298
作者: Yi Wang,Mushui Liu,Wanggui He,Longxiang Zhang,Ziwei Huang,Guanghao Zhang,Fangxun Shu,Zhong Tao,Dong She,Zhelun Yu,Haoyuan Li,Weilong Dai,Mingli Song,Jie Song,Hao Jiang
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-54] Fine-Grained Controllable Apparel Showcase Image Generation via Garment-Centric Outpainting

链接: https://arxiv.org/abs/2503.01294
作者: Rong Zhang,Jingnan Wang,Zhiwen Zuo,Jianfeng Dong,Wei Li,Chi Wang,Weiwei Xu,Xun Wang
机构: Zhejiang Gongshang University (浙江工商大学); Inceptio; Zhejiang University (浙江大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-55] PA-CLIP: Enhancing Zero-Shot Anomaly Detection through Pseudo-Anomaly Awareness

链接: https://arxiv.org/abs/2503.01292
作者: Yurui Pan,Lidong Wang,Yuchao Chen,Wenbing Zhu,Bo Peng,Mingmin Chi
机构: Fudan University (复旦大学); National University of Singapore (新加坡国立大学); Shanghai Ocean University (上海海洋大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages

点击查看摘要

[CV-56] SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance CVPR2025

链接: https://arxiv.org/abs/2503.01291
作者: Peishan Cong,Ziyi Wang,Yuexin Ma,Xiangyu Yue
机构: ShanghaiTech University (上海科技大学); The Chinese University of Hong Kong (香港中文大学); NSFC (国家自然科学基金委员会); Shanghai Frontiers Science Center of Human-centered Artificial Intelligence (ShangHAI) (上海前沿科学中心人类中心人工智能); MoE Key Laboratory of Intelligent Perception and Human-Machine Collaboration (KLIP-HuMaCo) (教育部智能感知与人机协作重点实验室); Shun Hing Institute of Advanced Engineering (SHIAE) (顺兴高等工程研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: accepted by CVPR 2025

点击查看摘要

[CV-57] Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual CVPR2025

链接: https://arxiv.org/abs/2503.01288
作者: Chong Wang,Lanqing Guo,Zixuan Fu,Siyuan Yang,Hao Cheng,Alex C. Kot,Bihan Wen
机构: Nanyang Technological University, Singapore (南洋理工大学，新加坡); The University of Texas at Austin, USA (德克萨斯大学奥斯汀分校，美国); Hebei University of Technology, China (河北工业大学，中国)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to CVPR 2025

点击查看摘要

[CV-58] Soybean Disease Detection via Interpretable Hybrid CNN-GNN: Integrating MobileNetV2 and GraphSAGE with Cross-Modal Attention

链接: https://arxiv.org/abs/2503.01284
作者: Md Abrar Jahin,Soudeep Shahriar,M. F. Mridha,Nilanjan Dey
机构: Okinawa Institute of Science and Technology Graduate University (冲绳科学技术研究生院大学); Department of Computer Science, American International University-Bangladesh (美国国际大学计算机科学系); Department of Computer Science & Engineering, Techno International New Town (Techno国际新城计算机科学与工程系)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-59] Object-Aware Video Matting with Cross-Frame Guidance

链接: https://arxiv.org/abs/2503.01262
作者: Huayu Zhang,Dongyue Wu,Yuanjie Shao,Nong Sang,Changxin Gao
机构: National Key Laboratory of Multispectral Information Intelligent Processing Technology (多光谱信息智能处理技术国家重点实验室), School of Artificial Intelligence and Automation (人工智能与自动化学院), Huazhong University of Science and Technology (华中科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-60] owards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text CVPR2025

链接: https://arxiv.org/abs/2503.01261
作者: Guotao Liang,Baoquan Zhang,Zhiyuan Wen,Junteng Zhao,Yunming Ye,Kola Ye,Yao He
机构: Harbin Institute of Technology (哈尔滨工业大学); Peng Cheng Laboratory (鹏城实验室); SiFar Company (思法公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025

点击查看摘要

[CV-61] SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion CVPR2025

链接: https://arxiv.org/abs/2503.01257
作者: Xuan Zhu,Jijun Xiang,Xianqi Wang,Longliang Liu,Yu Wang,Hong Zhang,Fei Guo,Xin Yang
机构: Huazhong University of Science and Technology (华中科技大学); Honor Device Co., Ltd (荣耀终端有限公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025

点击查看摘要

[CV-62] Convex Hull-based Algebraic Constraint for Visual Quadric SLAM

链接: https://arxiv.org/abs/2503.01254
作者: Xiaolong Yu,Junqiao Zhao,Shuangfu Song,Zhongyang Zhu,Zihan Yuan,Chen Ye,Tiantian Feng
机构: School of Computer Science and Technology, Tongji University (同济大学), Shanghai, China (同济大学, 上海, 中国); MOE Key Lab of Embedded System and Service Computing, Tongji University (同济大学), Shanghai, China (同济大学, 上海, 中国); Institute of Intelligent Vehicles, Tongji University (同济大学), Shanghai, China (同济大学, 上海, 中国); School of Surveying and Geo-Informatics, Tongji University (同济大学), Shanghai, China (同济大学, 上海, 中国)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-63] Self-Adaptive Gamma Context-Aware SSM-based Model for Metal Defect Detection

链接: https://arxiv.org/abs/2503.01234
作者: Sijin Sun,Ming Deng,Xingrui Yu,Xinyu Xi,Liangbin Zhao
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 19 pages, 9 figures, under review

点击查看摘要

[CV-64] ra-MIND: Tera-scale mouse brain simulation via spatial mRNA-guided diffusion

链接: https://arxiv.org/abs/2503.01220
作者: Jiqing Wu,Ingrid Berg,Yawei Li,Ender Konukoglu,Viktor H. Koelzer
机构: Department of Biomedical Engineering, University of Basel (巴斯el大学), Switzerland; Department of Pathology and Molecular Pathology, University Hospital, University of Zurich (苏黎世大学), Switzerland; Computer Vision Lab, ETH Zurich (瑞士联邦理工学院), Switzerland; Integrated System Laboratory, ETH Zurich (瑞士联邦理工学院), Switzerland; Institute of Medical Genetics and Pathology, University Hospital Basel (巴塞尔大学医院), Switzerland
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-65] One-Step Event-Driven High-Speed Autofocus CVPR2025

链接: https://arxiv.org/abs/2503.01214
作者: Yuhan Bao,Shaohua Gao,Wenyong Li,Kaiwei Wang
机构: State Key Laboratory of Extreme Photonics and Instrumentation, Zhejiang University (浙江大学), China
类目: Computer Vision and Pattern Recognition (cs.CV); Optics (physics.optics)
备注: Main text: 9 pages, 6 figures. Supplementary Material: 4 pages, 3 figures. Accepted by CVPR2025

点击查看摘要

[CV-66] Understanding Dataset Distillation via Spectral Filtering

链接: https://arxiv.org/abs/2503.01212
作者: Deyu Bo,Songhua Liu,Xinchao Wang
机构: National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-67] Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond

链接: https://arxiv.org/abs/2503.01210
作者: Guanyao Wu,Haoyu Liu,Hongming Fu,Yichuan Peng,Jinyuan Liu,Xin Fan,Risheng Liu
机构: School of Software Technology & DUT-RU International School of ISE, Dalian University of Technology (大连理工大学软件学院 & 大连理工大学-白俄罗斯国立大学国际信息科学与工程学院); School of Mechanical Engineering, Dalian University of Technology (大连理工大学机械工程学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-68] A Multi-Sensor Fusion Approach for Rapid Orthoimage Generation in Large-Scale UAV Mapping

链接: https://arxiv.org/abs/2503.01202
作者: Jialei He,Zhihao Zhan,Zhituo Tu,Xiang Zhu,Jie Yuan
机构: School of Electronic Science and Engineering, Nanjing University (南京大学), China; TopXGun Robotics (TopXGun机器人), Nanjing, China
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-69] Parameter-free Video Segmentation for Vision and Language Understanding

链接: https://arxiv.org/abs/2503.01201
作者: Louis Mahon,Mirella Lapata
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-70] LiteGS: A High-Performance Modular Framework for Gaussian Splatting Training

链接: https://arxiv.org/abs/2503.01199
作者: Kaimin Liao
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-71] PostHoc FREE Calibrating on Kolmogorov Arnold Networks

链接: https://arxiv.org/abs/2503.01195
作者: Wenhao Liang,Wei Emma Zhang,Lin Yue,Miao Xu,Olaf Maennel,Weitong Chen
机构: Model call failure
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: Under reviewing

点击查看摘要

[CV-72] Near-infrared Image Deblurring and Event Denoising with Synergistic Neuromorphic Imaging

链接: https://arxiv.org/abs/2503.01193
作者: Chao Qu,Shuo Zhu,Yuhang Wang,Zongze Wu,Xiaoyu Chen,Edmund Y.Lam,Jing Han
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-73] Enhancing Retinal Vessel Segmentation Generalization via Layout-Aware Generative Modelling

链接: https://arxiv.org/abs/2503.01190
作者: Jonathan Fhima,Jan Van Eijgen,Lennert Beeckmans,Thomas Jacobs,Moti Freiman,Luis Filipe Nakayama,Ingeborg Stalmans,Chaim Baskin,Joachim A. Behar
机构: Faculty of Biomedical Engineering, Technion-IIT, Israel (以色列理工学院生物医学工程学院); Faculty of Mathematics, Technion-IIT, Israel (以色列理工学院数学学院); Department of Neurosciences, KU Leuven, Belgium (比利时鲁汶大学神经科学系); Department of Ophthalmology, UZ Leuven, Belgium (比利时鲁汶大学医院眼科系); Department of Electrical Engineering, KU Leuven, Belgium (比利时鲁汶大学电气工程系); Ophthalmology Department, São Paulo Federal University, Brazil (巴西圣保罗联邦大学眼科系); Medical Engineering and Science, Massachusetts Institute of Technology, USA (美国麻省理工学院医学工程与科学); School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Israel (以色列本-古里安大学电气与计算机工程学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-74] DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution CVPR2025

链接: https://arxiv.org/abs/2503.01187
作者: Xingyuan Li,Zirui Wang,Yang Zou,Zhixin Chen,Jun Ma,Zhiying Jiang,Long Ma,Jinyuan Liu
机构: Dalian University of Technology (大连理工大学); Northwestern Polytechnical University (西北工业大学); Waseda University (早稻田大学); Dalian Maritime University (大连海事大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: This paper was accepted by CVPR 2025

点击查看摘要

[CV-75] Language-Assisted Feature Transformation for Anomaly Detection ICLR2025

链接: https://arxiv.org/abs/2503.01184
作者: EungGu Yun,Heonjin Ha,Yeongwoo Nam,Bryan Dongik Lee
机构: 未知
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: ICLR 2025

点击查看摘要

[CV-76] SAR-W-MixMAE: SAR Foundation Model Training Using Backscatter Power Weighting

链接: https://arxiv.org/abs/2503.01181
作者: Ali Caglayan,Nevrez Imamoglu,Toru Kouyama
机构: National Institute of Advanced Industrial Science and Technology (国立研究開発法人産業技術総合研究所)
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注: 5 pages, 1 figure

点击查看摘要

[CV-77] HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation CVPR2025

链接: https://arxiv.org/abs/2503.01175
作者: Hongye Cheng,Tianyu Wang,Guangsi Shi,Zexing Zhao,Yanwei Fu
机构: College of Mechanical and Electronic Engineering, Northwest A&F University (西北农林科技大学机械与电子工程学院); Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University (复旦大学类脑智能科学与技术研究院); Department of Chemical and Biological Engineering, Faculty of Engineering, Monash University (蒙纳士大学工程学院化学与生物工程系); College of Information Engineering, Northwest A&F University (西北农林科技大学信息工程学院); School of Data Science, Fudan University (复旦大学数据科学学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注: Accepted by CVPR 2025. See this https URL

点击查看摘要

[CV-78] A Zero-Shot Learning Approach for Ephemeral Gully Detection from Remote Sensing using Vision Language Models

链接: https://arxiv.org/abs/2503.01169
作者: Seyed Mohamad Ali Tousi,Ramy Farag,Jacket Demby’s,Gbenga Omotara,John A. Lory,G. N. DeSouza
机构: Vision Guided and Intelligent Robotics Laboratory (ViGIR), EECS Dept. (电气与计算机工程系); Division of Plant Sciences (植物科学系); University of Missouri (密苏里大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-79] Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data

链接: https://arxiv.org/abs/2503.01167
作者: Haoxin Li,Boyang Li
机构: 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-80] Med-LEGO: Editing and Adapting toward Generalist Medical Image Diagnosis

链接: https://arxiv.org/abs/2503.01164
作者: Yitao Zhu,Yuan Yin,Jiaming Li,Mengjie Xu,Zihao Zhao,Honglin Xiong,Sheng Wang,Qian Wang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-81] Split Gibbs Discrete Diffusion Posterior Sampling

链接: https://arxiv.org/abs/2503.01161
作者: Wenda Chu,Yang Song,Yisong Yue
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-82] EasyCraft: A Robust and Efficient Framework for Automatic Avatar Crafting

链接: https://arxiv.org/abs/2503.01158
作者: Suzhen Wang,Weijie Chen,Wei Zhang,Minda Zhao,Lincheng Li,Rongsheng Zhang,Zhipeng Hu,Xin Yu
机构: Netease Fuxi AI Lab (网易伏羲实验室); The University of Queensland (昆士兰大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-83] One-shot In-context Part Segmentation

链接: https://arxiv.org/abs/2503.01144
作者: Zhenqi Dai,Ting Liu,Xingxing Zhang,Yunchao Wei,Yanning Zhang
机构: Northwestern Polytechnical University(Xi’an, Shaanxi, China); Tsinghua University(Beijing, China); Beijing Jiaotong University(Beijing, China)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 10 pages

点击查看摘要

[CV-84] Prior-guided Hierarchical Harmonization Network for Efficient Image Dehazing

链接: https://arxiv.org/abs/2503.01136
作者: Xiongfei Su,Siyuan Li,Yuning Cui,Miao Cao,Yulun Zhang,Zheng Chen,Zongliang Wu,Zedong Wang,Yuanlong Zhang,Xin Yuan
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-85] AirRoom: Objects Matter in Room Reidentification CVPR2025

链接: https://arxiv.org/abs/2503.01130
作者: Runmao Yao,Yi Du,Zhuoqun Chen,Haoze Zheng,Chen Wang
机构: Spatial AI & Robotics (SAIR) Lab, University at Buffalo
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Paper accepted at CVPR 2025

点击查看摘要

[CV-86] ViKANformer: Embedding Kolmogorov Arnold Networks in Vision Transformers for Pattern-Based Learning DATE

链接: https://arxiv.org/abs/2503.01124
作者: Shreyas S,Akshath M
机构: School of Computer Science and Engineering (计算机科学与工程学院), VIT-AP University (VIT-AP大学), India (印度)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: This paper represents ongoing research and may be subject to revisions, refinements, and additional experiments in future updates

点击查看摘要

[CV-87] ACCORD: Alleviating Concept Coupling through Dependence Regularization for Text-to-Image Diffusion Personalization

链接: https://arxiv.org/abs/2503.01122
作者: Shizhan Liu,Hao Zheng,Hang Yu,Jianguo Li
机构: Ant Group (蚂蚁集团); AntGroup (蚂蚁集团)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-88] WeGen: A Unified Model for Interactive Multimodal Generation as We Chat CVPR2025

链接: https://arxiv.org/abs/2503.01115
作者: Zhipeng Huang,Shaobin Zhuang,Canmiao Fu,Binxin Yang,Ying Zhang,Chong Sun,Zhizheng Zhang,Yali Wang,Chen Li,Zheng-Jun Zha
机构: University of Science and Technology of China (中国科学技术大学); Shanghai Jiao Tong University (上海交通大学); WeChat, Tencent Inc (微信，腾讯公司); Chinese Academy of Sciences (中国科学院); Galbot
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: CVPR 2025

点击查看摘要

[CV-89] Semi-Supervised 360 Layout Estimation with Panoramic Collaborative Perturbations

链接: https://arxiv.org/abs/2503.01114
作者: Junsong Zhang,Chunyu Lin,Zhijie Shen,Lang Nie,Kang Liao,Yao Zhao
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages,4 figures

点击查看摘要

[CV-90] SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures CVPR2025

链接: https://arxiv.org/abs/2503.01113
作者: Hui Liu,Chen Jia,Fan Shi,Xu Cheng,Shengyong Chen
机构: School of Computer Science and Engineering, Tianjin University of Technology (天津大学技术师范大学计算机科学与工程学院); Engineering Research Center of Learning-Based Intelligent System (Ministry of Education) (基于学习的智能系统教育部工程研究中心); Key Laboratory of Computer Vision and System (Ministry of Education) (计算机视觉与系统教育部重点实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: This paper has been accepted by CVPR2025

点击查看摘要

[CV-91] FGS-SLAM: Fourier-based Gaussian Splatting for Real-time SLAM with Sparse and Dense Map Fusion

链接: https://arxiv.org/abs/2503.01109
作者: Yansong Xu,Junlin Li,Wei Zhang,Siyu Chen,Shengyong Zhang,Yuquan Leng,Weijia Zhou
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学国家重点实验室); University of Chinese Academy of Sciences (中国科学院大学); Department of Mechanical and Energy Engineering, Southern University of Science and Technology (南方科技大学机械与能源工程系)
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-92] VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priors

链接: https://arxiv.org/abs/2503.01107
作者: Juil Koo,Paul Guerrero,Chun-Hao Paul Huang,Duygu Ceylan,Minhyuk Sung
机构: KAIST; Adobe Research (Adobe 研究院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Project page: this https URL

点击查看摘要

[CV-93] Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator

链接: https://arxiv.org/abs/2503.01103
作者: Kaiwen Zheng,Yongxin Chen,Huayu Chen,Guande He,Ming-Yu Liu,Jun Zhu,Qinsheng Zhang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Project Page: this https URL

点击查看摘要

[CV-94] Fence Theorem: Preprocessing is Dual-Objective Semantic Structure Isolator in 3D Anomaly Detection

链接: https://arxiv.org/abs/2503.01100
作者: Hanzhe Liang,Jie Zhou,Xuanxin Chen,Jinbao Wang,Can Gao
机构: College of Computer Science and Software Engineering, Shenzhen University (深圳大学计算机科学与软件工程学院); Shenzhen Audencia Financial Technology Institute, Shenzhen University (深圳大学安特卫普金融科技研究所); National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University (大数据系统计算技术国家地方联合工程实验室); Faculty of Education, Shenzhen University (教育学院, 深圳大学); Guangdong Provincial Key Laboratory of Intelligent Information Processing (广东省智能信息处理重点实验室)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-95] One-Shot Affordance Grounding of Deformable Objects in Egocentric Organizing Scenes

链接: https://arxiv.org/abs/2503.01092
作者: Wanjun Jia,Fan Yang,Mengfei Duan,Xianchi Chen,Yinxi Wang,Yiming Jiang,Wenrui Chen,Kailun Yang,Zhiyong Li
机构: School of Robotics, Hunan University, China (湖南大学机器人学院); National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, China (湖南大学机器人视觉感知与控制技术国家工程研究中心)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO); Image and Video Processing (eess.IV)
备注: Source code and benchmark dataset will be publicly available at this https URL

点击查看摘要

[CV-96] Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-Time CVPR2025

链接: https://arxiv.org/abs/2503.01087
作者: Jon Donnelly,Zhicheng Guo,Alina Jade Barnett,Hayden McTavish,Chaofan Chen,Cynthia Rudin
机构: Duke University; University of Maine (缅因大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Accepted for publication in CVPR 2025

点击查看摘要

[CV-97] Identity documents recognition and detection using semantic segmentation with convolutional neural network

链接: https://arxiv.org/abs/2503.01085
作者: Mykola Kozlenko,Volodymyr Sendetskyi,Oleksiy Simkiv,Nazar Savchenko,Andy Bosyi
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 9 pages, 8 figures. This paper was originally published in 2021 Workshop on Cybersecurity Providing in Information and Telecommunication Systems, in CEUR Workshop Proceedings, vol. 2923, available: this https URL

点击查看摘要

[CV-98] OceanSim: A GPU-Accelerated Underwater Robot Perception Simulation Framework

链接: https://arxiv.org/abs/2503.01074
作者: Jingyu Song,Haoyu Ma,Onur Bagoren,Advaith V. Sethuraman,Yiting Zhang,Katherine A. Skinner
机构: Department of Robotics, University of Michigan (密歇根大学机器人系)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 6 figures

点击查看摘要

[CV-99] A Comparison of Object Detection and Phrase Grounding Models in Chest X-ray Abnormality Localization using Eye-tracking Data

链接: https://arxiv.org/abs/2503.01037
作者: Elham Ghelichkhan,Tolga Tasdizen
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Accepted in 2025 IEEE International Symposium on Biomedical Imaging (ISBI 2025)

点击查看摘要

[CV-100] Delving into Out-of-Distribution Detection with Medical Vision-Language Models

链接: https://arxiv.org/abs/2503.01020
作者: Lie Ju,Sijin Zhou,Yukun Zhou,Huimin Lu,Zhuoting Zhu,Pearse A. Keane,Zongyuan Ge
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-101] MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations CVPR2025

链接: https://arxiv.org/abs/2503.01019
作者: Ziyang Zhang,Yang Yu,Yucheng Chen,Xulei Yang,Si Yong Yeo
机构: MedVisAI Lab; Department of Electrical and Computer Engineering, Northwestern University; Department of Machine Intellection, Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR); Lee Kong Chian School of Medicine, Nanyang Technological University
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: To be pubilshed in CVPR 2025

点击查看摘要

[CV-102] Generative Motion Infilling From Imprecisely Timed Keyframes

链接: https://arxiv.org/abs/2503.01016
作者: Purvi Goel,Haotian Zhang,C. Karen Liu,Kayvon Fatahalian
机构: Stanford University (斯坦福大学); NVIDIA (英伟达)
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, Eurographics 2025

点击查看摘要

[CV-103] Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning ICLR2025

链接: https://arxiv.org/abs/2503.00986
作者: Baoqi Pei,Yifei Huang,Jilan Xu,Guo Chen,Yuping He,Lijin Yang,Yali Wang,Weidi Xie,Yu Qiao,Fei Wu,Limin Wang
机构: Zhejiang University (浙江大学); Shanghai Artificial Intelligence Laboratory (上海人工智能实验室); The University of Tokyo (东京大学); Fudan University (复旦大学); Nanjing University (南京大学); SIAT (深圳先进技术研究院); Shanghai Jiao Tong University (上海交通大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted as ICLR 2025 conference paper

点击查看摘要

[CV-104] Semantic-ICP: Iterative Closest Point for Non-rigid Multi-Organ Point Cloud Registration MICCAI2025

链接: https://arxiv.org/abs/2503.00972
作者: Wanwen Chen,Carson Studders,Jamie J.Y. Kwon,Emily H.T. Pang,Eitan Prisman,Septimiu E. Salcudean
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 3 figures, submitted to MICCAI 2025

点击查看摘要

[CV-105] Using Synthetic Images to Augment Small Medical Image Datasets

链接: https://arxiv.org/abs/2503.00962
作者: Minh H. Vu,Lorenzo Tronchin,Tufve Nyholm,Tommy Löfstedt
机构: Umeå University (乌梅å大学); Università Campus Bio-Medico di Roma (生物医学校区罗马大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 14 pages

点击查看摘要

[CV-106] A Survey on Ordinal Regression: Applications Advances and Prospects

链接: https://arxiv.org/abs/2503.00952
作者: Jinhong Wang,Jintai Chen,Jian Liu,Dongqi Tang,Danny Z. Chen,Jian Wu
机构: College of Computer Science & Technology Zhejiang University (浙江大学计算机科学与技术学院), State Key Laboratory of Transvascular Implantation Devices of The Second Affiliated Hospital Zhejiang University School of Medicine (浙江大学医学院第二附属医院血管植入装置国家重点实验室), Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence (浙江省医学影像人工智能重点实验室), School of Public Health Zhejiang University (浙江大学公共卫生学院), AntGroup (蚂蚁集团), HKUST (Guangzhou) (香港科技大学（广州）), University of Notre Dame (圣母大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-107] Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models ICLR2025

链接: https://arxiv.org/abs/2503.00951
作者: Xingzhuo Guo,Yu Zhang,Baixu Chen,Haoran Xu,Jianmin Wang,Mingsheng Long
机构: School of Software, BNRist, Tsinghua University (清华大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: ICLR 2025 Accepted

点击查看摘要

[CV-108] Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think CVPR2025

链接: https://arxiv.org/abs/2503.00948
作者: Jie Tian,Xiaoye Qu,Zhenyi Lu,Wei Wei,Sichen Liu,Yu Cheng
机构: School of Computer Science & Technology, Huazhong University of Science and Technology (华中科技大学计算机科学与技术学院); The Chinese University of Hong Kong (香港中文大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR2025

点击查看摘要

[CV-109] From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization

链接: https://arxiv.org/abs/2503.00938
作者: Chao Yuan,Guiwei Zhang,Changxiao Ma,Tianyi Zhang,Guanglin Niu
机构: School of Computer Science and Engineering, Beihang University (北航计算机科学与工程学院); School of Artificial Intelligence, Beihang University (北航人工智能学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-110] IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis AAAI2025

链接: https://arxiv.org/abs/2503.00936
作者: Yuji Wang,Jingchen Ni,Yong Liu,Chun Yuan,Yansong Tang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: AAAI 2025

点击查看摘要

[CV-111] Improving the Transferability of Adversarial Attacks by an Input Transpose

链接: https://arxiv.org/abs/2503.00932
作者: Qing Wan,Shilong Deng,Xun Wang
机构: School of Computer Science and Technology, Zhejiang Gongshang University (浙江工商大学计算机科学与技术学院), Zhejiang Province 310018, China (中国浙江省310018)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Machine Learning (cs.LG)
备注: 15 pages, 11 figures

点击查看摘要

[CV-112] Revisiting CAD Model Generation by Learning Raster Sketch

链接: https://arxiv.org/abs/2503.00928
作者: Pu Li,Wenhao Zhang,Jianwei Guo,Jinglu Chen,Dong-Ming Yan
机构: 未知
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-113] Explainable Classifier for Malignant Lymphoma Subtyping via Cell Graph and Image Fusion

链接: https://arxiv.org/abs/2503.00925
作者: Daiki Nishiyama,Hiroaki Miyoshi,Noriaki Hashimoto,Koichi Ohshima,Hidekata Hontani,Ichiro Takeuchi,Jun Sakuma
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 11 pages, 3 figure

点击查看摘要

[CV-114] Multimodal Distillation-Driven Ensemble Learning for Long-Tailed Histopathology Whole Slide Images Analysis

链接: https://arxiv.org/abs/2503.00915
作者: Xitong Ling,Yifeng Ping,Jiawen Li,Jing Peng,Yuxuan Chen,Minxi Ouyang,Yizhi Wang,Yonghong He,Tian Guan,Xiaoping Liu,Lianghui Zhu
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-115] DEAL: Data-Efficient Adversarial Learning for High-Quality Infrared Imaging

链接: https://arxiv.org/abs/2503.00905
作者: Zhu Liu,Zijun Wang,Jinyuan Liu,Fanqi Meng,Long Ma,Risheng Liu
机构: School of Software Technology, Dalian University of Technology (大连理工大学软件学院); School of Mechanical Engineering, Dalian University of Technology (大连理工大学机械工程学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: The source code will be available at this https URL

点击查看摘要

[CV-116] FunBench: Benchmarking Fundus Reading Skills of MLLM s

链接: https://arxiv.org/abs/2503.00901
作者: Qijie Wei,Kaiheng Qian,Xirong Li
机构: Renmin University of China (中国人民大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 7 pages

点击查看摘要

[CV-117] A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning

链接: https://arxiv.org/abs/2503.00897
作者: Shashank Gupta,Chaitanya Ahuja,Tsung-Yu Lin,Sreya Dutta Roy,Harrie Oosterhuis,Maarten de Rijke,Satya Narayan Shukla
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-118] Estimating Blood Pressure with a Camera: An Exploratory Study of Ambulatory Patients with Cardiovascular Disease

链接: https://arxiv.org/abs/2503.00890
作者: Theodore Curran,Chengqian Ma,Xin Liu,Daniel McDuff,Girish Narayanswamy,George Stergiou,Shwetak Patel,Eugene Yang
机构: Paul G. Allen School of Computer Science & Engineering (保罗·G·艾伦计算机科学与工程学院); Division of Cardiology, University of Washington School of Medicine (华盛顿大学医学院心脏科); National and Kapodistrian University of Athens, School of Medicine (雅典国立卡波迪斯特里安大学医学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-119] Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization

链接: https://arxiv.org/abs/2503.00881
作者: You Shen,Zhipeng Zhang,Xinyang Li,Yansong Qu,Yu Lin,Shengchuan Zhang,Liujuan Cao
机构: Key Laboratory of Multimedia Trusted Perception and Efficient Computing (多媒体可信感知与高效计算重点实验室), Ministry of Education of China (中华人民共和国教育部), Xiamen University (厦门大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-120] Zero-Shot Head Swapping in Real-World Scenarios CVPR’25

链接: https://arxiv.org/abs/2503.00861
作者: Sohyun Jeong,Taewoong Kang,Hyojin Jang,Jaegul Choo
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: CVPR’25

点击查看摘要

[CV-121] MTReD: 3D Reconstruction Dataset for Fly-over Videos of Maritime Domain WACV

链接: https://arxiv.org/abs/2503.00853
作者: Rui Yi Yong,Samuel Picosson,Arnold Wiliem
机构: Shield AI; Monash University (蒙纳士大学); Queensland University of Technology (昆士兰科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: WACV Workshop 2025 - 3rd Workshop on Maritime Computer Vision (MaCVI2025)

点击查看摘要

[CV-122] PSRGS:Progressive Spectral Residual of 3D Gaussian for High-Frequency Recovery

链接: https://arxiv.org/abs/2503.00848
作者: BoCheng Li,WenJuan Zhang,Bing Zhang,YiLing Yao,YaNing Wang
机构: Aerospace Information Research Institute (航天信息研究院); University of Chinese Academy of Sciences (中国科学院大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-123] Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Models ICLR2025

链接: https://arxiv.org/abs/2503.00838
作者: Jeffrey Gu,Serena Yeung-Levy
机构: Institute for Computational and Mathematical Engineering (ICME), Department of Biomedical Data Science (生物医学数据科学系), Stanford University (斯坦福大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: ICLR 2025

点击查看摘要

[CV-124] raining-Free Dataset Pruning for Instance Segmentation ICLR2025

链接: https://arxiv.org/abs/2503.00828
作者: Yalun Dai,Lingao Xiao,Ivor W. Tsang,Yang He
机构: CFAR, Agency for Science, Technology and Research (ASTAR), Singapore; IHPC, Agency for Science, Technology and Research (ASTAR), Singapore; Nanyang Technological University (南洋理工大学); National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Accepted by ICLR 2025

点击查看摘要

[CV-125] ask-Agnostic Guided Feature Expansion for Class-Incremental Learning CVPR2025

链接: https://arxiv.org/abs/2503.00823
作者: Bowen Zheng,Da-Wei Zhou,Han-Jia Ye,De-Chuan Zhan
机构: National Key Laboratory for Novel Software Technology, Nanjing University (南京大学国家重点实验室); School of Artificial Intelligence, Nanjing University (南京大学人工智能学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to CVPR2025

点击查看摘要

[CV-126] Random Walks in Self-supervised Learning for Triangular Meshes

链接: https://arxiv.org/abs/2503.00816
作者: Gal Yefet,Ayellet Tal
机构: Technion – Israel Institute of Technology (以色列理工学院)
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-127] Evaluating and Predicting Distorted Human Body Parts for Generated Images

链接: https://arxiv.org/abs/2503.00811
作者: Lu Ma,Kaibo Cao,Hao Liang,Jiaxin Lin,Zhuang Li,Yuhong Liu,Jihong Zhang,Wentao Zhang,Bin Cui
机构: Peking University (北京大学); Tencent Inc. (腾讯控股有限公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages, 6 figures

点击查看摘要

[CV-128] GenAnalysis: Joint Shape Analysis by Learning Man-Made Shape Generators with Deformation Regularizations

链接: https://arxiv.org/abs/2503.00807
作者: Yuezhi Yang,Haitao Yang,Kiyohiro Nakayama,Xiangru Huang,Leonidas Guibas,Qixing Huang
机构: The University of Texas at Austin (德克萨斯大学奥斯汀分校); Stanford University (斯坦福大学); Westlake University (西湖大学)
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV)
备注: 21 pages, 25 figures

点击查看摘要

[CV-129] DELST: Dual Entailment Learning for Hyperbolic Image-Gene Pretraining in Spatial Transcriptomics

链接: https://arxiv.org/abs/2503.00804
作者: Xulin Chen,Junzhou Huang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-130] HiMo: High-Speed Objects Motion Compensation in Point Clouds

链接: https://arxiv.org/abs/2503.00803
作者: Qingwen Zhang,Ajinkya Khoche,Yi Yang,Li Ling,Sina Sharif Mansouri,Olov Andersson,Patric Jensfelt
机构: Unknown
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注: 12 pages

点击查看摘要

[CV-131] MFM-DA: Instance-Aware Adaptor and Hierarchical Alignment for Efficient Domain Adaptation in Medical Foundation Models

链接: https://arxiv.org/abs/2503.00802
作者: Jia-Xuan Jiang,Wenhui Lei,Yifeng Wu,Hongtao Wu,Furong Li,Yining Xie,Xiaofan Zhang,Zhong Wang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-132] STAR-Edge: Structure-aware Local Spherical Curve Representation for Thin-walled Edge Extraction from Unstructured Point Clouds CVPR2025

链接: https://arxiv.org/abs/2503.00801
作者: Zikuan Li,Honghua Chen,Yuecheng Wang,Sibo Wu,Mingqiang Wei,Jun Wang
机构: Nanjing University of Aeronautics and Astronautics (南京航空航天大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at CVPR 2025

点击查看摘要

[CV-133] A Simple and Efficient Baseline for Video Action Recognition

链接: https://arxiv.org/abs/2503.00796
作者: Zhe Wang,Xulei Yang
机构: AAAI Press (AAAI出版社)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-134] Bridging Spectral-wise and Multi-spectral Depth Estimation via Geometry-guided Contrastive Learning ICRA2025

链接: https://arxiv.org/abs/2503.00793
作者: Ukcheol Shin,Kyunghyun Lee,Jean Oh
机构: CMU RI (卡内基梅隆大学机器人研究所); LG AI Research (LG人工智能研究院); CMU RI (卡内基梅隆大学机器人研究所)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Robotics (cs.RO)
备注: Accepted at ICRA 2025, Github link: this https URL

点击查看摘要

[CV-135] CARIL: Confidence-Aware Regression in Imitation Learning for Autonomous Driving

链接: https://arxiv.org/abs/2503.00783
作者: Elahe Delavari,Aws Khalil,Jaerock Kwon
机构: Department of Electrical and Computer Engineering, University of Michigan-Dearborn (密歇根大学迪尔伯恩分校电气与计算机工程系)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-136] Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation

链接: https://arxiv.org/abs/2503.00782
作者: Wenzhao Xiang,Chang Liu,Hongyang Yu,Xilin Chen
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-137] Enhanced Multi-Class Classification of Gastrointestinal Endoscopic Images with Interpretable Deep Learning Model

链接: https://arxiv.org/abs/2503.00780
作者: Astitva Kamble,Vani Bandodkar,Saakshi Dharmadhikary,Veena Anand,Pradyut Kumar Sanki,Mei X. Wu,Biswabandhu Jana
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-138] MR-EIT: Multi-Resolution Reconstruction for Electrical Impedance Tomography via Data-Driven and Unsupervised Dual-Mode Neural Networks

链接: https://arxiv.org/abs/2503.00762
作者: Fangming Shi,Jinzhen Liu,Xiangqian Meng,Yapeng Zhou,Hui Xiong
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-139] RACE: A Self-Improving Framework for Robot Behavior Forecasting with Vision-Language Models

链接: https://arxiv.org/abs/2503.00761
作者: Gokul Puthumanaillam,Paulo Padrao,Jose Fuentes,Pranay Thangeda,William E. Schafer,Jae Hyuk Song,Karan Jagdale,Leonardo Bobadilla,Melkior Ornik
机构: University of Illinois Urbana-Champaign (UIUC)(伊利诺伊大学厄巴纳-香槟分校); Florida International University (FIU)(佛罗里达国际大学); Lucid Group, Inc.(Lucid 集团公司)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV); Multiagent Systems (cs.MA); Systems and Control (eess.SY)
备注:

点击查看摘要

[CV-140] Dynamic Gradient Sparsification Training for Few-Shot Fine-tuning of CT Lymph Node Segmentation Foundation Model

链接: https://arxiv.org/abs/2503.00748
作者: Zihao Luo,Zijun Gao,Wenjun Liao,Shichuan Zhang,Guotai Wang,Xiangde Luo
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 3 figures, 2 tables, and the lymph node segmentation foundation model code and pretrained model are available

点击查看摘要

[CV-141] Unifying Light Field Perception with Field of Parallax

链接: https://arxiv.org/abs/2503.00747
作者: Fei Teng,Buyin Deng,Boyuan Zheng,Kai Luo,Kunyu Peng,Jiaming Zhang,Kailun Yang
机构: Hunan University (湖南大学); Karlsruhe Institute of Technology (卡尔斯鲁厄理工学院); ETH Zürich (瑞士联邦理工学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO); Image and Video Processing (eess.IV)
备注: The source code will be made publicly available at this https URL

点击查看摘要

[CV-142] DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting CVPR2025

链接: https://arxiv.org/abs/2503.00746
作者: Liao Shen,Tianqi Liu,Huiqiang Sun,Jiaqi Li,Zhiguo Cao,Wei Li,Chen Change Loy
机构: School of AIA, Huazhong University of Science and Technology (华中科技大学); S-Lab, Nanyang Technological University (南洋理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: CVPR 2025

点击查看摘要

[CV-143] Confounder-Aware Medical Data Selection for Fine-Tuning Pretrained Vision Models

链接: https://arxiv.org/abs/2503.00744
作者: Anyang Ji,Qingbo Kang,Wei Xu,Changfan Wang,Kang Li,Qicheng Lao
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 5 pages, 3 figures

点击查看摘要

[CV-144] Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models

链接: https://arxiv.org/abs/2503.00743
作者: Dilxat Muhtar,Enzhuo Zhang,Zhenshi Li,Feng Gu,Yanglangxing He,Pengfeng Xiao,Xueliang Zhang
机构: Nanjing University (南京大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 21 pages, 7 figures

点击查看摘要

[CV-145] FaceShot: Bring Any Character into Life ICLR2025

链接: https://arxiv.org/abs/2503.00740
作者: Junyao Gao,Yanan Sun,Fei Shen,Xin Jiang,Zhening Xing,Kai Chen,Cairong Zhao
机构: Tongji University (同济大学); Shanghai AI Laboratory (上海人工智能实验室); Nanjing University of Science and Technology (南京理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Published as a conference paper at ICLR 2025

点击查看摘要

[CV-146] Multi-Cali Anything: Dense Feature Multi-Frame Structure-from-Motion for Large-Scale Camera Array Calibration

链接: https://arxiv.org/abs/2503.00737
作者: Jinjiang You,Hewei Wang,Yijie Li,Mingxiao Huo,Long Van Tran Ha,Mingyuan Ma,Jinfeng Xu,Puzhen Wu,Shubham Garg,Wei Pu
机构: School of Computer Science, Carnegie Mellon University (卡内基梅隆大学计算机科学学院); Electrical and Computer Engineering, Carnegie Mellon University (卡内基梅隆大学电气与计算机工程学院); Harvard John A. Paulson School of Engineering And Applied Sciences, Harvard University (哈佛大学约翰·A·保尔森工程与应用科学学院); Department of Electrical and Electronic Engineering, The University of Hong Kong (香港大学电机电子工程系); Weill Cornell Medicine, Cornell University (康奈尔大学威尔医学院); Meta Reality Labs (Meta现实实验室)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 8 pages

点击查看摘要

[CV-147] Shazam: Unifying Multiple Foundation Models for Advanced Computational Pathology

链接: https://arxiv.org/abs/2503.00736
作者: Wenhui Lei,Anqi Li,Yusheng Tan,Hanyu Chen,Xiaofan Zhang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 9 pages, 2 figures

点击查看摘要

[CV-148] LightEndoStereo: A Real-time Lightweight Stereo Matching Method for Endoscopy Images

链接: https://arxiv.org/abs/2503.00731
作者: Yang Ding,Can Han,Sijia Du,Yaqi Wang,Dahong Qian
机构: The School of Biomedical Engineering, Shanghai Jiao Tong University (上海交通大学生物医学工程学院); The College of Media Engineering, Communication University of Zhejiang (浙江传媒学院媒体工程学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-149] Enhancing Monocular 3D Scene Completion with Diffusion Model

链接: https://arxiv.org/abs/2503.00726
作者: Changlin Song,Jiaqi Wang,Liyun Zhu,He Weng
机构: Australian National University (澳大利亚国立大学)
类目: Graphics (cs.GR); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: All authors had equal contribution

点击查看摘要

[CV-150] CREATE-FFPE: Cross-Resolution Compensated and Multi-Frequency Enhanced FS-to-FFPE Stain Transfer for Intraoperative IHC Images

链接: https://arxiv.org/abs/2503.00697
作者: Yiyang Lin,Danling Jiang,Xinyu Liu,Yun Miao,Yixuan Yuan
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-151] MoSFormer: Augmenting Temporal Context with Memory of Surgery for Surgical Phase Recognition

链接: https://arxiv.org/abs/2503.00695
作者: Hao Ding,Xu Lian,Mathias Unberath
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-152] Advancing Prompt-Based Methods for Replay-Independent General Continual Learning ICLR2025

链接: https://arxiv.org/abs/2503.00677
作者: Zhiqi Kang,Liyuan Wang,Xingxing Zhang,Karteek Alahari
机构: Inria(法国国家信息与自动化研究所); Tsinghua University (清华大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: ICLR 2025

点击查看摘要

[CV-153] Dur360BEV: A Real-world Single 360-degree Camera Dataset and Benchmark for Bird-Eye View Mapping in Autonomous Driving

链接: https://arxiv.org/abs/2503.00675
作者: Wenke E,Chao Yuan,Li Li,Yixin Sun,Yona Falinie A. Gaus,Amir Atapour-Abarghouei,Toby P. Breckon
机构: Durham University (杜伦大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-154] ransformer Based Self-Context Aware Prediction for Few-Shot Anomaly Detection in Videos

链接: https://arxiv.org/abs/2503.00670
作者: Gargi V. Pillai,Ashish Verma,Debashis Sen
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Copyright 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

点击查看摘要

[CV-155] Development of an Unpaired Deep Neural Network for Synthesizing X-ray Fluoroscopic Images from Digitally Reconstructed Tomography in Image Guided Radiotherapy

链接: https://arxiv.org/abs/2503.00665
作者: Chisako Hayashi,Shinichiro Mori,Yasukuni Mori,Lim Taehyeung,Hiroki Suyari,Hitoshi Ishikawa
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Medical Physics (physics.med-ph)
备注:

点击查看摘要

[CV-156] Deep Change Monitoring: A Hyperbolic Representative Learning Framework and a Dataset for Long-term Fine-grained Tree Change Detection

链接: https://arxiv.org/abs/2503.00643
作者: Yante Li,Hanwen Qi,Haoyu Chen,Xinlian Liang,Guoying Zhao
机构: Univeristy of Oulu (奥卢大学); Wuhan University (武汉大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 10 pages, 6 figures

点击查看摘要

[CV-157] Self-supervision via Controlled Transformation and Unpaired Self-conditioning for Low-light Image Enhancement

链接: https://arxiv.org/abs/2503.00642
作者: Aupendu Kar,Sobhan K. Dhara,Debashis Sen,Prabir K. Biswas
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注: Copyright 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

点击查看摘要

[CV-158] How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations ICLR2025

链接: https://arxiv.org/abs/2503.00641
作者: Siddhartha Gairola,Moritz Böhle,Francesco Locatello,Bernt Schiele
机构: Max Planck Institute for Informatics (德国马克斯·普朗克计算机科学研究所); Institute of Science and Technology Austria (奥地利科学技术学院); Kyutai (未知)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted as poster at ICLR 2025. GitHub Link: this https URL

点击查看摘要

[CV-159] Perceptual Visual Quality Assessment: Principles Methods and Future Directions

链接: https://arxiv.org/abs/2503.00625
作者: Wei Zhou,Hadi Amirpour,Christian Timmerer,Guangtao Zhai,Patrick Le Callet,Alan C. Bovik
机构: Cardiff University (卡迪夫大学, UK); University of Klagenfurt (克拉根福大学, Austria); Shanghai Jiao Tong University (上海交通大学, China); University of Nantes (南特大学, France); University of Texas at Austin (德克萨斯大学奥斯汀分校, USA)
类目: Multimedia (cs.MM); Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR)
备注: A tutorial and review

点击查看摘要

[CV-160] GenVDM: Generating Vector Displacement Maps From a Single Image CVPR2025

链接: https://arxiv.org/abs/2503.00605
作者: Yuezhi Yang,Qimin Chen,Vladimir G. Kim,Siddhartha Chaudhuri,Qixing Huang,Zhiqin Chen
机构: The University of Texas at Austin (德克萨斯大学奥斯汀分校); Simon Fraser University (西蒙弗雷泽大学); Adobe Research (Adobe 研究院)
类目: Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV)
备注: accepted to CVPR2025

点击查看摘要

[CV-161] AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models CVPR2025

链接: https://arxiv.org/abs/2503.00591
作者: Sohan Patnaik,Rishabh Jain,Balaji Krishnamurthy,Mausoom Sarkar
机构: Adobe Research (Adobe 研究院); MDSR Adobe (MDSR Adobe)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted for publication in CVPR 2025

点击查看摘要

[CV-162] Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasing CVPR2025

链接: https://arxiv.org/abs/2503.00548
作者: Yanjun Li,Zhaoyang Li,Honghui Chen,Lizhi Xu
机构: University of Science and Technology of China (中国科学技术大学); College of Physics and Information Engineering, Fuzhou University (福州大学物理与信息工程学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
备注: 17 pages, 8 figures, CVPR 2025

点击查看摘要

[CV-163] RFWNet: A Lightweight Remote Sensing Object Detector Integrating Multi-Scale Receptive Fields and Foreground Focus Mechanism

链接: https://arxiv.org/abs/2503.00545
作者: Yujie Lei,Wenjie Sun,Sen Jia,Qingquan Li,Jie Zhang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-164] Streaming Video Question-Answering with In-context Video KV-Cache Retrieval ICLR2025

链接: https://arxiv.org/abs/2503.00540
作者: Shangzhe Di,Zhelun Yu,Guanghao Zhang,Haoyuan Li,Tao Zhong,Hao Cheng,Bolin Li,Wanggui He,Fangxun Shu,Hao Jiang
机构: Shanghai Jiao Tong University (上海交通大学); Alibaba Group (阿里巴巴集团)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to ICLR 2025. Code: this https URL

点击查看摘要

[CV-165] GaussianSeal: Rooting Adaptive Watermarks for 3D Gaussian Generation Model

链接: https://arxiv.org/abs/2503.00531
作者: Runyi Li,Xuanyu Zhang,Chuhan Tong,Zhipei Xu,Jian Zhang
机构: School of Electronic and Computer Engineering, Peking University (北京大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注:

点击查看摘要

[CV-166] Efficient Prompting for Continual Adaptation to Missing Modalities NAACL2025

链接: https://arxiv.org/abs/2503.00528
作者: Zirun Guo,Shulei Wang,Wang Lin,Weicai Yan,Yangyang Wu,Tao Jin
机构: Zhejiang University (浙江大学)
类目: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to NAACL 2025 Main

点击查看摘要

[CV-167] 2DMCG:2DMambawith Change Flow Guidance for Change Detection in Remote Sensing

链接: https://arxiv.org/abs/2503.00521
作者: JunYao Kaung,HongWei Ge
机构: Jiangnan University (江南大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-168] Explainable LiDAR 3D Point Cloud Segmentation and Clustering for Detecting Airplane-Generated Wind Turbulence KDD2025

链接: https://arxiv.org/abs/2503.00518
作者: Zhan Qu,Shuzhou Yuan,Michael Färber,Marius Brennfleck,Niklas Wartha,Anton Stephan
机构: Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院); ScaDS.AI, TU Dresden(TU德累斯顿ScaDS人工智能中心); Institute of Atmospheric Physics, German Aerospace Center(德国航空航天中心大气物理研究所); RWTH Aachen University(亚琛工业大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: Accepted at KDD 2025

点击查看摘要

[CV-169] wo-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking AAAI2025

链接: https://arxiv.org/abs/2503.00516
作者: Jiawen Zhu,Huayi Tang,Xin Chen,Xinying Wang,Dong Wang,Huchuan Lu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by AAAI2025

点击查看摘要

[CV-170] Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning

链接: https://arxiv.org/abs/2503.00515
作者: Songlin Dong,Yuhang He,Zhengdong Zhou,Haoyu Luo,Xing Wei,Alex C. Kot,Yihong Gong
机构: College of Artificial Intelligence, Xi’an Jiaotong University (西安交通大学人工智能学院); College of Software Engineering, Xi’an Jiaotong University (西安交通大学软件工程学院); School of Electrical and Electronic Engineering, Nanyang Technological University (南洋理工大学电气与电子工程学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-171] Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning CVPR2025

链接: https://arxiv.org/abs/2503.00513
作者: Hanxun Yu,Wentong Li,Song Wang,Junbo Chen,Jianke Zhu
机构: Zhejiang University (浙江大学); Nanjing University of Aeronautics and Astronautics (南京航空航天大学); Udeer.ai
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: CVPR2025, Code Link: this https URL

点击查看摘要

[CV-172] owards High-fidelity 3D Talking Avatar with Personalized Dynamic Texture

链接: https://arxiv.org/abs/2503.00495
作者: Xuanchen Li,Jianyu Wang,Yuhao Cheng,Yikun Zeng,Xingyu Ren,Wenhan Zhu,Weiming Zhao,Yichao Yan
机构: MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University (教育部人工智能重点实验室，上海交通大学人工智能研究院); Student Innovation Center, Shanghai Jiao Tong University (上海交通大学学生创新中心); Xueshen AI (学神人工智能)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-173] SDW: A Tri-Stream Dynamic Weight Network for Cloth-Changing Person Re-Identification

链接: https://arxiv.org/abs/2503.00477
作者: Ruiqi He,Zihan Wang,Xiang Zhou
机构: School of Software, Nanchang University (南昌大学软件学院), China; Department of Computer Science and Technology, Tongji University (同济大学计算机科学与技术系), China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-174] Rapid morphology characterization of two-dimensional TMDs and lateral heterostructures based on deep learning

链接: https://arxiv.org/abs/2503.00470
作者: Junqi He,Yujie Zhang,Jialu Wang,Tao Wang,Pan Zhang,Chengjie Cai,Jinxing Yang,Xiao Lin,Xiaohui Yang
机构: Hangzhou Key Laboratory of Quantum Matter, School of Physics, Hangzhou Normal University (杭州师范大学); ZJU-Hangzhou Global Scientific and Technological Innovation Center, College of Integrated Circuits, Zhejiang University (浙江大学); Department of Physics and Texas Center for Superconductivity, University of Houston (休斯敦大学); Key Laboratory for Quantum Materials of Zhejiang Province, Department of Physics, School of Science, Westlake University (西湖大学)
类目: Machine Learning (cs.LG); Materials Science (cond-mat.mtrl-sci); Computer Vision and Pattern Recognition (cs.CV); Optics (physics.optics)
备注:

点击查看摘要

[CV-175] Adaptive Rectangular Convolution for Remote Sensing Pansharpening CVPR

链接: https://arxiv.org/abs/2503.00467
作者: Xueyang Wang,Zhixin Zheng,Jiandong Shao,Yule Duan,Liang-Jian Deng
机构: University of Electronic Science and Technology of China (电子科技大学), Chengdu, China
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注: 8 pages, 6 figures, Accepted by CVPR

点击查看摘要

[CV-176] Bring Your Own Grasp Generator: Leverag ing Robot Grasp Generation for Prosthetic Grasping ICRA2025

链接: https://arxiv.org/abs/2503.00466
作者: Giuseppe Stracquadanio,Federico Vasile,Elisa Maiettini,Nicolò Boccardo,Lorenzo Natale
机构: Istituto Italiano di Tecnologia (意大利技术研究院); Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS), University of Genova (热那亚大学计算机、生物医学工程、机器人及系统工程系); Open University Affiliated Research Centre at Istituto Italiano di Tecnologia (IIT 的开放大学附属研究中心)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV); Systems and Control (eess.SY)
备注: Accepted to ICRA 2025. Project Website: this https URL

点击查看摘要

[CV-177] Deep Learning based approach to detect Customer Age Gender and Expression in Surveillance Video

链接: https://arxiv.org/abs/2503.00453
作者: Earnest Paul Ijjina,Goutham Kanahasabai,Aniruddha Srinivas Joshi
机构: National Institute of Technology Warangal (国家技术学院瓦朗加尔)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-178] Customer Analytics using Surveillance Video

链接: https://arxiv.org/abs/2503.00452
作者: Earnest Paul Ijjina,Aniruddha Srinivas Joshi,Goutham Kanahasabai,Keerthi Priyanka P
机构: National Institute of Technology Warangal (国家技术学院瓦朗加尔)
类目: Computers and Society (cs.CY); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-179] Ranking pre-trained segmentation models for zero-shot transferability

链接: https://arxiv.org/abs/2503.00450
作者: Joshua Talks,Anna Kreshuk
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 11 pages, 3 figures

点击查看摘要

[CV-180] Detection of Customer Interested Garments in Surveillance Video using Computer Vision

链接: https://arxiv.org/abs/2503.00442
作者: Earnest Paul Ijjina,Aniruddha Srinivas Joshi,Goutham Kanahasabai
机构: National Institute of Technology Warangal (国家技术学院瓦朗加尔)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-181] Split Adaptation for Pre-trained Vision Transformers CVPR2025

链接: https://arxiv.org/abs/2503.00441
作者: Lixu Wang,Bingqi Shang,Yi Li,Payal Mohapatra,Wei Dong,Xiao Wang,Qi Zhu
机构: Northwestern University (西北大学); Nanyang Technological University (南洋理工大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: This paper has been accepted by CVPR 2025. The first two authors contributed equally

点击查看摘要

[CV-182] HalCECE: A Framework for Explainable Hallucination Detection through Conceptual Counterfactuals in Image Captioning

链接: https://arxiv.org/abs/2503.00436
作者: Maria Lymperaiou,Giorgos FIlandrianos,Angeliki Dimitriou,Athanasios Voulodimos,Giorgos Stamou
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-183] DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing

链接: https://arxiv.org/abs/2503.00429
作者: Jingyi Yang,Xun Lin,Zitong Yu,Liepiao Zhang,Xin Liu,Hui Li,Xiaochen Yuan,Xiaochun Cao
机构: Great Bay University (大湾区大学); University of Science and Technology of China (中国科学技术大学); Dongguan Key Laboratory for Intelligence and Information Technology (东莞智能信息技术重点实验室); GRGBanking Equipment Co., Ltd. (广电运通设备有限公司); South China University of Technology (华南理工大学); Lappeenranta University of Technology (拉彭兰塔工业大学); Macao Polytechnic University (澳门城市大学); Shenzhen Campus of Sun Yat-sen University (中山大学深圳校区)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 18 pages, 9 figures

点击查看摘要

[CV-184] DashCop: Automated E-ticket Generation for Two-Wheeler Traffic Violations Using Dashcam Videos

链接: https://arxiv.org/abs/2503.00428
作者: Deepti Rawat,Keshav Gupta,Aryamaan Basu Roy,Ravi Kiran Sarvadevabhatla
机构: International Institute of Information Technology, Hyderabad, India (国际信息技术研究院，海得拉巴，印度)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-185] SGC-Net: Stratified Granular Comparison Network for Open-Vocabulary HOI Detection CVPR2025

链接: https://arxiv.org/abs/2503.00414
作者: Xin Lin,Chong Shi,Zuopeng Yang,Haojin Tang,Zhili Zhou
机构: Guangzhou University (广州大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025

点击查看摘要

[CV-186] CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering CVPR2025

链接: https://arxiv.org/abs/2503.00413
作者: Tianyu Huai,Jie Zhou,Xingjiao Wu,Qin Chen,Qingchun Bai,Ze Zhou,Liang He
机构: School of Computer Science and Technology, East China Normal University (华东师范大学计算机科学与技术学院); Shanghai Open University (上海开放大学), Shanghai, China; ZhuQingTing Data Technology (Zhejiang) Co., Ltd (浙江烛青亭数据科技有限公司)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 10 pages,4 figures,accepted by CVPR2025

点击查看摘要

[CV-187] High Dynamic Range Video Compression: A Large-Scale Benchmark Dataset and A Learned Bit-depth Scalable Compression Algorithm

链接: https://arxiv.org/abs/2503.00410
作者: Zhaoyi Tian,Feifeng Wang,Shiwei Wang,Zihao Zhou,Yao Zhu,Liquan Shen
机构: Shanghai University (上海大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-188] Inteval Analysis for two spherical functions arising from robust Perspective-n-Lines problem

链接: https://arxiv.org/abs/2503.00400
作者: Xiang Zheng,Haodong Jiang,Junfeng Wu
机构: School of Data Science (数据科学学院), The Chinese University of Hong Kong(SZ) (香港中文大学（深圳）)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-189] aming Large Multimodal Agents for Ultra-low Bitrate Semantically Disentangled Image Compression CVPR2025

链接: https://arxiv.org/abs/2503.00399
作者: Juan Song,Lijie Yang,Mingtao Feng
机构: School of Computer Science and Technology, Xidian University (计算机科学与技术学院, 西安电子科技大学); School of Artificial Intelligence, Xidian University (人工智能学院, 西安电子科技大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted to CVPR 2025

点击查看摘要

[CV-190] Floorplan-SLAM: A Real-Time High-Accuracy and Long-Term Multi-Session Point-Plane SLAM for Efficient Floorplan Reconstruction

链接: https://arxiv.org/abs/2503.00397
作者: Haolin Wang,Zeren Lv,Hao Wei,Haijiang Zhu,Yihong Wu
机构: State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences (中国科学院自动化研究所多模态人工智能系统国家重点实验室); School of Artificial Intelligence, University of Chinese Academy of Sciences (中国科学院大学人工智能学院); College of Information Science and Technology, Beijing University of Chemical Technology (北京化工大学信息科学与技术学院)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-191] BGM2Pose: Active 3D Human Pose Estimation with Non-Stationary Sounds

链接: https://arxiv.org/abs/2503.00389
作者: Yuto Shibata,Yusuke Oumi,Go Irie,Akisato Kimura,Yoshimitsu Aoki,Mariko Isogawa
机构: Keio University (庆应义塾大学); NTT Corporation (日本电气株式会社); Tokyo University of Science (东京理科大学); Keio University, JST Presto (庆应义塾大学, 科学技术振兴机构 Presto)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Sound (cs.SD); Audio and Speech Processing (eess.AS)
备注:

点击查看摘要

[CV-192] A Survey of Adversarial Defenses in Vision-based Systems: Categorization Methods and Challenges

链接: https://arxiv.org/abs/2503.00384
作者: Nandish Chattopadhyay,Abdul Basit,Bassem Ouni,Muhammad Shafique
机构: National Institute of Standards and Technology (国家标准与技术研究院); Department of Physics, Colorado State University (科罗拉多州立大学物理系); Electrical Engineering Department, University of Colorado (科罗拉多大学电气工程系)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-193] EigenActor: Variant Body-Object Interaction Generation Evolved from Invariant Action Basis Reasoning

链接: https://arxiv.org/abs/2503.00382
作者: Xuehao Gao,Yang Yang,Shaoyi Du,Yang Wu,Yebin Liu,Guo-Jun Qi
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-194] Adversarial Attacks on Event-Based Pedestrian Detectors: A Physical Approach AAAI2025

链接: https://arxiv.org/abs/2503.00377
作者: Guixu Lin,Muyao Niu,Qingtian Zhu,Zhengwei Yin,Zhuoxiao Li,Shengfeng He,Yinqiang Zheng
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by AAAI 2025

点击查看摘要

[CV-195] Few-shot crack image classification using clip based on bayesian optimization

链接: https://arxiv.org/abs/2503.00376
作者: Yingchao Zhang,Cheng Liu
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: 5 pages, 5 figures, 3 tables, submit to the 1st International Workshop on Bayesian Approach in Civil Engineering (IWOBA 2025)

点击查看摘要

[CV-196] MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention

链接: https://arxiv.org/abs/2503.00374
作者: Tianyi Wang,Jianan Fan,Dingxin Zhang,Dongnan Liu,Yong Xia,Heng Huang,Weidong Cai
机构: School of Computer Science, The University of Sydney (悉尼大学计算机学院), Australia; National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science and Engineering, Northwestern Polytechnical University (西北工业大学计算机科学与工程学院, 国家空天陆海大数据应用技术工程实验室), China; Department of Computer Science, University of Maryland (马里兰大学计算机科学系), USA
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 10 pages, 5 figures, 3 tables

点击查看摘要

[CV-197] Jointly Understand Your Command and Intention:Reciprocal Co-Evolution between Scene-Aware 3D Human Motion Synthesis and Analysis

链接: https://arxiv.org/abs/2503.00371
作者: Xuehao Gao,Yang Yang,Shaoyi Du,Guo-Jun Qi,Junwei Han
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-198] CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion

链接: https://arxiv.org/abs/2503.00364
作者: Yaowei Guo,Jiazheng Xing,Xiaojun Hou,Shuo Xin,Juntao Jiang,Demetri Terzopoulos,Chenfanfu Jiang,Yong Liu
机构: University of California, Los Angeles (加州大学洛杉矶分校); Zhejiang University (浙江大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-199] Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding

链接: https://arxiv.org/abs/2503.00361
作者: Wei Suo,Lijun Zhang,Mengyang Sun,Lin Yuanbo Wu,Peng Wang,Yanning Zhang
机构: School of Computer Science and Ningbo Institute, Northwestern Polytechnical University (西北工业大学), China; School of Cybersecurity, Northwestern Polytechnical University (西北工业大学), China; Computer Science, Swansea University (斯旺西大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-200] Solving Instance Detection from an Open-World Perspective CVPR2025

链接: https://arxiv.org/abs/2503.00359
作者: Qianqian Shen,Yunhan Zhao,Nahyun Kwon,Jeeeun Kim,Yanan Li,Shu Kong
机构: Zhejiang University (浙江大学); UC Irvine (加州大学欧文分校); Texas A&M University (德克萨斯农工大学); Zhejiang Lab (之江实验室); University of Macau (澳门大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at CVPR 2025

点击查看摘要

[CV-201] CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression ICLR

链接: https://arxiv.org/abs/2503.00357
作者: Yu-Ting Zhan,Cheng-Yuan Ho,Hebi Yang,Yi-Hsin Chen,Jui Chiu Chiang,Yu-Lun Liu,Wen-Hsiao Peng
机构: National Yang Ming Chiao Tung University (国立阳明交通大学), Taiwan; National Chung Cheng University (中正大学), Taiwan
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted for Publication in International Conference on Learning Representations (ICLR)

点击查看摘要

[CV-202] SHAZAM: Self-Supervised Change Monitoring for Hazard Detection and Mapping

链接: https://arxiv.org/abs/2503.00348
作者: Samuel Garske,Konrad Heidler,Bradley Evans,KC Wong,Xiao Xiang Zhu
机构: School of Aerospace, Mechanical, and Mechatronic Engineering, The University of Sydney, NSW 2006, Australia (悉尼大学航空航天、机械与机电工程学院); School of Environmental and Rural Science, The University of New England, Armidale, NSW 2350, Australia (新英格兰大学环境与农村科学学院); Australian Research Council (ARC) Training Centre for CubeSats, UAVs & Their Applications (CUAVA) (澳大利亚研究委员会立方星、无人机及其应用培训中心); Chair of Data Science in Earth Observation (SiPEO), Department of Aerospace and Geodesy, School of Engineering and Design and Munich Center for Machine Learning, Technical University of Munich (TUM), 80333 Munich, Germany (慕尼黑工业大学地球观测数据科学系、工程与设计学院及慕尼黑机器学习中心)
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注: 20 pages, 9 figures, 3 tables, code available at: this https URL

点击查看摘要

[CV-203] ABC: Achieving Better Control of Multimodal Embeddings using VLMs

链接: https://arxiv.org/abs/2503.00329
作者: Benjamin Schneider,Florian Kerschbaum,Wenhu Chen
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注:

点击查看摘要

[CV-204] CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leverag ing CVPR2025

链接: https://arxiv.org/abs/2503.00325
作者: Zhiwei Ling,Yachen Chang,Hailiang Zhao,Xinkui Zhao,Kingsum Chow,Shuiguang Deng
机构: Zhejiang University (浙江大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: This paper has been accepted by CVPR 2025

点击查看摘要

[CV-205] Abstract Rendering: Computing All Seen in Gaussian Splat Scenes

链接: https://arxiv.org/abs/2503.00308
作者: Yangge Li,Chenxi Ji,Xiangru Zhong,Huan Zhang,Sayan Mitra
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-206] Differential Coding for Training-Free ANN-to-SNN Conversion

链接: https://arxiv.org/abs/2503.00301
作者: Zihan Huang,Wei Fang,Tong Bu,Peng Xue,Zecheng Hao,Wenxuan Liu,Yuanhong Tang,Zhaofei Yu,Tiejun Huang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-207] Learning to Animate Images from A Few Videos to Portray Delicate Human Actions

链接: https://arxiv.org/abs/2503.00276
作者: Haoxin Li,Yingchen Yu,Qilong Wu,Hanwang Zhang,Boyang Li,Song Bai
机构: Nanyang Technological University (南洋理工大学); ByteDance (字节跳动); National University of Singapore (新加坡国立大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-208] Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality

链接: https://arxiv.org/abs/2503.00266
作者: Milad Yazdani,Yasamin Medghalchi,Pooria Ashrafian,Ilker Hacihaliloglu,Dena Shahriari
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-209] Seeing A 3D World in A Grain of Sand

链接: https://arxiv.org/abs/2503.00260
作者: Yufan Zhang,Yu Ji,Yu Guo,Jinwei Ye
机构: George Mason University (乔治梅森大学); LightThought LLC (LightThought LLC)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-210] Solar Multimodal Transformer: Intraday Solar Irradiance Predictor using Public Cameras and Time Series WACV2025

链接: https://arxiv.org/abs/2503.00250
作者: Yanan Niu,Roy Sarkis,Demetri Psaltis,Mario Paolone,Christophe Moser,Luisa Lambertini
机构: EPFL (瑞士联邦理工学院); Universita’ della Svizzera Italiana (USI) (意大利语大学)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: WACV2025

点击查看摘要

[CV-211] ransformers with Joint Tokens and Local-Global Attention for Efficient Human Pose Estimation

链接: https://arxiv.org/abs/2503.00232
作者: Kaleab A. Kinfu,René Vidal
机构: Center for Innovation in Data Engineering and Science, University of Pennsylvania (宾夕法尼亚大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: This work has been submitted to the IEEE for possible publication

点击查看摘要

[CV-212] Spiking Transformer:Introducing Accurate Addition-Only Spiking Self-Attention for Transformer CVPR2025

链接: https://arxiv.org/abs/2503.00226
作者: Yufei Guo,Xiaode Liu,Yuanpei Chen,Weihang Peng,Yuhan Zhang,Zhe Ma
机构: Intelligent Science & Technology Academy of CASIC (智能科学与技术中科院空天院), China
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR2025

点击查看摘要

[CV-213] Foundation-Model-Boosted Multimodal Learning for fMRI-based Neuropathic Pain Drug Response Prediction

链接: https://arxiv.org/abs/2503.00210
作者: Wenrui Fan,L. M. Riza Rizky,Jiayang Zhang,Chen Chen,Haiping Lu,Kevin Teh,Dinesh Selvarajah,Shuo Zhou
机构: 未知
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Signal Processing (eess.SP)
备注:

点击查看摘要

[CV-214] MIDAS: Mixing Ambiguous Data with Soft Labels for Dynamic Facial Expression Recognition WACV2024

链接: https://arxiv.org/abs/2503.00202
作者: Ryosuke Kawamura,Hideaki Hayashi,Noriko Takemura,Hajime Nagahara
机构: Fujitsu Research of America, Inc. (富士通研究北美研究所); Osaka University (大阪大学); Kyushu Institute of Technology (九州工业技术学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at WACV2024

点击查看摘要

[CV-215] Unified Video Action Model

链接: https://arxiv.org/abs/2503.00200
作者: Shuang Li,Yihuai Gao,Dorsa Sadigh,Shuran Song
机构: Stanford University (斯坦福大学)
类目: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
备注: Project website: this https URL

点击查看摘要

[CV-216] PRISM: High-Resolution Precise Counterfactual Medical Image Generation using Language-guided Stable Diffusion

链接: https://arxiv.org/abs/2503.00196
作者: Amar Kumar,Anita Kriz,Mohammad Havaei,Tal Arbel
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: Under Review for MIDL 2025

点击查看摘要

[CV-217] PaliGemma-CXR: A Multi-task Multimodal Model for TB Chest X-ray Interpretation

链接: https://arxiv.org/abs/2503.00171
作者: Denis Musinguzi,Andrew Katumba,Sudi Murindanyi
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-218] SSL4EO-S12 v1.1: A Multimodal Multiseasonal Dataset for Pretraining Updated

链接: https://arxiv.org/abs/2503.00168
作者: Benedikt Blumenstiel,Nassim Ait Ali Braham,Conrad M Albrecht,Stefano Maurogiovanni,Paolo Fraccaro
机构: IBM Research Europe; German Aerospace Center; Julich Supercomputing Centre (于利希超算中心)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-219] EVLoc: Event-based Visual Localization in LiDAR Maps via Event-Depth Registration

链接: https://arxiv.org/abs/2503.00167
作者: Kuangyi Chen,Jun Zhang,Friedrich Fraundorfer
机构: Institute of Visual Computing, Graz University of Technology (格拉茨技术大学视觉计算研究所); Graz University of Technology (格拉茨技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-220] Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalance CVPR2025

链接: https://arxiv.org/abs/2503.00147
作者: Sanchayan Santra,Vishal Chudasama,Pankaj Wasnik,Vineeth N. Balasubramanian
机构: Sony Research India (索尼印度研究院); Indian Institute of Technology Hyderabad (印度理工学院海得拉巴校区)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted at CVPR 2025

点击查看摘要

[CV-221] Conformal Risk Control for Semantic Uncertainty Quantification in Computed Tomography

链接: https://arxiv.org/abs/2503.00136
作者: Jacopo Teneggi,J Webster Stayman,Jeremias Sulam
机构: Johns Hopkins University (约翰·霍普金斯大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
备注:

点击查看摘要

[CV-222] CNSv2: Probabilistic Correspondence Encoded Neural Image Servo

链接: https://arxiv.org/abs/2503.00132
作者: Anzhe Chen,Hongxiang Yu,Shuxin Li,Yuxi Chen,Zhongxiang Zhou,Wentao Sun,Rong Xiong,Yue Wang
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-223] Unmanned Aerial Vehicle (UAV)-Based Mapping of Iris Pseudacorus L. Invasion in Laguna del Sauce (Uruguay) Coast

链接: https://arxiv.org/abs/2503.00122
作者: Alejo Silvarrey,Pablo Negri
机构: Departamento de Ingeniería (工程系), Universidad Católica del Uruguay (乌拉圭天主教大学); Instituto de Investigación en Ciencias de la Computación (ICC) (计算科学研究所), UBA-CONICET, Universidad de Buenos Aires (布宜诺斯艾利斯大学), FCEyN (经济与工商管理学院), Computer Department (计算机系), Buenos Aires, Argentina
类目: Computer Vision and Pattern Recognition (cs.CV); Emerging Technologies (cs.ET)
备注: 14 pages, 10 figures

点击查看摘要

[CV-224] Generalization of CNNs on Relational Reasoning with Bar Charts

链接: https://arxiv.org/abs/2503.00086
作者: Zhenxing Cui,Lu Chen,Yunhai Wang,Daniel Haehn,Yong Wang,Hanspeter Pfister
机构: School of Computer Science and Technology, Shandong University, China(山东大学计算机科学与技术学院); State Key Lab of CAD&CG, Zhejiang University, China(浙江大学CAD&CG国家重点实验室); School of Information, Renmin University of China, China(中国人民大学信息学院); College of Science and Mathematics, University of Massachusetts Boston, USA(美国波士顿大学理学院和数学学院); College of Computing and Data Science, Nanyang Technological University, Singapore(新加坡南洋理工大学计算与数据科学学院); School of Engineering and Applied Sciences, Harvard University, USA(哈佛大学工程与应用科学学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
备注: Accepted by TVCG. GitHub repository: this https URL

点击查看摘要

[CV-225] Forecasting Whole-Brain Neuronal Activity from Volumetric Video

链接: https://arxiv.org/abs/2503.00073
作者: Alexander Immer,Jan-Matthis Lueckmann,Alex Bo-Yuan Chen,Peter H. Li,Mariela D. Petkova,Nirmala A. Iyer,Aparna Dev,Gudrun Ihrke,Woohyun Park,Alyson Petruncio,Aubrey Weigel,Wyatt Korff,Florian Engert,Jeff W. Lichtman,Misha B. Ahrens,Viren Jain,Michał Januszewski
机构: Google Research; Harvard University; HHMI Janelia
类目: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC)
备注:

点击查看摘要

[CV-226] PI-HMR: Towards Robust In-bed Temporal Human Shape Reconstruction with Contact Pressure Sensing CVPR2025

链接: https://arxiv.org/abs/2503.00068
作者: Ziyu Wu,Yufan Xiong,Mengting Niu,Fangting Xie,Quan Wan,Qijun Ying,Boyan Liu,Xiaohui Cai
机构: University of Science and Technology of China (中国科学技术大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Emerging Technologies (cs.ET)
备注: Accepeted by CVPR2025 (submitted version)

点击查看摘要

[CV-227] NoPain: No-box Point Cloud Attack via Optimal Transport Singular Boundary

链接: https://arxiv.org/abs/2503.00063
作者: Zezeng Li,Xiaoyu Du,Na Lei,Liming Chen,Weimin Wang
机构: School of Software, Dalian University of Technology (大连理工大学软件学院); École Centrale de Lyon (里昂中央理工学院)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-228] SAC-ViT: Semantic-Aware Clustering Vision Transformer with Early Exit

链接: https://arxiv.org/abs/2503.00060
作者: Youbing Hu,Yun Cheng,Anqi Lu,Dawei Wei,Zhijun Li
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-229] Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models

链接: https://arxiv.org/abs/2503.00059
作者: Rui Hu,Delai Qiu,Shuyu Wei,Jiaming Zhang,Yining Wang,Shengping Liu,Jitao Sang
机构: Beijing Jiaotong University (北京交通大学); Unisound AI Technology Co., Ltd. (音智达人工智能科技有限公司)
类目: Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-230] African Gender Classification Using Clothing Identification Via Deep Learning

链接: https://arxiv.org/abs/2503.00058
作者: Samuel Ozechi
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注: 3 Pages, 10 Figures

点击查看摘要

[CV-231] Deciphering the complaint aspects: Towards an aspect-based complaint identification model with video complaint dataset in finance

链接: https://arxiv.org/abs/2503.00054
作者: Sarmistha Das,Basha Mujavarsheik,R E Zera Lyngkhoi,Sriparna Saha,Alka Maurya
机构: Indian Institute of Technology Patna (印度理工学院巴特那); Crisil Limited (克里希评级有限公司)
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-232] RURA-Net: A general disease diagnosis method based on Zero-Shot Learning MICCAI2025

链接: https://arxiv.org/abs/2503.00052
作者: Yan Su,Qiulin Wu,Weizhen Li,Chengchang Pan,Honggang Qi
机构: 未知
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
备注: 10 pages, 3 figures, 6 tables, submitted to The 28th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2025)

点击查看摘要

[CV-233] Correspondence-Free Pose Estimation with Patterns: A Unified Approach for Multi-Dimensional Vision

链接: https://arxiv.org/abs/2503.00051
作者: Quan Quan,Dun Dai
机构: School of Automation Science and Electrical Engineering, Beihang University (北京航空航天大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

[CV-234] Omni-SILA: Towards Omni-scene Driven Visual Sentiment Identifying Locating and Attributing in Videos

链接: https://arxiv.org/abs/2503.00049
作者: Jiamin Luo,Jingjing Wang,Junxiao Ma,Yujie Jin,Shoushan Li,Guodong Zhou
机构: School of Computer Science and Technology, Soochow University(Soochow University 计算机科学与技术学院)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-235] Leverag ing Large Models for Evaluating Novel Content: A Case Study on Advertisement Creativity

链接: https://arxiv.org/abs/2503.00046
作者: Zhaoyi Joey Hou,Adriana Kovashka,Xiang Lorraine Li
机构: University of Pittsburgh (匹兹堡大学)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
备注:

点击查看摘要

[CV-236] Advanced YOLO-based Real-time Power Line Detection for Vegetation Management

链接: https://arxiv.org/abs/2503.00044
作者: Shuaiang Rong,Lina He,Salih Furkan Atici,Ahmet Enis Cetin
机构: Electrical and Computer Engineering Department, University of Illinois at Chicago (UIUC)(电气与计算机工程系, 芝加哥伊利诺伊大学); Apple Inc. (苹果公司)
类目: Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)
备注: 13 pages. Revised version submitted to IEEE Transaction on Power Delivery

点击查看摘要

[CV-237] An Analysis of Segment Anything 2

链接: https://arxiv.org/abs/2503.00042
作者: Clayton Bromley,Alexander Moore,Amar Saini,Doug Poland,Carmen Carrano
机构: LLNL (Lawrence Livermore National Laboratory)
类目: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV)
备注: 19 pages, 30 figures

点击查看摘要

[CV-238] Memory-Free and Parallel Computation for Quantized Spiking Neural Networks

链接: https://arxiv.org/abs/2503.00040
作者: Dehao Zhang,Shuai Wang,Yichen Xiao,Wenjie Wei,Yimeng Shan,Malu Zhang,Yang Yang
机构: School of Computer Science and Engineering, University of Electronic Science and Technology of China (电子科技大学计算机科学与工程学院)
类目: Neural and Evolutionary Computing (cs.NE); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-239] M-SCAN: A Multistage Framework for Lumbar Spinal Canal Stenosis Grading Using Multi-View Cross Attention

链接: https://arxiv.org/abs/2503.01634
作者: Arnesh Batra,Arush Gumber,Anushk Kumar
机构: IIIT-Delhi (印度理工学院德里校区)
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-240] An Efficient Approach to Detecting Lung Nodules Using Swin Transformer

链接: https://arxiv.org/abs/2503.01592
作者: Saeed Shakuri,Alireza Rezvanian
机构: 未知
类目: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 19th Iranian Conference on Intelligent Systems (ICIS), IEEE, 2024

点击查看摘要

[CV-241] Lossy Neural Compression for Geospatial Analytics: A Review

链接: https://arxiv.org/abs/2503.01505
作者: Carlos Gomes,Isabelle Wittmann,Damien Robert,Johannes Jakubik,Tim Reichelt,Michele Martone,Stefano Maurogiovanni,Rikard Vinge,Jonas Hurst,Erik Scheurer,Rocco Sedona,Thomas Brunschwiler,Stefan Kesselheim,Matej Batic,Philip Stier,Jan Dirk Wegner,Gabriele Cavallaro,Edzer Pebesma,Michael Marszalek,Miguel A Belenguer-Plomer,Kennedy Adriko,Paolo Fraccaro,Romeo Kienzler,Rania Briq,Sabrina Benassou,Michele Lazzarini,Conrad M Albrecht
机构: IBM Research - Europe, Switzerland(IBM研究欧洲实验室，瑞士); University of Zurich, Switzerland(苏黎世大学，瑞士); IBM Research - Europe, Switzerland(IBM研究欧洲实验室，瑞士); University of Oxford, United Kingdom(牛津大学，英国); Forschungszentrum Jülich, Germany(德国于利希研究中心); University of Iceland, Iceland(冰岛大学，冰岛); German Aerospace Center, Germany(德国航空航天中心); University of Münster, Germany(明斯特大学，德国); Forschungszentrum Jülich, Germany(德国于利希研究中心); Forschungszentrum Jülich, Germany(德国于利希研究中心); IBM Research - Europe, Switzerland(IBM研究欧洲实验室，瑞士); Forschungszentrum Jülich, Germany(德国于利希研究中心); University of Oxford, United Kingdom(牛津大学，英国); Sinergise Solutions, Slovenia(斯洛文尼亚Sinergise解决方案公司); University of Münster, Germany(明斯特大学，德国); University of Zurich, Switzerland(苏黎世大学，瑞士); Forschungszentrum Jülich, Germany(德国于利希研究中心); University of Iceland, Iceland(冰岛大学，冰岛); European Union Satellite Centre, Spain(欧盟卫星中心，西班牙); Forschungszentrum Jülich, Germany(德国于利希研究中心); IBM Research - Europe, Switzerland(IBM研究欧洲实验室，瑞士); IBM Research - Europe, Switzerland(IBM研究欧洲实验室，瑞士); Forschungszentrum Jülich, Germany(德国于利希研究中心); European Union Satellite Centre, Spain(欧盟卫星中心，西班牙); German Aerospace Center, Germany(德国航空航天中心)
类目: ignal Processing (eess.SP); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Geophysics (physics.geo-ph)
备注: self-consistent review paper

点击查看摘要

[CV-242] S-R2D2: a spherical extension of the R2D2 deep neural network series paradigm for wide-field radio-interferometric imaging

链接: https://arxiv.org/abs/2503.01462
作者: A. Tajja,A. Aghabiglou,E. Tolley,J-P. Kneib,J-P. Thiran,Y. Wiaux
机构: EPFL, École Polytechnique Fédérale de Lausanne (瑞士联邦理工学院); Institute of Sensors, Signal, and Systems, Heriot-Watt University (传感器、信号与系统研究所，赫瑞瓦特大学)
类目: Instrumentation and Methods for Astrophysics (astro-ph.IM); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 16 pages, 13 figures

点击查看摘要

[CV-243] Hyperspectral image segmentation with a machine learning model trained using quantum annealer

链接: https://arxiv.org/abs/2503.01400
作者: Dawid Mazur,Tomasz Rybotycki,Piotr Gawron
机构: 未知
类目: Quantum Physics (quant-ph); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
备注: 16 pages, 6 figures, 3 tables

点击查看摘要

[CV-244] Diffusion-based Virtual Staining from Polarimetric Mueller Matrix Imaging

链接: https://arxiv.org/abs/2503.01352
作者: Xiaoyu Zheng,Jing Wen,Jiaxin Zhuang,Yao Du,Jing Cong,Limei Guo,Chao He,Lin Luo,Hao Chen
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-245] From Claims to Evidence: A Unified Framework and Critical Analysis of CNN vs. Transformer vs. Mamba in Medical Image Segmentation

链接: https://arxiv.org/abs/2503.01306
作者: Pooya Mohammadi Kazaj,Giovanni Baj,Yazdan Salimi,Anselm W. Stark,Waldo Valenzuela,George CM. Siontis,Habib Zaidi,Mauricio Reyes,Christoph Graeni,Isaac Shiri
机构: Department of Cardiology Inselspital Bern University Hospital University of Bern Bern Switzerland; Geneva University Hospital Division of Nuclear Medicine and Molecular Imaging CH-1211 Geneva Switzerland; University Institute for Diagnostic and Interventional Neuroradiology Inselspital Bern University Hospital University of Bern Freiburgstrasse 3010 Bern Switzerland; Department of Nuclear Medicine and Molecular Imaging University of Groningen University Medical Center Groningen Groningen Netherlands; Department of Nuclear Medicine University of Southern Denmark Odense Denmark; Department of Radiation Oncology University Hospital Bern University of Bern Bern Switzerland; Center for Artificial Intelligence in Medicine University of Bern Bern Switzerland; ARTORG Center for Biomedical Engineering Research University of Bern Bern Switzerland
类目: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Medical Physics (physics.med-ph)
备注:

点击查看摘要

[CV-246] Interactive Gadolinium-Free MRI Synthesis: A Transformer with Localization Prompt Learning

链接: https://arxiv.org/abs/2503.01265
作者: Linhao Li,Changhui Su,Yu Guo,Huimao Zhang,Dong Liang,Kun Shang
机构: School of Artificial Intelligence, Hebei University of Technology (河北工业大学人工智能学院); Department of Radiology, The First Hospital of Jilin University (吉林大学第一医院放射科); Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences (中国科学院深圳先进技术研究院医疗人工智能研究中心)
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-247] Automated Retinal Layer and Fluid Segmentation and Cross-sectional Analysis using Spectral Domain Optical Coherence Tomography Images for Diabetic Retinopathy

链接: https://arxiv.org/abs/2503.01248
作者: S. Chen,D. Ma,M. Raviselvan,S. Sundaramoorthy,K. Popuri,M. J. Ju,M. V. Sarunic,D. Ratra,M. F. Beg
机构: School of Engineering Science, Simon Fraser University (西蒙弗雷泽大学), Burnaby, BC, Canada; School of Medicine, Wake Forest University (维克森林大学), Winston-Salem, NC, United States; Sankara Nethralaya, Chennai, Tamil Nadu, India; Department of Ophthalmology & Visual Sciences, The University of British Columbia (不列颠哥伦比亚大学), Vancouver, BC, Canada; Institute of Ophthalmology, University College London (伦敦大学学院), London, United Kingdom; Department of Medical Physics and Biomedical Engineering, University College London (伦敦大学学院), London, United Kingdom; Memorial University of New Foundland (纽芬兰纪念大学), Department of Computer Science, St. Johns, Canada
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Tissues and Organs (q-bio.TO)
备注: 16 pages, 9 figures

点击查看摘要

[CV-248] ackling Hallucination from Conditional Models for Medical Image Reconstruction with DynamicDPS

链接: https://arxiv.org/abs/2503.01075
作者: Seunghoi Kim,Henry F. J. Tregidgo,Matteo Figini,Chen Jin,Sarang Joshi,Daniel C. Alexander
机构: 未知
类目: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-249] Cross Modality Medical Image Synthesis for Improving Liver Segmentation

链接: https://arxiv.org/abs/2503.00945
作者: Muhammad Rafiq,Hazrat Ali,Ghulam Mujtaba,Zubair Shah,Shoaib Azmat
机构: CUI Islamabad Campus (伊斯兰堡工程技术大学); COMSATS University Islamabad (真纳高等教育委员会); Hamad Bin Khalifa University (哈马德·本·哈利法大学)
类目: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: Submitted to Computer Methods in Biomechanics and Biomedical Engineering: Imaging Visualization

点击查看摘要

[CV-250] Patient-Level Anatomy Meets Scanning-Level Physics: Personalized Federated Low-Dose CT Denoising Empowered by Large Language Model CVPR2025

链接: https://arxiv.org/abs/2503.00908
作者: Ziyuan Yang,Yingyu Chen,Zhiwen Wang,Hongming Shan,Yang Chen,Yi Zhang
机构: College of Computer Science, Sichuan University (四川大学), China; Key Laboratory of Data Protection and Intelligent Management, Ministry of Education, Sichuan University (教育部数据保护与智能管理重点实验室, 四川大学), China; School of Cyber Science and Engineering, Sichuan University (四川大学网络空间安全学院), China; School of Computer Science and Software Engineering, Southwest Petroleum University (西南石油大学计算机科学与软件工程学院), China; Institute of Science and Technology for Brain-inspired Intelligence, Fudan University (复旦大学类脑智能科学技术研究所), China; School of Computer Science and Engineering, Southeast University (东南大学计算机科学与工程学院), China
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注: Accepted by CVPR 2025

点击查看摘要

[CV-251] NCF: Neural Correspondence Field for Medical Image Registration

链接: https://arxiv.org/abs/2503.00760
作者: Lei Zhou,Nimu Yuan,Katjana Ehrlich,Jinyi Qi
机构: University of California(加州大学)
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-252] Geodesic Diffusion Models for Medical Image-to-Image Generation

链接: https://arxiv.org/abs/2503.00745
作者: Teng Zhang,Hongxu Jiang,Kuang Gong,Wei Shao
机构: University of Florida (佛罗里达大学)
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-253] LesionDiffusion: Towards Text-controlled General Lesion Synthesis

链接: https://arxiv.org/abs/2503.00741
作者: Henrui Tian,Wenhui Lei,Linrui Dai,Hanyu Chen,Xiaofan Zhang
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注: 10 pages, 4 figures

点击查看摘要

[CV-254] Artificially Generated Visual Scanpath Improves Multi-label Thoracic Disease Classification in Chest X-Ray Images

链接: https://arxiv.org/abs/2503.00657
作者: Ashish Verma,Aupendu Kar,Krishnendu Ghosh,Sobhan Kanti Dhara,Debashis Sen,Prabir Kumar Biswas
机构: Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology Kharagpur (印度理工学院克勒格布尔); Department of Electronics and Communication Engineering, National Institute of Technology Rourkela (印度理工学院鲁尔克拉)
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注: Copyright 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

点击查看摘要

[CV-255] Cross-Attention Fusion of MRI and Jacobian Maps for Alzheimers Disease Diagnosis MICCAI2025

链接: https://arxiv.org/abs/2503.00586
作者: Shijia Zhang,Xiyu Ding,Brian Caffo,Junyu Chen,Cindy Zhang,Hadi Kharrazi,Zheyu Wang
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Quantitative Methods (q-bio.QM)
备注: Submitted to MICCAI 2025

点击查看摘要

[CV-256] NeuroSymAD: A Neuro-Symbolic Framework for Interpretable Alzheimers Disease Diagnosis

链接: https://arxiv.org/abs/2503.00510
作者: Yexiao He,Ziyao Wang,Yuning Zhang,Tingting Dan,Tianlong Chen,Guorong Wu,Ang Li
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-257] BELE: Blur Equivalent Linearized Estimator

链接: https://arxiv.org/abs/2503.00503
作者: Paolo Giannitrapani,Elio D. Di Claudio,Giovanni Jacovitti
机构: Dept. of Information Engineering, Electronics and Telecommunications (DIET), University of Rome “Sapienza” (罗马大学“Sapienza”)
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-258] AI-Augmented Thyroid Scintigraphy for Robust Classification

链接: https://arxiv.org/abs/2503.00366
作者: Maziar Sabouri,Ghasem Hajianfar,Alireza Rafiei Sardouei,Milad Yazdani,Azin Asadzadeh,Soroush Bagheri,Mohsen Arabi,Seyed Rasoul Zakavi,Emran Askari,Atena Aghaee,Dena Shahriari,Habib Zaidi,Arman Rahmim
机构: 未知
类目: Medical Physics (physics.med-ph); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-259] SegImgNet: Segmentation-Guided Dual-Branch Network for Retinal Disease Diagnoses

链接: https://arxiv.org/abs/2503.00267
作者: Xinwei Luo,Songlin Zhao,Yun Zong,Yong Chen,Gui-shuang Ying,Lifang He
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-260] Boundary-Emphasized Weight Maps for Distal Airway Segmentation

链接: https://arxiv.org/abs/2503.00242
作者: Ali Keshavarzi,Elsa Angelini
机构: 未知
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV)
备注:

点击查看摘要

[CV-261] EXACT-CT: EXplainable Analysis for Crohns and Tuberculosis using CT

链接: https://arxiv.org/abs/2503.00159
作者: Shashwat Gupta,Sarthak Gupta,Akshan Agrawal,Mahim Naaz,Rajanikanth Yadav,Priyanka Bagade
机构: 未知
类目: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
备注: 8 figures, 5 tables

点击查看摘要

[CV-262] Neural Posterior Estimation for Cataloging Astronomical Images with Spatially Varying Backgrounds and Point Spread Functions

链接: https://arxiv.org/abs/2503.00156
作者: Aakash Patel,Tianqing Zhang,Camille Avestruz,Jeffrey Regier, theLSST Dark Energy Science Collaboration
机构: Department of Electrical Engineering and Computer Science, University of Michigan (密歇根大学); Department of Physics and Astronomy and PITT PACC, University of Pittsburgh (匹兹堡大学); Department of Physics, University of Michigan (密歇根大学); Leinweber Center for Theoretical Physics, University of Michigan (密歇根大学); Department of Statistics, University of Michigan (密歇根大学); the LSST Dark Energy Science Collaboration (未知)
类目: Instrumentation and Methods for Astrophysics (astro-ph.IM); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Image and Video Processing (eess.IV); Applications (stat.AP)
备注:

点击查看摘要

[CV-263] PCE-GAN: A Generative Adversarial Network for Point Cloud Attribute Quality Enhancement based on Optimal Transport

链接: https://arxiv.org/abs/2503.00047
作者: Tian Guo,Hui Yuan,Qi Liu,Honglei Su,Raouf Hamzaoui,Sam Kwong
机构: School of Control Science and Engineering, Shandong University (山东大学控制科学与工程学院), Jinan 250061, China; Key Laboratory of Machine Intelligence and System Control, Ministry of Education (教育部机器智能与系统控制重点实验室), Ji’nan, 250061, China; School of Electronic Information, Qingdao University (青岛大学电子信息技术学院), Qingdao, 266071, China; School of Engineering and Sustainable Development, De Montfort University (德蒙福特大学工程与可持续发展学院), LE1 9BH Leicester, UK; Department of Computing and Decision Science, Lingnan University (岭南大学计算与决策科学系), Hong Kong
类目: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Signal Processing (eess.SP)
备注:

点击查看摘要

[CV-264] Observability Investigation for Rotational Calibration of (Global-pose aided) VIO under Straight Line Motion

链接: https://arxiv.org/abs/2503.00027
作者: Junlin Song,Antoine Richard,Miguel Olivares-Mendez
机构: Space Robotics (SpaceR) Research Group, Int. Centre for Security, Reliability and Trust (SnT), University of Luxembourg (卢森堡大学)
类目: ignal Processing (eess.SP); Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
备注:

点击查看摘要

人工智能

[AI-0] Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry

链接: https://arxiv.org/abs/2503.01822
作者: Sai Sumedh R. Hindupur,Ekdeep Singh Lubana,Thomas Fel,Demba Ba
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: Preprint

点击查看摘要

[AI-1] AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses

链接: https://arxiv.org/abs/2503.01811
作者: Nicholas Carlini,Javier Rando,Edoardo Debenedetti,Milad Nasr,Florian Tramèr
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-2] Generating Counterfactual Explanations Under Temporal Constraints

链接: https://arxiv.org/abs/2503.01792
作者: Andrei Buliga,Chiara Di Francescomarino,Chiara Ghidini,Marco Montali,Massimiliano Ronzani
类目: Artificial Intelligence (cs.AI)
*备注: 9 pages

点击查看摘要

[AI-3] Zero-Trust Artificial Intelligence Model Security Based on Moving Target Defense and Content Disarm and Reconstruction

链接: https://arxiv.org/abs/2503.01758
作者: Daniel Gilkarov,Ran Dubin
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-4] Position: Dont use the CLT in LLM evals with fewer than a few hundred datapoints

链接: https://arxiv.org/abs/2503.01747
作者: Sam Bowyer,Laurence Aitchison,Desi R. Ivanova
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 36 pages, 37 figures

点击查看摘要

[AI-5] Adversarial Agents : Black-Box Evasion Attacks with Reinforcement Learning

链接: https://arxiv.org/abs/2503.01734
作者: Kyle Domico,Jean-Charles Noirot Ferrand,Ryan Sheatsley,Eric Pauley,Josiah Hanna,Patrick McDaniel
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-6] Learning Exposure Mapping Functions for Inferring Heterogeneous Peer Effects

链接: https://arxiv.org/abs/2503.01722
作者: Shishir Adhikari,Sourav Medya,Elena Zheleva
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Social and Information Networks (cs.SI)
*备注:

点击查看摘要

[AI-7] SAGE: A Framework of Precise Retrieval for RAG

链接: https://arxiv.org/abs/2503.01713
作者: Jintao Zhang,Guoliang Li,Jinyang Su
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Databases (cs.DB); Information Retrieval (cs.IR)
*备注:

点击查看摘要

[AI-8] Spark-TTS: An Efficient LLM -Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens ACL2025

链接: https://arxiv.org/abs/2503.01710
作者: Xinsheng Wang,Mingqi Jiang,Ziyang Ma,Ziyu Zhang,Songxiang Liu,Linqin Li,Zheng Liang,Qixi Zheng,Rui Wang,Xiaoqin Feng,Weizhen Bian,Zhen Ye,Sitong Cheng,Ruibin Yuan,Zhixian Zhao,Xinfa Zhu,Jiahao Pan,Liumeng Xue,Pengcheng Zhu,Yunlin Chen,Zhifei Li,Xie Chen,Lei Xie,Yike Guo,Wei Xue
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS)
*备注: Submitted to ACL 2025

点击查看摘要

[AI-9] Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks AISTATS2025

链接: https://arxiv.org/abs/2503.01702
作者: Nandi Schoots,Mattia Jacopo Villani,Niels uit de Bos
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: accepted to AISTATS 2025; 12 pages including bibliography and appendix

点击查看摘要

[AI-10] Perceptual Motor Learning with Active Inference Framework for Robust Lateral Control IROS2025

链接: https://arxiv.org/abs/2503.01676
作者: Elahe Delavari,John Moore,Junho Hong,Jaerock Kwon
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
*备注: This work has been submitted to IROS 2025 and is currently under review

点击查看摘要

[AI-11] An Efficient Continual Learning Framework for Multivariate Time Series Prediction Tasks with Application to Vehicle State Estimation

链接: https://arxiv.org/abs/2503.01669
作者: Arvin Hosseinzadeh,Ladan Khoshnevisan,Mohammad Pirani,Shojaeddin Chenouri,Amir Khajepour
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-12] CoPL: Collaborative Preference Learning for Personalizing LLM s

链接: https://arxiv.org/abs/2503.01658
作者: Youngbin Choi,Seunghyuk Cho,Minjong Lee,MoonJeong Park,Yesong Ko,Jungseul Ok,Dongwoo Kim
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
*备注: 13pages, 4 figures, 6tables

点击查看摘要

[AI-13] Graph-Augmented Reasoning : Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning

链接: https://arxiv.org/abs/2503.01642
作者: Wenjie Wu,Yongcheng Jing,Yingjie Wang,Wenbin Hu,Dacheng Tao
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-14] CoT-VLM4Tar: Chain-of-Thought Guided Vision-Language Models for Traffic Anomaly Resolution

链接: https://arxiv.org/abs/2503.01632
作者: Tianchi Ren,Haibo Hu,Jiacheng Zuo,Xinhong Chen,Jianping Wang,Chun Jason Xue,Jen-Ming Wu,Nan Guan
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-15] Machine Learners Should Acknowledge the Legal Implications of Large Language Models as Personal Data

链接: https://arxiv.org/abs/2503.01630
作者: Henrik Nolte,Michèle Finck,Kristof Meding
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
*备注:

点击查看摘要

[AI-16] SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models

链接: https://arxiv.org/abs/2503.01584
作者: Cansu Sancaktar,Christian Gumbsch,Andrii Zadaianchuk,Pavel Kolev,Georg Martius
类目: Artificial Intelligence (cs.AI)
*备注: Preprint, under review. Project webpage at this https URL

点击查看摘要

[AI-17] A Selective Learning Method for Temporal Graph Continual Learning

链接: https://arxiv.org/abs/2503.01580
作者: Hanmo Liu,Shimin Di,Haoyang Li,Xun Jian,Yue Wang,Lei Chen
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-18] MoCFL: Mobile Cluster Federated Learning Framework for Highly Dynamic Network

链接: https://arxiv.org/abs/2503.01557
作者: Kai Fang,Jiangtao Deng,Chengzu Dong,Usman Naseem,Tongcun Liu,Hailin Feng,Wei Wang
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 10 pages, 7 figures, conference

点击查看摘要

[AI-19] Effective High-order Graph Representation Learning for Credit Card Fraud Detection IJCAI2024

链接: https://arxiv.org/abs/2503.01556
作者: Yao Zou,Dawei Cheng
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 9 pages, 5 figures, accepted at IJCAI 2024

点击查看摘要

[AI-20] Entailment vs. Verification for Partial-assignment Satisfiability and Enumeration

链接: https://arxiv.org/abs/2503.01536
作者: Roberto Sebastiani
类目: Logic in Computer Science (cs.LO); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-21] Enabling AI Scientists to Recognize Innovation: A Domain-Agnostic Algorithm for Assessing Novelty

链接: https://arxiv.org/abs/2503.01508
作者: Yao Wang,Mingxuan Cui,Arthur Jiang
类目: Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
*备注:

点击查看摘要

[AI-22] Compare different SG-Schemes based on large least square problems

链接: https://arxiv.org/abs/2503.01507
作者: Ramkrishna Acharya
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-23] ProRCA: A Causal Python Package for Actionable Root Cause Analysis in Real-world Business Scenarios

链接: https://arxiv.org/abs/2503.01475
作者: Ahmed Dawoud,Shravan Talupula
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-24] Position: Ensuring mutual privacy is necessary for effective external evaluation of proprietary AI systems

链接: https://arxiv.org/abs/2503.01470
作者: Ben Bucknall,Robert F. Trager,Michael A. Osborne
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
*备注:

点击查看摘要

[AI-25] SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning

链接: https://arxiv.org/abs/2503.01458
作者: Xu Wan,Chao Yang,Cheng Yang,Jie Song,Mingyang Sun
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
*备注:

点击查看摘要

[AI-26] POPGym Arcade: Parallel Pixelated POMDPs

链接: https://arxiv.org/abs/2503.01450
作者: Zekang Wang,Zhe He,Edan Toledo,Steven Morad
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO)
*备注:

点击查看摘要

[AI-27] Leverag ing LLM s for Mental Health: Detection and Recommendations from Social Discussions

链接: https://arxiv.org/abs/2503.01442
作者: Vaishali Aggarwal,Sachin Thukral,Krushil Patel,Arnab Chatterjee
类目: ocial and Information Networks (cs.SI); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
*备注: 5 pages, 4 figures, 3 tables, to be published in WI-IAT 2024

点击查看摘要

[AI-28] Eau De Q-Network: Adaptive Distillation of Neural Networks in Deep Reinforcement Learning

链接: https://arxiv.org/abs/2503.01437
作者: Théo Vincent,Tim Faust,Yogesh Tripathi,Jan Peters,Carlo D’Eramo
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: Accepted at RLDM

点击查看摘要

[AI-29] Building Interval Type-2 Fuzzy Membership Function: A Deck of Cards based Co-constructive Approach

链接: https://arxiv.org/abs/2503.01413
作者: Bapi Dutta,Diego García-Zamora,José Rui Figueira,Luis Martínez
类目: Artificial Intelligence (cs.AI); Optimization and Control (math.OC)
*备注:

点击查看摘要

[AI-30] Learning Actionable World Models for Industrial Process Control

链接: https://arxiv.org/abs/2503.01411
作者: Peng Yan,Ahmed Abdulkadir,Gerrit A. Schatte,Giulia Anguzzi,Joonsu Gha,Nikola Pascher,Matthias Rosenthal,Yunlong Gao,Benjamin F. Grewe,Thilo Stadelmann
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Systems and Control (eess.SY)
*备注:

点击查看摘要

[AI-31] Enhancing Social Media Rumor Detection: A Semantic and Graph Neural Network Approach for the 2024 Global Election

链接: https://arxiv.org/abs/2503.01394
作者: Liu Yan,Liu Yunpeng,Zhao Liang
类目: ocial and Information Networks (cs.SI); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-32] Learning Conjecturing from Scratch

链接: https://arxiv.org/abs/2503.01389
作者: Thibault Gauthier,Josef Urban
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Logic in Computer Science (cs.LO); Neural and Evolutionary Computing (cs.NE); Symbolic Computation (cs.SC)
*备注:

点击查看摘要

[AI-33] Combining Flow Matching and Transformers for Efficient Solution of Bayesian Inverse Problems

链接: https://arxiv.org/abs/2503.01375
作者: Daniil Sherki,Ivan Oseledets,Ekaterina Muravleva
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-34] Dendron: Enhancing Human Activity Recognition with On-Device TinyML Learning

链接: https://arxiv.org/abs/2503.01353
作者: Hazem Hesham Yousef Shalby,Manuel Roveri
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: Accepted to IEEE SSCI

点击查看摘要

[AI-35] Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning ICLR2025

链接: https://arxiv.org/abs/2503.01329
作者: Anh Tong,Thanh Nguyen-Tang,Dongeun Lee,Duc Nguyen,Toan Tran,David Hall,Cheongwoong Kang,Jaesik Choi
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: ICLR 2025

点击查看摘要

[AI-36] PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization

链接: https://arxiv.org/abs/2503.01328
作者: Xinyi Wan,Penghui Qi,Guangxing Huang,Jialin Li,Min Lin
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注:

点击查看摘要

[AI-37] Scaling Law Phenomena Across Regression Paradigms: Multiple and Kernel Approaches

链接: https://arxiv.org/abs/2503.01314
作者: Yifang Chen,Xuyang Guo,Xiaoyu Li,Yingyu Liang,Zhenmei Shi,Zhao Song
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
*备注:

点击查看摘要

[AI-38] ACTIVA: Amortized Causal Effect Estimation without Graphs via Transformer-based Variational Autoencoder

链接: https://arxiv.org/abs/2503.01290
作者: Andreas Sauter,Saber Salehkaleybar,Aske Plaat,Erman Acar
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-39] Robust Simulation-Based Inference under Missing Data via Neural Processes ICLR2025

链接: https://arxiv.org/abs/2503.01287
作者: Yogesh Verma,Ayush Bharti,Vikas Garg
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
*备注: Accepted at ICLR 2025

点击查看摘要

[AI-40] OptMetaOpenFOAM: Large Language Model Driven Chain of Thought for Sensitivity Analysis and Parameter Optimization based on CFD

链接: https://arxiv.org/abs/2503.01273
作者: Yuxuan Chen,Long Zhang,Xu Zhu,Hua Zhou,Zhuyin Ren
类目: Artificial Intelligence (cs.AI); Fluid Dynamics (physics.flu-dyn)
*备注: 26 pages,11 figures

点击查看摘要

[AI-41] Multi-Level Collaboration in Model Merging

链接: https://arxiv.org/abs/2503.01268
作者: Qi Li,Runpeng Yu,Xinchao Wang
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-42] Voice Cloning for Dysarthric Speech Synthesis: Addressing Data Scarcity in Speech-Language Pathology

链接: https://arxiv.org/abs/2503.01266
作者: Birger Moell,Fredrik Sand Aronsson
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS)
*备注:

点击查看摘要

[AI-43] A Taxonomy for Evaluating Generalist Robot Policies

链接: https://arxiv.org/abs/2503.01238
作者: Jensen Gao,Suneel Belkhale,Sudeep Dasari,Ashwin Balakrishna,Dhruv Shah,Dorsa Sadigh
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: 25 pages

点击查看摘要

[AI-44] LLM -Advisor: An LLM Benchmark for Cost-efficient Path Planning across Multiple Terrains

链接: https://arxiv.org/abs/2503.01236
作者: Ling Xiao,Toshihiko Yamasaki
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-45] Learning Covariance-Based Multi-Scale Representation of Neuroimaging Measures for Alzheimer Classification

链接: https://arxiv.org/abs/2503.01232
作者: Seunghun Baek,Injun Choi,Mustafa Dere,Minjeong Kim,Guorong Wu,Won Hwa Kim
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: ISBI 2023

点击查看摘要

[AI-46] Prognostics and Health Management of Wafer Chemical-Mechanical Polishing System using Autoencoder

链接: https://arxiv.org/abs/2503.01176
作者: Kart-Leong Lim,Rahul Dutta
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-47] STGAN: Spatial-temporal Graph Autoregression Network for Pavement Distress Deterioration Prediction

链接: https://arxiv.org/abs/2503.01152
作者: Shilin Tong,Difei Wu,Xiaona Liu,Le Zheng,Yuchuan Du,Difan Zou
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 16 pages, 16 figures, 4 tables, accepted by IEEE Transactions on Intelligent Transportation Systems (TITS)

点击查看摘要

[AI-48] Can Large Language Models Help Experimental Design for Causal Discovery?

链接: https://arxiv.org/abs/2503.01139
作者: Junyi Li,Yongqiang Chen,Chenxi Liu,Qianyi Cai,Tongliang Liu,Bo Han,Kun Zhang,Hui Xiong
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Methodology (stat.ME)
*备注:

点击查看摘要

[AI-49] Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs

链接: https://arxiv.org/abs/2503.01134
作者: Yuheng Zhang,Nan Jiang
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-50] Constrained multi-fidelity Bayesian optimization with automatic stop condition

链接: https://arxiv.org/abs/2503.01126
作者: Zahra Zanjani Foumani,Ramin Bostanabad
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[AI-51] Hybrid Metaheuristic Vehicle Routing Problem for Security Dispatch Operations

链接: https://arxiv.org/abs/2503.01121
作者: Nguyen Gia Hien Vu,Yifan Tang,Rey Lim,G. Gary Wang
类目: Artificial Intelligence (cs.AI); Discrete Mathematics (cs.DM); Optimization and Control (math.OC)
*备注:

点击查看摘要

[AI-52] Ground contact and reaction force sensing for linear policy control of quadruped robot

链接: https://arxiv.org/abs/2503.01102
作者: Harshita Mhaske,Aniket Mandhare,Jidong Huang,Yu Bai
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注: 5 pages, 11 figures

点击查看摘要

[AI-53] FAIR: Facilitating Artificial Intelligence Resilience in Manufacturing Industrial Internet

链接: https://arxiv.org/abs/2503.01086
作者: Yingyan Zeng,Ismini Lourentzou,Xinwei Deng,Ran Jin
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-54] Depth-Adaptive Graph Neural Networks via Learnable Bakry-Emery Curvature

链接: https://arxiv.org/abs/2503.01079
作者: Asela Hevapathige,Ahad N. Zehmakan,Qing Wang
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-55] Multi-Agent Reinforcement Learning with Long-Term Performance Objectives for Service Workforce Optimization

链接: https://arxiv.org/abs/2503.01069
作者: Kareem Eissa,Rayal Prasad,Sarith Mohan,Ankur Kapoor,Dorin Comaniciu,Vivek Singh
类目: Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
*备注:

点击查看摘要

[AI-56] Language-Guided Object Search in Agricultural Environments ICRA2025

链接: https://arxiv.org/abs/2503.01068
作者: Advaith Balaji,Saket Pradhan,Dmitry Berenson
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注: 8 pages, 4 figures, 2 tables, accepted to the 2025 International Conference on Robotics and Automation (ICRA 2025)

点击查看摘要

[AI-57] SFO: Piloting VLM Feedback for Offline RL

链接: https://arxiv.org/abs/2503.01062
作者: Jacob Beck
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: Code is provided at this https URL

点击查看摘要

[AI-58] An Exact Solver for Satisfiability Modulo Counting with Probabilistic Circuits

链接: https://arxiv.org/abs/2503.01009
作者: Jinzhao Li,Nan Jiang,Yexiang Xue
类目: Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO)
*备注:

点击查看摘要

[AI-59] Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks

链接: https://arxiv.org/abs/2503.00957
作者: Chang Liu,Haolin Wu,Xi Yang,Kui Zhang,Cong Wu,Weiming Zhang,Nenghai Yu,Tianwei Zhang,Qing Guo,Jie Zhang
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS)
*备注:

点击查看摘要

[AI-60] Can AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisions

链接: https://arxiv.org/abs/2503.00940
作者: Vijay Keswani,Vincent Conitzer,Walter Sinnott-Armstrong,Breanna K. Nguyen,Hoda Heidari,Jana Schaich Borg
类目: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
*备注: In ACM Conference on Human Factors in Computing Systems (CHI), 2025

点击查看摘要

[AI-61] Behavior Preference Regression for Offline Reinforcement Learning AAAI25

链接: https://arxiv.org/abs/2503.00930
作者: Padmanaba Srinivasan,William Knottenbelt
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: Conference paper at AAAI 25

点击查看摘要

[AI-62] S4M: S4 for multivariate time series forecasting with Missing values

链接: https://arxiv.org/abs/2503.00900
作者: Jing Peng,Meiqi Yang,Qiong Zhang,Xiaoxiao Li
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-63] CyberCScope: Mining Skewed Tensor Streams and Online Anomaly Detection in Cybersecurity Systems WWW2025

链接: https://arxiv.org/abs/2503.00871
作者: Kota Nakamura,Koki Kawabata,Shungo Tanaka,Yasuko Matsubara,Yasushi Sakurai
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
*备注: Accepted by WWW 2025 short research paper

点击查看摘要

[AI-64] NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains ICLR2025

链接: https://arxiv.org/abs/2503.00870
作者: Wonje Choi,Jinwoo Park,Sanghyun Ahn,Daehee Lee,Honguk Woo
类目: Artificial Intelligence (cs.AI)
*备注: Accepted at ICLR 2025

点击查看摘要

[AI-65] A Law Reasoning Benchmark for LLM with Tree-Organized Structures including Factum Probandum Evidence and Experiences

链接: https://arxiv.org/abs/2503.00841
作者: Jiaxin Shen,Jinan Xu,Huiqi Hu,Luyi Lin,Fei Zheng,Guoyang Ma,Fandong Meng,Jie Zhou,Wenjuan Han
类目: Artificial Intelligence (cs.AI)
*备注: 20 pages, 13 figures

点击查看摘要

[AI-66] owards Reliable LLM -Driven Fuzz Testing: Vision and Road Ahead

链接: https://arxiv.org/abs/2503.00795
作者: Yiran Cheng,Hong Jin Kang,Lwin Khin Shar,Chaopeng Dong,Zhiqiang Shi,Shichao Lv,Limin Sun
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-67] aming Infinity one Chunk at a Time: Concisely Represented Strategies in One-Counter MDPs

链接: https://arxiv.org/abs/2503.00788
作者: Michal Ajdarów,James C. A. Main,Petr Novotný,Mickael Randour
类目: Computer Science and Game Theory (cs.GT); Artificial Intelligence (cs.AI); Formal Languages and Automata Theory (cs.FL); Logic in Computer Science (cs.LO); Probability (math.PR)
*备注: 55 pages

点击查看摘要

[AI-68] Graph Attention Networks Unleashed: A Fast and Explainable Vulnerability Assessment Framework for Microgrids

链接: https://arxiv.org/abs/2503.00786
作者: Wei Liu,Tao Zhang,Chenhui Lin,Kaiwen Li,Rui Wang
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-69] FLOAT Drone: A Fully-actuated Coaxial Aerial Robot for Close-Proximity Operations

链接: https://arxiv.org/abs/2503.00785
作者: Junxiao Lin,Shuhang Ji,Yuze Wu,Tianyue Wu,Zhichao Han,Fei Gao
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注: 8 pages, 9 figures

点击查看摘要

[AI-70] owards Efficient Educational Chatbots: Benchmarking RAG Frameworks

链接: https://arxiv.org/abs/2503.00781
作者: Umar Ali Khan,Ekram Khan,Fiza Khan,Athar Ali Moinuddin
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-71] LLM s are everywhere: Ubiquitous Utilization of AI Models through Air Computing

链接: https://arxiv.org/abs/2503.00767
作者: Baris Yamansavascilar,Atay Ozgovde,Cem Ersoy
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI)
*备注: 7 pages, 5 figures

点击查看摘要

[AI-72] Rethinking Light Decoder-based Solvers for Vehicle Routing Problems ICLR2025

链接: https://arxiv.org/abs/2503.00753
作者: Ziwei Huang,Jianan Zhou,Zhiguang Cao,Yixin Xu
类目: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: Accepted at ICLR 2025

点击查看摘要

[AI-73] Edge Prompt Tuning for Graph Neural Networks ICLR2025

链接: https://arxiv.org/abs/2503.00750
作者: Xingbo Fu,Yinhan He,Jundong Li
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: Accepted by ICLR 2025

点击查看摘要

[AI-74] LADDER: Self-Improving LLM s Through Recursive Problem Decomposition

链接: https://arxiv.org/abs/2503.00735
作者: Toby Simonds,Akira Yoshiyama
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-75] CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments

链接: https://arxiv.org/abs/2503.00729
作者: Mingcong Lei,Ge Wang,Yiming Zhao,Zhixin Mai,Qing Zhao,Yao Guo,Zhen Li,Shuguang Cui,Yatong Han,Jinke Ren
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-76] From Understanding the World to Intervening in It: A Unified Multi-Scale Framework for Embodied Cognition

链接: https://arxiv.org/abs/2503.00727
作者: Maijunxian Wang
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Symbolic Computation (cs.SC)
*备注:

点击查看摘要

[AI-77] LLM DR: LLM -Driven Deadlock Detection and Resolution in Multi-Agent Pathfinding

链接: https://arxiv.org/abs/2503.00717
作者: Seungbae Seo,Junghwan Kim,Minjeong Shin,Bongwon Suh
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-78] Speculative Ad-hoc Querying

链接: https://arxiv.org/abs/2503.00714
作者: Haoyu Li,Srikanth Kandula,Maria Angels de Luis Balaguer,Aditya Akella,Venkat Arun
类目: Databases (cs.DB); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
*备注:

点击查看摘要

[AI-79] OpenECG: Benchmarking ECG Foundation Models with Public 1.2 Million Records

链接: https://arxiv.org/abs/2503.00711
作者: Zhijiang Wan,Qianhao Yu,Jia Mao,Wenfeng Duan,Cheng Ding
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-80] Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo

链接: https://arxiv.org/abs/2503.00699
作者: Hyunsu Kim,Giung Nam,Chulhee Yun,Hongseok Yang,Juho Lee
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
*备注:

点击查看摘要

[AI-81] GPIoT: Tailoring Small Language Models for IoT Program Synthesis and Development

链接: https://arxiv.org/abs/2503.00686
作者: Leming Shen,Qiang Yang,Xinyu Huang,Zijing Ma,Yuanqing Zheng
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-82] Factorized Deep Q-Network for Cooperative Multi-Agent Reinforcement Learning in Victim Tagging

链接: https://arxiv.org/abs/2503.00684
作者: Maria Ana Cardei,Afsaneh Doryab
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Robotics (cs.RO)
*备注: This work has been submitted to the IEEE for possible publication

点击查看摘要

[AI-83] OrdRankBen: A Novel Ranking Benchmark for Ordinal Relevance in NLP

链接: https://arxiv.org/abs/2503.00674
作者: Yan Wang,Lingfei Qian,Xueqing Peng,Jimin Huang,Dongji Feng
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
*备注: 6 pages

点击查看摘要

[AI-84] Generative Artificial Intelligence for Academic Research: Evidence from Guidance Issued for Researchers by Higher Education Institutions in the United States

链接: https://arxiv.org/abs/2503.00664
作者: Amrita Ganguly,Aditya Johri,Areej Ali,Nora McDonald
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-85] Efficiently Editing Mixture-of-Experts Models with Compressed Experts

链接: https://arxiv.org/abs/2503.00634
作者: Yifei He,Yang Liu,Chen Liang,Hany Hassan Awadalla
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-86] PinLanding: Content-First Keyword Landing Page Generation via Multi-Modal AI for Web-Scale Discovery

链接: https://arxiv.org/abs/2503.00619
作者: Faye Zhang,Jasmine Wan,Qianyu Cheng,Jinfeng Rao
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-87] Modeling Arbitrarily Applicable Relational Responding with the Non-Axiomatic Reasoning System: A Machine Psychology Approach

链接: https://arxiv.org/abs/2503.00611
作者: Robert Johansson
类目: Artificial Intelligence (cs.AI)
*备注: 5 figures, 1 table

点击查看摘要

[AI-88] Urban Safety Perception Through the Lens of Large Multimodal Models: A Persona-based Approach

链接: https://arxiv.org/abs/2503.00610
作者: Ciro Beneduce,Bruno Lepri,Massimiliano Luca
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-89] Space-Time Graphs of Convex Sets for Multi-Robot Motion Planning IROS’25

链接: https://arxiv.org/abs/2503.00583
作者: Jingtao Tang,Zining Mao,Lufan Yang,Hang Ma
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注: submitted to IROS’25

点击查看摘要

[AI-90] Brain Foundation Models: A Survey on Advancements in Neural Signal Processing and Brain Discovery

链接: https://arxiv.org/abs/2503.00580
作者: Xinliang Zhou,Chenyu Liu,Zhisheng Chen,Kun Wang,Yi Ding,Ziyu Jia,Qingsong Wen
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Signal Processing (eess.SP)
*备注:

点击查看摘要

[AI-91] A Guide to Failure in Machine Learning: Reliability and Robustness from Foundations to Practice

链接: https://arxiv.org/abs/2503.00563
作者: Eric Heim,Oren Wright,David Shriver
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-92] Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reason able

链接: https://arxiv.org/abs/2503.00555
作者: Tiansheng Huang,Sihao Hu,Fatih Ilhan,Selim Furkan Tekin,Zachary Yahn,Yichang Xu,Ling Liu
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-93] Distributionally Robust Reinforcement Learning with Human Feedback

链接: https://arxiv.org/abs/2503.00539
作者: Debmalya Mandal,Paulius Sasnauskas,Goran Radanovic
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-94] What Makes a Good Diffusion Planner for Decision Making? ICLR2025

链接: https://arxiv.org/abs/2503.00535
作者: Haofei Lu,Dongqi Han,Yifei Shen,Dongsheng Li
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: ICLR 2025 (Spotlight), Code: this https URL

点击查看摘要

[AI-95] Never too Prim to Swim: An LLM -Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions

链接: https://arxiv.org/abs/2503.00527
作者: Guanwen Xie,Jingzehua Xu,Yimian Ding,Zhi Zhang,Shuai Zhang,Yi Li
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注: 8 pages, 8 figures

点击查看摘要

[AI-96] End-To-End Learning of Gaussian Mixture Priors for Diffusion Sampler

链接: https://arxiv.org/abs/2503.00524
作者: Denis Blessing,Xiaogang Jia,Gerhard Neumann
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
*备注:

点击查看摘要

[AI-97] Functional multi-armed bandit and the best function identification problems

链接: https://arxiv.org/abs/2503.00509
作者: Yuriy Dorn,Aleksandr Katrutsa,Ilgam Latypov,Anastasiia Soboleva
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Optimization and Control (math.OC); Machine Learning (stat.ML)
*备注:

点击查看摘要

[AI-98] Interacting with AI Reasoning Models: Harnessing “Thoughts” for AI-Driven Software Engineering

链接: https://arxiv.org/abs/2503.00483
作者: Christoph Treude,Raula Gaikovina Kula
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
*备注:

点击查看摘要

[AI-99] Challenges in Testing Large Language Model Based Software: A Faceted Taxonomy

链接: https://arxiv.org/abs/2503.00481
作者: Felix Dobslaw,Robert Feldt,Juyeon Yoon,Shin Yoo
类目: oftware Engineering (cs.SE); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-100] Leverag ing Compute-in-Memory for Efficient Generative Model Inference in TPUs DATE2025

链接: https://arxiv.org/abs/2503.00461
作者: Zhantong Zhu,Hongou Li,Wenjie Ren,Meng Wu,Le Ye,Ru Huang,Tianyu Jia
类目: Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI)
*备注: Accepted to appear at DATE 2025

点击查看摘要

[AI-101] PodAgent : A Comprehensive Framework for Podcast Generation

链接: https://arxiv.org/abs/2503.00455
作者: Yujia Xiao,Lei He,Haohan Guo,Fenglong Xie,Tan Lee
类目: ound (cs.SD); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Multimedia (cs.MM); Audio and Speech Processing (eess.AS)
*备注:

点击查看摘要

[AI-102] Unveiling AIs Threats to Child Protection: Regulatory efforts to Criminalize AI-Generated CSAM and Emerging Childrens Rights Violations

链接: https://arxiv.org/abs/2503.00433
作者: Emmanouela Kokolaki,Paraskevi Fragopoulou
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-103] Language Model Mapping in Multimodal Music Learning: A Grand Challenge Proposal

链接: https://arxiv.org/abs/2503.00427
作者: Daniel Chin,Gus Xia
类目: ound (cs.SD); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-104] Auto-encoding Molecules: Graph-Matching Capabilities Matter

链接: https://arxiv.org/abs/2503.00426
作者: Magnus Cunow,Gerrit Großmann
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-105] Breaking the Loop: Detecting and Mitigating Denial-of-Service Vulnerabilities in Large Language Models

链接: https://arxiv.org/abs/2503.00416
作者: Junzhe Yu,Yi Liu,Huijia Sun,Ling Shi,Yuqi Chen
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Performance (cs.PF)
*备注:

点击查看摘要

[AI-106] Reservoir Network with Structural Plasticity for Human Activity Recognition

链接: https://arxiv.org/abs/2503.00393
作者: Abdullah M. Zyarah,Alaa M. Abdul-Hadi,Dhireesha Kudithipudi
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-107] Progressive Sparse Attention: Algorithm and System Co-design for Efficient Attention in LLM Serving

链接: https://arxiv.org/abs/2503.00392
作者: Qihui Zhou,Peiqi Yin,Pengfei Zuo,James Cheng
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: 12 pages, 6 figures

点击查看摘要

[AI-108] heoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems CVPR2025

链接: https://arxiv.org/abs/2503.00383
作者: Song Xia,Yi Yu,Wenhan Yang,Meiwen Ding,Zhuo Chen,Lingyu Duan,Alex C. Kot,Xudong Jiang
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
*备注: accepted by CVPR2025

点击查看摘要

[AI-109] Conditioning on Local Statistics for Scalable Heterogeneous Federated Learning

链接: https://arxiv.org/abs/2503.00378
作者: Rickard Brännvall
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注: 7 pages, 2 figures, 7 tables

点击查看摘要

[AI-110] Nucleolus Credit Assignment for Effective Coalitions in Multi-agent Reinforcement Learning

链接: https://arxiv.org/abs/2503.00372
作者: Yugu Li,Zehong Cao,Jianglin Qiao,Siyi Hu
类目: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-111] CRUPL: A Semi-Supervised Cyber Attack Detection with Consistency Regularization and Uncertainty-aware Pseudo-Labeling in Smart Grid

链接: https://arxiv.org/abs/2503.00358
作者: Smruti P. Dash,Kedar V. Khandeparkar,Nipun Agrawal
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: 20 pages, 5 figures

点击查看摘要

[AI-112] MCNet: Monotonic Calibration Networks for Expressive Uncertainty Calibration in Online Advertising WWW2025

链接: https://arxiv.org/abs/2503.00334
作者: Quanyu Dai,Jiaren Xiao,Zhaocheng Du,Jieming Zhu,Chengxiao Luo,Xiao-Ming Wu,Zhenhua Dong
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
*备注: Accepted by WWW2025

点击查看摘要

[AI-113] PINN-DT: Optimizing Energy Consumption in Smart Building Using Hybrid Physics-Informed Neural Networks and Digital Twin Framework with Blockchain Security

链接: https://arxiv.org/abs/2503.00331
作者: Hajar Kazemi Naeini,Roya Shomali,Abolhassan Pishahang,Hamidreza Hasanzadeh,Mahdieh Mohammadi,Saeid Asadi,Ahmad Gholizadeh Lonbar
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-114] FLStore: Efficient Federated Learning Storag e for non-training workloads

链接: https://arxiv.org/abs/2503.00323
作者: Ahmad Faraz Khan,Samuel Fountain,Ahmed M. Abdelmoniem,Ali R. Butt,Ali Anwar
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注: 11 pages, 19 figures, 2 tables This paper has been accepted at the The Eighth Annual Conference on Machine Learning and Systems (MLSys 2025)

点击查看摘要

[AI-115] -REX: A 68-567 μs/token 0.41-3.95 μJ/token Transformer Accelerator with Reduced External Memory Access and Enhanced Hardware Utilization in 16nm FinFET

链接: https://arxiv.org/abs/2503.00322
作者: Seunghyun Moon,Mao Li,Gregory Chen,Phil Knag,Ram Krishnamurthy,Mingoo Seok
类目: Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI)
*备注: Accepted to IEEE ISSCC 2025

点击查看摘要

[AI-116] Pseudo-Knowledge Graph: Meta-Path Guided Retrieval and In-Graph Text for RAG -Equipped LLM

链接: https://arxiv.org/abs/2503.00309
作者: Yuxin Yang,Haoyang Wu,Tao Wang,Jia Yang,Hao Ma,Guojie Luo
类目: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-117] Hidden Convexity of Fair PCA and Fast Solver via Eigenvalue Optimization

链接: https://arxiv.org/abs/2503.00299
作者: Junhui Shen,Aaron J. Davis,Ding Lu,Zhaojun Bai
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Optimization and Control (math.OC); Machine Learning (stat.ML)
*备注:

点击查看摘要

[AI-118] A Unified Framework for Heterogeneous Semi-supervised Learning

链接: https://arxiv.org/abs/2503.00286
作者: Marzi Heidari,Abdullah Alchihabi,Hao Yan,Yuhong Guo
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-119] Input Specific Neural Networks

链接: https://arxiv.org/abs/2503.00268
作者: Asghar A. Jadoon,D. Thomas Seidl,Reese E. Jones,Jan N. Fuhg
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Neural and Evolutionary Computing (cs.NE)
*备注:

点击查看摘要

[AI-120] Human-AI Collaboration: Trade-offs Between Performance and Preferences

链接: https://arxiv.org/abs/2503.00248
作者: Lukas William Mayer,Sheer Karny,Jackie Ayoub,Miao Song,Danyang Tian,Ehsan Moradi-Pari,Mark Steyvers
类目: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA)
*备注: LW Mayer S Karny are co-first authors

点击查看摘要

[AI-121] 1-Lipschitz Network Initialization for Certifiably Robust Classification Applications: A Decay Problem

链接: https://arxiv.org/abs/2503.00240
作者: Marius F. R. Juston,William R. Norris,Dustin Nottage,Ahmet Soylemezoglu
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
*备注: 12 pages, 8 figures

点击查看摘要

[AI-122] Agent ic AI Needs a Systems Theory

链接: https://arxiv.org/abs/2503.00237
作者: Erik Miehling,Karthikeyan Natesan Ramamurthy,Kush R. Varshney,Matthew Riemer,Djallel Bouneffouf,John T. Richards,Amit Dhurandhar,Elizabeth M. Daly,Michael Hind,Prasanna Sattigeri,Dennis Wei,Ambrish Rawat,Jasmina Gajcin,Werner Geyer
类目: Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-123] owards Fairness for the Right Reason s: Using Saliency Maps to Evaluate Bias Removal in Neural Networks

链接: https://arxiv.org/abs/2503.00234
作者: Lukasz Sztukiewicz,Ignacy Stępka,Michał Wiliński,Jerzy Stefanowski
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
*备注:

点击查看摘要

[AI-124] SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models

链接: https://arxiv.org/abs/2503.00211
作者: Jiawei Zhang,Xuan Yang,Taiqi Wang,Yu Yao,Aleksandr Petiushko,Bo Li
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-125] Quantifying First-Order Markov Violations in Noisy Reinforcement Learning: A Causal Discovery Approach

链接: https://arxiv.org/abs/2503.00206
作者: Naveen Mysore
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
*备注: Under review for RLC 2025

点击查看摘要

[AI-126] Learning Vision-Based Neural Network Controllers with Semi-Probabilistic Safety Guarantees IROS2025

链接: https://arxiv.org/abs/2503.00191
作者: Xinhang Ma,Junlin Wu,Hussein Sibai,Yiannis Kantaros,Yevgeniy Vorobeychik
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注: 6 pages, 2 figures, submitted to IROS 2025

点击查看摘要

[AI-127] Steering Large Language Model Activations in Sparse Spaces

链接: https://arxiv.org/abs/2503.00177
作者: Reza Bayat,Ali Rahimi-Kalahroudi,Mohammad Pezeshki,Sarath Chandar,Pascal Vincent
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-128] Fed-KAN: Federated Learning with Kolmogorov-Arnold Networks for Traffic Prediction

链接: https://arxiv.org/abs/2503.00154
作者: Engin Zeydan,Cristian J. Vaca-Rubio,Luis Blanco,Roberto Pereira,Marius Caus,Kapal Dev
类目: Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: This work has been submitted to the IEEE for possible publication

点击查看摘要

[AI-129] Learner and Instructor Needs in AI-Supported Programming Learning Tools: Design Implications for Features and Adaptive Control

链接: https://arxiv.org/abs/2503.00144
作者: Zihan Wu,Yicheng Tang,Barbara Ericson
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-130] Rethinking LLM Bias Probing Using Lessons from the Social Sciences

链接: https://arxiv.org/abs/2503.00093
作者: Kirsten N. Morehouse,Siddharth Swaroop,Weiwei Pan
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-131] EdgeAIGuard: Agent ic LLM s for Minor Protection in Digital Spaces

链接: https://arxiv.org/abs/2503.00092
作者: Ghulam Mujtaba,Sunder Ali Khowaja,Kapal Dev
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-132] Experiences with Content Development and Assessment Design in the Era of GenAI

链接: https://arxiv.org/abs/2503.00081
作者: Aakanksha Sharma,Samar Shailendra,Rajan Kadel
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-133] AI Literacy in K-12 and Higher Education in the Wake of Generative AI: An Integrative Review

链接: https://arxiv.org/abs/2503.00079
作者: Xingjian(Lance)Gu,Barbara J. Ericson
类目: Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
*备注: 29 pages, 7 figures

点击查看摘要

[AI-134] Navigating the Edge with the State-of-the-Art Insights into Corner Case Identification and Generation for Enhanced Autonomous Vehicle Safety

链接: https://arxiv.org/abs/2503.00077
作者: Gabriel Kenji Godoy Shimanuki,Alexandre Moreira Nascimento,Lucio Flavio Vismari,Joao Batista Camargo Junior,Jorge Rady de Almeida Junior,Paulo Sergio Cugnasca
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
*备注:

点击查看摘要

[AI-135] Systematic Review of Cybersecurity in Banking: Evolution from Pre-Industry 4.0 to Post-Industry 4.0 in Artificial Intelligence Blockchain Policies and Practice

链接: https://arxiv.org/abs/2503.00070
作者: Tue Nhi Tran
类目: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE)
*备注:

点击查看摘要

[AI-136] AI and Semantic Communication for Infrastructure Monitoring in 6G-Driven Drone Swarms

链接: https://arxiv.org/abs/2503.00053
作者: Tasnim Ahmed,Salimur Choudhury
类目: Robotics (cs.RO); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-137] MergeIT: From Selection to Merging for Efficient Instruction Tuning

链接: https://arxiv.org/abs/2503.00034
作者: Hongyi Cai,Yuqian Fu,Hongming Fu,Bo Zhao
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-138] Game-Theoretic Regularized Self-Play Alignment of Large Language Models

链接: https://arxiv.org/abs/2503.00030
作者: Xiaohang Tang,Sangwoong Yoon,Seongho Son,Huizhuo Yuan,Quanquan Gu,Ilija Bogunovic
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注: Preprint

点击查看摘要

[AI-139] Streaming Looking Ahead with Token-level Self-reward

链接: https://arxiv.org/abs/2503.00029
作者: Hongming Zhang,Ruixin Hong,Dong Yu
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-140] Genetics-Driven Personalized Disease Progression Model

链接: https://arxiv.org/abs/2503.00028
作者: Haoyu Yang,Sanjoy Dey,Pablo Meyer
类目: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-141] Dynamic spillovers and investment strategies across artificial intelligence ETFs artificial intelligence tokens and green markets

链接: https://arxiv.org/abs/2503.01148
作者: Ying-Hui Shao,Yan-Hong Yang,Wei-Xing Zhou
类目: Risk Management (q-fin.RM); Artificial Intelligence (cs.AI)
*备注: 21 pages, 8 figures

点击查看摘要

[AI-142] MAPS: Multi-Fidelity AI-Augmented Photonic Simulation and Inverse Design Infrastructure DATE2025

链接: https://arxiv.org/abs/2503.01046
作者: Pingchuan Ma,Zhengqi Gao,Meng Zhang,Haoyu Yang,Mark Ren,Rena Huang,Duane S. Boning,Jiaqi Gu
类目: Optics (physics.optics); Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET)
*备注: 6 pages. Accepted to DATE 2025

点击查看摘要

[AI-143] LLM -Fusion: A Novel Multimodal Fusion Model for Accelerated Material Discovery AAAI2025

链接: https://arxiv.org/abs/2503.01022
作者: Onur Boyar,Indra Priyadarsini,Seiji Takeda,Lisa Hamada
类目: Materials Science (cond-mat.mtrl-sci); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: 4 pages, presented at AAAI 2025 Workshop on AI to Accelerating Science and Engineering (AI2ASE)

点击查看摘要

[AI-144] AI Agents for Ground-Based Gamma Astronomy

链接: https://arxiv.org/abs/2503.00821
作者: D. Kostunin,V. Sotnikov,S. Golovachev,A. Strube
类目: Instrumentation and Methods for Astrophysics (astro-ph.IM); Artificial Intelligence (cs.AI)
*备注: proceedings of ADASS2025 (submitted), original talk and demos: this https URL

点击查看摘要

[AI-145] A physics-informed Bayesian optimization method for rapid development of electrical machines

链接: https://arxiv.org/abs/2503.00420
作者: Pedram Asef,Christopher Vagg
类目: ignal Processing (eess.SP); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Systems and Control (eess.SY); Optimization and Control (math.OC)
*备注:

点击查看摘要

[AI-146] LNUCB-TA: Linear-nonlinear Hybrid Bandit Learning with Temporal Attention

链接: https://arxiv.org/abs/2503.00387
作者: Hamed Khosravi,Mohammad Reza Shafie,Ahmed Shoyeb Raihan,Srinjoy Das,Imtiaz Ahmed
类目: Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注:

点击查看摘要

[AI-147] Investigating the contribution of terrain-following coordinates and conservation schemes in AI-driven precipitation forecasts

链接: https://arxiv.org/abs/2503.00332
作者: Yingkai Sha,John S. Schreck,William Chapman,David John Gagne II
类目: Atmospheric and Oceanic Physics (physics.ao-ph); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

[AI-148] Shifting Power: Leverag ing LLM s to Simulate Human Aversion in ABMs of Bilateral Financial Exchanges A bond market study

链接: https://arxiv.org/abs/2503.00320
作者: Alicia Vidler,Toby Walsh
类目: Trading and Market Microstructure (q-fin.TR); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
*备注: 9 pages

点击查看摘要

[AI-149] BixBench: a Comprehensive Benchmark for LLM -based Agents in Computational Biology

链接: https://arxiv.org/abs/2503.00096
作者: Ludovico Mitchener,Jon M Laurent,Benjamin Tenmann,Siddharth Narayanan,Geemi P Wellawatte,Andrew White,Lorenzo Sani,Samuel G Rodriques
类目: Quantitative Methods (q-bio.QM); Artificial Intelligence (cs.AI)
*备注: 8 main text pages, 5 main figures

点击查看摘要

[AI-150] Protein Structure Tokenization: Benchmarking and New Recipe

链接: https://arxiv.org/abs/2503.00089
作者: Xinyu Yuan,Zichen Wang,Marcus Collins,Huzefa Rangwala
类目: Quantitative Methods (q-bio.QM); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
*备注: Preprint

点击查看摘要

[AI-151] A Novel Spatiotemporal Correlation Anomaly Detection Method Based on Time-Frequency-Domain Feature Fusion and a Dynamic Graph Neural Network in Wireless Sensor Network

链接: https://arxiv.org/abs/2503.00036
作者: Miao Ye,Zhibang Jiang,Xingsi Xue,Xingwang Li,Peng Wen,Yong Wang
类目: ignal Processing (eess.SP); Artificial Intelligence (cs.AI)
*备注:

点击查看摘要

机器学习

[LG-0] When Can You Get Away with Low Memory Adam?

链接: https://arxiv.org/abs/2503.01843
作者: Dayal Singh Kalra,John Kirchenbauer,Maissam Barkeshli,Tom Goldstein
类目: Machine Learning (cs.LG); Disordered Systems and Neural Networks (cond-mat.dis-nn); Machine Learning (stat.ML)
*备注: 9+17 pages, 11+19 figures

点击查看摘要

[LG-1] GRAIN: Exact Graph Reconstruction from Gradients ICLR

链接: https://arxiv.org/abs/2503.01838
作者: Maria Drencheva,Ivo Petrov,Maximilian Baader,Dimitar I. Dimitrov,Martin Vechev
类目: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注: Published at The Thirteenth International Conference on Learning Representations (ICLR) 2025

点击查看摘要

[LG-2] Open-source framework for detecting bias and overfitting for large pathology images

链接: https://arxiv.org/abs/2503.01827
作者: Anders Sildnes,Nikita Shvetsov,Masoud Tafavvoghi,Vi Ngoc-Nha Tran,Kajsa Møllersen,Lill-Tove Rasmussen Busund,Thomas K. Kilvær,Lars Ailo Bongo
类目: Machine Learning (cs.LG); Software Engineering (cs.SE); Image and Video Processing (eess.IV)
*备注:

点击查看摘要

[LG-3] From superposition to sparse codes: interpretable representations in neural networks

链接: https://arxiv.org/abs/2503.01824
作者: David Klindt,Charles O’Neill,Patrik Reizinger,Harald Maurer,Nina Miolane
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-4] On the Power of Context-Enhanced Learning in LLM s

链接: https://arxiv.org/abs/2503.01821
作者: Xingyu Zhu,Abhishek Panigrahi,Sanjeev Arora
类目: Machine Learning (cs.LG)
*备注: 76 pages, 17 figures; Pre-print

点击查看摘要

[LG-5] Noise to the Rescue: Escaping Local Minima in Neurosymbolic Local Search

链接: https://arxiv.org/abs/2503.01817
作者: Alessandro Daniele,Emile van Krieken
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-6] Deep Reinforcement Learning-Based User Association in Hybrid LiFi/WiFi Indoor Networks

链接: https://arxiv.org/abs/2503.01803
作者: Peijun Hou,Nan Cen
类目: Machine Learning (cs.LG); Signal Processing (eess.SP)
*备注: 12 pages, 15 figures

点击查看摘要

[LG-7] PhishVQC: Optimizing Phishing URL Detection with Correlation Based Feature Selection and Variational Quantum Classifier

链接: https://arxiv.org/abs/2503.01799
作者: Md. Farhan Shahriyar,Gazi Tanbhir,Abdullah Md Raihan Chy,Mohammed Abdul Al Arafat Tanzin,Md. Jisan Mashrafi
类目: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
*备注: This paper has been accepted and presented at the 3rd International Conference on Intelligent Systems Advanced Computing and Communication (ISACC 2025)

点击查看摘要

[LG-8] m4: A Learned Flow-level Network Simulator

链接: https://arxiv.org/abs/2503.01770
作者: Chenning Li,Anton A. Zabreyko,Arash Nasr-Esfahany,Kevin Zhao,Prateesh Goyal,Mohammad Alizadeh,Thomas Anderson
类目: Networking and Internet Architecture (cs.NI); Machine Learning (cs.LG); Performance (cs.PF); Systems and Control (eess.SY)
*备注: 12 pages body, 15 pages total

点击查看摘要

[LG-9] Optimal Differentially Private Sampling of Unbounded Gaussians

链接: https://arxiv.org/abs/2503.01766
作者: Valentio Iverson,Gautam Kamath,Argyris Mouzakis
类目: Data Structures and Algorithms (cs.DS); Cryptography and Security (cs.CR); Information Theory (cs.IT); Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 47 pages

点击查看摘要

[LG-10] ECG-EmotionNet: Nested Mixture of Expert (NMoE) Adaptation of ECG-Foundation Model for Driver Emotion Recognition

链接: https://arxiv.org/abs/2503.01750
作者: Nastaran Mansourian,Arash Mohammadi,M. Omair Ahmad,M.N.S. Swamy
类目: Machine Learning (cs.LG); Signal Processing (eess.SP)
*备注:

点击查看摘要

[LG-11] Self-attention-based Diffusion Model for Time-series Imputation in Partial Blackout Scenarios AAAI2025

链接: https://arxiv.org/abs/2503.01737
作者: Mohammad Rafid Ul Islam,Prasad Tadepalli,Alan Fern
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 7 pages, 2 figures, 3 tables, Accepted in AAAI 2025 Main Track

点击查看摘要

[LG-12] DeepSuM: Deep Sufficient Modality Learning Framework

链接: https://arxiv.org/abs/2503.01728
作者: Zhe Gao,Jian Huang,Ting Li,Xueqin Wang
类目: Machine Learning (cs.LG); Methodology (stat.ME)
*备注:

点击查看摘要

[LG-13] Mamba base PKD for efficient knowledge compression

链接: https://arxiv.org/abs/2503.01727
作者: José Medina,Amnir Hadachi,Paul Honeine,Abdelaziz Bensrhair
类目: Machine Learning (cs.LG)
*备注: A preliminary version of this work was presented as a short poster titled “Mamba-PKD: A Framework for Efficient and Scalable Model Compression in Image Classification” at The 40th ACM/SIGAPP Symposium on Applied Computing this https URL

点击查看摘要

[LG-14] How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings ICLR2025

链接: https://arxiv.org/abs/2503.01723
作者: Nikolaos Nakis,Niels Raunkjær Holm,Andreas Lyhne Fiehn,Morten Mørup
类目: Machine Learning (cs.LG); Social and Information Networks (cs.SI)
*备注: Published as a conference paper at ICLR 2025

点击查看摘要

[LG-15] Quality Measures for Dynamic Graph Generative Models ICLR2025

链接: https://arxiv.org/abs/2503.01720
作者: Ryien Hosseini,Filippo Simini,Venkatram Vishwanath,Rebecca Willett,Henry Hoffmann
类目: Machine Learning (cs.LG)
*备注: To appear as a spotlight presentation at ICLR 2025

点击查看摘要

[LG-16] Learning Surrogate Equations for the Analysis of an Agent -Based Cancer Model

链接: https://arxiv.org/abs/2503.01718
作者: Kevin Burrage,Pamela Burrage,Justin N. Kreikemeyer,Adelinde M. Uhrmacher,Hasitha N. Weerasinghe
类目: Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
*备注: 15 pages, 6 figures

点击查看摘要

[LG-17] DILEMMA: Joint LLM Quantization and Distributed LLM Inference Over Edge Computing Systems

链接: https://arxiv.org/abs/2503.01704
作者: Minoo Hosseinzadeh,Hana Khamfroush
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-18] On the Development of Binary Classification Algorithm Based on Principles of Geometry and Statistical Inference

链接: https://arxiv.org/abs/2503.01703
作者: Vatsal Srivastava
类目: Machine Learning (cs.LG); Algebraic Geometry (math.AG)
*备注: 20 pages and some figures might give overfull warnings but compiled successfully and looks good so can be ignored

点击查看摘要

[LG-19] Regret Minimization for Piecewise Linear Rewards: Contracts Auctions and Beyond

链接: https://arxiv.org/abs/2503.01701
作者: Francesco Bacchiocchi,Matteo Castiglioni,Alberto Marchesi,Nicola Gatti
类目: Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-20] textscPerseus: Tracing the Masterminds Behind Cryptocurrency Pump-and-Dump Schemes

链接: https://arxiv.org/abs/2503.01686
作者: Honglin Fu,Yebo Feng,Cong Wu,Jiahua Xu
类目: Computers and Society (cs.CY); Machine Learning (cs.LG); Trading and Market Microstructure (q-fin.TR)
*备注:

点击查看摘要

[LG-21] GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models

链接: https://arxiv.org/abs/2503.01682
作者: Mufan Qiu,Xinyu Hu,Fengwei Zhan,Sukwon Yun,Jie Peng,Ruichen Zhang,Bhavya Kailkhura,Jiekun Yang,Tianlong Chen
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-22] Merging Hazy Sets with m-Schemes: A Geometric Approach to Data Visualization

链接: https://arxiv.org/abs/2503.01664
作者: Lukas Silvester Barth,Hannaneh Fahimi,Parvaneh Joharinad,Jürgen Jost,Janis Keck
类目: Machine Learning (cs.LG); Discrete Mathematics (cs.DM); Metric Geometry (math.MG)
*备注:

点击查看摘要

[LG-23] Non-convergence to the optimal risk for Adam and stochastic gradient descent optimization in the training of deep neural networks

链接: https://arxiv.org/abs/2503.01660
作者: Thang Do,Arnulf Jentzen,Adrian Riekert
类目: Machine Learning (cs.LG); Numerical Analysis (math.NA)
*备注: 42 pages

点击查看摘要

[LG-24] CAPS: Context-Aware Priority Sampling for Enhanced Imitation Learning in Autonomous Driving

链接: https://arxiv.org/abs/2503.01650
作者: Hamidreza Mirkhani,Behzad Khamidehi,Ehsan Ahmadi,Fazel Arasteh,Mohammed Elmahgiubi,Weize Zhang,Umar Rajguru,Kasra Rezaee
类目: Machine Learning (cs.LG); Robotics (cs.RO)
*备注:

点击查看摘要

[LG-25] Heterogeneity Matters even More in Distributed Learning: Study from Generalization Perspective

链接: https://arxiv.org/abs/2503.01598
作者: Masoud Kavian,Milad Sefidgaran,Abdellatif Zaidi,Romain Chor
类目: Machine Learning (cs.LG); Information Theory (cs.IT); Machine Learning (stat.ML)
*备注: 42 pages, 11 figures

点击查看摘要

[LG-26] Stability-based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning AAAI2025

链接: https://arxiv.org/abs/2503.01530
作者: Liang Wu,Ruixi Hu,Yunwen Lei
类目: Machine Learning (cs.LG)
*备注: To appear in AAAI 2025

点击查看摘要

[LG-27] R2VF: A Two-Step Regularization Algorithm to Cluster Categories in GLMs

链接: https://arxiv.org/abs/2503.01521
作者: Yuval Ben Dror
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-28] Whats Behind PPOs Collapse in Long-CoT? Value Optimization Holds the Secret

链接: https://arxiv.org/abs/2503.01491
作者: Yufeng Yuan,Yu Yue,Ruofei Zhu,Tiantian Fan,Lin Yan
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-29] InversionGNN: A Dual Path Network for Multi-Property Molecular Optimization ICLR2025

链接: https://arxiv.org/abs/2503.01488
作者: Yifan Niu,Ziqi Gao,Tingyang Xu,Yang Liu,Yatao Bian,Yu Rong,Junzhou Huang,Jia Li
类目: Machine Learning (cs.LG)
*备注: ICLR 2025

点击查看摘要

[LG-30] FlowDec: A flow-based full-band general audio codec with high perceptual quality ICLR2025

链接: https://arxiv.org/abs/2503.01485
作者: Simon Welker,Matthew Le,Ricky T. Q. Chen,Wei-Ning Hsu,Timo Gerkmann,Alexander Richard,Yi-Chiao Wu
类目: ound (cs.SD); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS); Signal Processing (eess.SP)
*备注: Accepted at ICLR 2025

点击查看摘要

[LG-31] KurTail : Kurtosis-based LLM Quantization

链接: https://arxiv.org/abs/2503.01483
作者: Mohammad Sadegh Akhondzadeh,Aleksandar Bojchevski,Evangelos Eleftheriou,Martino Dazzi
类目: Machine Learning (cs.LG)
*备注: 12 pages, 3 figures

点击查看摘要

[LG-32] Improving Plasticity in Non-stationary Reinforcement Learning with Evidential Proximal Policy Optimization

链接: https://arxiv.org/abs/2503.01468
作者: Abdullah Akgül,Gulcin Baykal,Manuel Haußmann,Melih Kandemir
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-33] Provably optimal decision trees with arbitrary splitting rules in polynomial time

链接: https://arxiv.org/abs/2503.01455
作者: Xi He,Max A. Little
类目: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS)
*备注:

点击查看摘要

[LG-34] rajectory-Class-Aware Multi-Agent Reinforcement Learning ICLR2025

链接: https://arxiv.org/abs/2503.01440
作者: Hyungho Na,Kwanghyeon Lee,Sumin Lee,Il-Chul Moon
类目: Machine Learning (cs.LG); Multiagent Systems (cs.MA)
*备注: Accepted at ICLR 2025

点击查看摘要

[LG-35] How simple can you go? An off-the-shelf transformer approach to molecular dynamics

链接: https://arxiv.org/abs/2503.01431
作者: Max Eissler,Tim Korjakow,Stefan Ganscha,Oliver T. Unke,Klaus-Robert Müller,Stefan Gugler
类目: Machine Learning (cs.LG)
*备注: 21 pages, code at this https URL

点击查看摘要

[LG-36] FABG : End-to-end Imitation Learning for Embodied Affective Human-Robot Interaction

链接: https://arxiv.org/abs/2503.01363
作者: Yanghai Zhang,Changyi Liu,Keting Fu,Wenbin Zhou,Qingdu Li,Jianwei Zhang
类目: Robotics (cs.RO); Machine Learning (cs.LG)
*备注: Project website: this https URL

点击查看摘要

[LG-37] DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models CVPR2025

链接: https://arxiv.org/abs/2503.01359
作者: Yongqi Huang,Peng Ye,Chenyu Huang,Jianjian Cao,Lin Zhang,Baopu Li,Gang Yu,Tao Chen
类目: Machine Learning (cs.LG)
*备注: Accepted by CVPR2025

点击查看摘要

[LG-38] MAB-Based Channel Scheduling for Asynchronous Federated Learning in Non-Stationary Environments

链接: https://arxiv.org/abs/2503.01324
作者: Zhiyin Li,Yubo Yang,Tao Yang,Xiaofeng Wu,Ziyu Guo,Bo Hu
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-39] Regularization-based Framework for Quantization- Fault- and Variability-Aware Training

链接: https://arxiv.org/abs/2503.01297
作者: Anmol Biswas,Raghav Singhal,Sivakumar Elangovan,Shreyas Sabnis,Udayan Ganguly
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-40] Stone Soup Multi-Target Tracking Feature Extraction For Autonomous Search And Track In Deep Reinforcement Learning Environment

链接: https://arxiv.org/abs/2503.01293
作者: Jan-Hendrik Ewers,Joe Gibbs,David Anderson
类目: Robotics (cs.RO); Machine Learning (cs.LG); Systems and Control (eess.SY)
*备注: Submitted to IEEE FUSION 2025

点击查看摘要

[LG-41] OIPR: Evaluation for Time-series Anomaly Detection Inspired by Operator Interest

链接: https://arxiv.org/abs/2503.01260
作者: Yuhan Jing,Jingyu Wang,Lei Zhang,Haifeng Sun,Bo He,Zirui Zhuang,Chengsen Wang,Qi Qi,Jianxin Liao
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-42] Prior-Fitted Networks Scale to Larger Datasets When Treated as Weak Learners AISTATS2025

链接: https://arxiv.org/abs/2503.01256
作者: Yuxin Wang,Botian Jiang,Yiran Guo,Quan Gan,David Wipf,Xuanjing Huang,Xipeng Qiu
类目: Machine Learning (cs.LG)
*备注: AISTATS 2025

点击查看摘要

[LG-43] A Survey On Large Language Models For Code Generation

链接: https://arxiv.org/abs/2503.01245
作者: Nam Huynh,Beiyu Lin
类目: oftware Engineering (cs.SE); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-44] Gaussian Process Surrogate Models for Efficient Estimation of Structural Response Distributions and Order Statistics

链接: https://arxiv.org/abs/2503.01242
作者: Vegard Flovik,Sebastian Winter,Christian Agrell
类目: Machine Learning (cs.LG); Computational Engineering, Finance, and Science (cs.CE)
*备注: Accepted for publication, journal reference will be added after publication

点击查看摘要

[LG-45] Enhancing Network Security Management in Water Systems using FM-based Attack Attribution

链接: https://arxiv.org/abs/2503.01229
作者: Aleksandar Avdalovic,Joseph Khoury,Ahmad Taha,Elias Bou-Harb
类目: Machine Learning (cs.LG); Cryptography and Security (cs.CR); Systems and Control (eess.SY)
*备注:

点击查看摘要

[LG-46] CE-U: Cross Entropy Unlearning

链接: https://arxiv.org/abs/2503.01224
作者: Bo Yang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-47] Architectural and Inferential Inductive Biases For Exchangeable Sequence Modeling

链接: https://arxiv.org/abs/2503.01215
作者: Daksh Mittal,Ang Li,Tzu-Ching Yen,Daniel Guetta,Hongseok Namkoong
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 35 Pages, 20 Figures

点击查看摘要

[LG-48] Hypergraph Foundation Model

链接: https://arxiv.org/abs/2503.01203
作者: Yifan Feng,Shiquan Liu,Xiangmin Han,Shaoyi Du,Zongze Wu,Han Hu,Yue Gao
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-49] Differentiable Information Enhanced Model-Based Reinforcement Learning AAAI2025

链接: https://arxiv.org/abs/2503.01178
作者: Xiaoyuan Zhang,Xinyan Cai,Bo Liu,Weidong Huang,Song-Chun Zhu,Siyuan Qi,Yaodong Yang
类目: Machine Learning (cs.LG); Robotics (cs.RO)
*备注: Accepted by AAAI 2025

点击查看摘要

[LG-50] Unify and Anchor: A Context-Aware Transformer for Cross-Domain Time Series Forecasting

链接: https://arxiv.org/abs/2503.01157
作者: Xiaobin Hong,Jiawen Zhang,Wenzhong Li,Sanglu Lu,Jia Li
类目: Machine Learning (cs.LG)
*备注: 20 pages, 12 figures, 8 tables, conference under review

点击查看摘要

[LG-51] CoInD: Enabling Logical Compositions in Diffusion Models

链接: https://arxiv.org/abs/2503.01145
作者: Sachit Gaudi,Gautam Sreekumar,Vishnu Boddeti
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-52] DPR: Diffusion Preference-based Reward for Offline Reinforcement Learning

链接: https://arxiv.org/abs/2503.01143
作者: Teng Pang,Bingzheng Wang,Guoqiang Wu,Yilong Yin
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-53] DDEQs: Distributional Deep Equilibrium Models through Wasserstein Gradient Flows AISTATS2025

链接: https://arxiv.org/abs/2503.01140
作者: Jonathan Geuter,Clément Bonet,Anna Korba,David Alvarez-Melis
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 39 pages, 17 figures. To be published in AISTATS 2025

点击查看摘要

[LG-54] Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear Programming

链接: https://arxiv.org/abs/2503.01129
作者: Haoyang Liu,Jie Wang,Zijie Geng,Xijun Li,Yuxuan Zong,Fangzhou Zhu,Jianye Hao,Feng Wu
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-55] Measuring the Validity of Clustering Validation Datasets

链接: https://arxiv.org/abs/2503.01097
作者: Hyeon Jeon,Michaël Aupetit,DongHwa Shin,Aeri Cho,Seokhyeon Park,Jinwook Seo
类目: Machine Learning (cs.LG)
*备注: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

点击查看摘要

[LG-56] Active Learning for Direct Preference Optimization

链接: https://arxiv.org/abs/2503.01076
作者: Branislav Kveton,Xintong Li,Julian McAuley,Ryan Rossi,Jingbo Shang,Junda Wu,Tong Yu
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-57] All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning

链接: https://arxiv.org/abs/2503.01067
作者: Gokul Swamy,Sanjiban Choudhury,Wen Sun,Zhiwei Steven Wu,J. Andrew Bagnell
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-58] ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Parity LLM Data Valuation NAACL2025

链接: https://arxiv.org/abs/2503.01052
作者: Yanzhou Pan,Huawei Lin,Yide Ran,Jiamin Chen,Xiaodong Yu,Weijie Zhao,Denghui Zhang,Zhaozhuo Xu
类目: Machine Learning (cs.LG)
*备注: Accepted to NAACL 2025. Keywords: Influence Function, Data Valuation, Influence Estimation

点击查看摘要

[LG-59] Personalize Your LLM : Fake it then Align it

链接: https://arxiv.org/abs/2503.01048
作者: Yijing Zhang,Dyah Adila,Changho Shin,Frederic Sala
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-60] Data Unlearning in Diffusion Models ICLR2025

链接: https://arxiv.org/abs/2503.01034
作者: Silas Alberti,Kenan Hasanaliyev,Manav Shah,Stefano Ermon
类目: Machine Learning (cs.LG)
*备注: ICLR 2025

点击查看摘要

[LG-61] Explainable Multi-modal Time Series Prediction with LLM -in-the-Loop

链接: https://arxiv.org/abs/2503.01013
作者: Yushan Jiang,Wenchao Yu,Geon Lee,Dongjin Song,Kijung Shin,Wei Cheng,Yanchi Liu,Haifeng Chen
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-62] Underdamped Diffusion Bridges with Applications to Sampling

链接: https://arxiv.org/abs/2503.01006
作者: Denis Blessing,Julius Berner,Lorenz Richter,Gerhard Neumann
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-63] Machine Learning for Health symposium 2024 – Findings track

链接: https://arxiv.org/abs/2503.00984
作者: Stefan Hegselmann,Helen Zhou,Elizabeth Healey,Trenton Chang,Caleb Ellington,Vishwali Mhasawade,Sana Tonekaboni,Peniel Argaw,Haoran Zhang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-64] Molecule Generation for Target Protein Binding with Hierarchical Consistency Diffusion Model

链接: https://arxiv.org/abs/2503.00975
作者: Guanlue Li,Chenran Jiang,Ziqi Gao,Yu Liu,Chenyang Liu,Jiean Chen,Yong Huang,Jia Li
类目: Machine Learning (cs.LG)
*备注: 24 pages, 5 figures, 2 tables

点击查看摘要

[LG-65] CAGN-GAT Fusion: A Hybrid Contrastive Attentive Graph Neural Network for Network Intrusion Detection

链接: https://arxiv.org/abs/2503.00961
作者: Md Abrar Jahin,Shahriar Soudeep,M. F. Mridha,Raihan Kabir,Md Rashedul Islam,Yutaka Watanobe
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-66] Learning-Augmented Frequent Directions

链接: https://arxiv.org/abs/2503.00937
作者: Anders Aamand,Justin Y. Chen,Siddharth Gollapudi,Sandeep Silwal,Hao Wu
类目: Machine Learning (cs.LG); Data Structures and Algorithms (cs.DS)
*备注:

点击查看摘要

[LG-67] Parameter-Adaptive Dynamic Pricing

链接: https://arxiv.org/abs/2503.00929
作者: Xueping Gong,Jiheng Zhang
类目: Machine Learning (cs.LG)
*备注: 44 pages

点击查看摘要

[LG-68] AMUN: Adversarial Machine UNlearning

链接: https://arxiv.org/abs/2503.00917
作者: Ali Ebrahimpour-Boroojeny,Hari Sundaram,Varun Chandrasekaran
类目: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
*备注:

点击查看摘要

[LG-69] Riemannian Integrated Gradients: A Geometric View of Explainable AI

链接: https://arxiv.org/abs/2503.00892
作者: Federico Costanza,Lachlan Simpson
类目: Machine Learning (cs.LG); Differential Geometry (math.DG)
*备注:

点击查看摘要

[LG-70] Re-Evaluating the Impact of Unseen-Class Unlabeled Data on Semi-Supervised Learning Model ICLR2025

链接: https://arxiv.org/abs/2503.00884
作者: Rundong He,Yicong Dong,Lanzhe Guo,Yilong Yin,Tailin Wu
类目: Machine Learning (cs.LG)
*备注: Published as a conference paper at ICLR 2025

点击查看摘要

[LG-71] Patch-wise Structural Loss for Time Series Forecasting

链接: https://arxiv.org/abs/2503.00877
作者: Dilfira Kudrat,Zongxia Xie,Yanru Sun,Tianyu Jia,Qinghua Hu
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-72] Improve Representation for Imbalanced Regression through Geometric Constraints CVPR2025

链接: https://arxiv.org/abs/2503.00876
作者: Zijian Dong,Yilei Wu,Chongyao Chen,Yingtian Zou,Yichi Zhang,Juan Helen Zhou
类目: Machine Learning (cs.LG)
*备注: CVPR 2025. The first three authors contributed equally

点击查看摘要

[LG-73] Systematic Literature Review on Clinical Trial Eligibility Matching

链接: https://arxiv.org/abs/2503.00863
作者: Muhammad Talha Sharif,Abdul Rehman
类目: Machine Learning (cs.LG); Information Retrieval (cs.IR)
*备注:

点击查看摘要

[LG-74] Hierarchical graph sampling based minibatch learning with chain preservation and variance reduction

链接: https://arxiv.org/abs/2503.00860
作者: Qia Hu,Bo Jiao
类目: Machine Learning (cs.LG)
*备注: 26 pages, 9 figures

点击查看摘要

[LG-75] FACROC: a fairness measure for FAir Clustering through ROC curves PAKDD2025

链接: https://arxiv.org/abs/2503.00854
作者: Tai Le Quy,Long Le Thanh,Lan Luong Thi Hong,Frank Hopfgartner
类目: Machine Learning (cs.LG)
*备注: Accepted to Special Session: Data Science: Foundations and Applications (DSFA), PAKDD 2025

点击查看摘要

[LG-76] A Transfer Framework for Enhancing Temporal Graph Learning in Data-Scarce Settings SIGIR

链接: https://arxiv.org/abs/2503.00852
作者: Shubham Gupta,Srikanta Bedathur
类目: Machine Learning (cs.LG); Information Theory (cs.IT)
*备注: under review in SIGIR conference

点击查看摘要

[LG-77] oward Stable and Consistent Evaluation Results: A New Methodology for Base Model Evaluation

链接: https://arxiv.org/abs/2503.00812
作者: Hongzhi Luan,Changxin Tian,Zhaoxin Huan,Xiaolu Zhang,Kunlong Chen,Zhiqiang Zhang,Jun Zhou
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-78] Minimax Optimal Reinforcement Learning with Quasi-Optimism ICLR2025

链接: https://arxiv.org/abs/2503.00810
作者: Harin Lee,Min-hwan Oh
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: 48 pages, ICLR 2025 camera ready version

点击查看摘要

[LG-79] On Generalization Across Environments In Multi-Objective Reinforcement Learning ICLR2025

链接: https://arxiv.org/abs/2503.00799
作者: Jayden Teoh,Pradeep Varakantham,Peter Vamplew
类目: Machine Learning (cs.LG)
*备注: Published at The Thirteenth International Conference on Learning Representations (ICLR 2025)

点击查看摘要

[LG-80] Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks

链接: https://arxiv.org/abs/2503.00755
作者: Anas Jnini,Lorenzo Breschi,Flavio Vella
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-81] Re-Imagining Multimodal Instruction Tuning: A Representation View

链接: https://arxiv.org/abs/2503.00723
作者: Yiyang Liu,James Chenhao Liang,Ruixiang Tang,Yugyung Lee,Majid Rabbani,Sohail Dianat,Raghuveer Rao,Lifu Huang,Dongfang Liu,Qifan Wang,Cheng Han
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-82] Proteina: Scaling Flow-based Protein Structure Generative Models ICLR2025

链接: https://arxiv.org/abs/2503.00710
作者: Tomas Geffner,Kieran Didi,Zuobai Zhang,Danny Reidenbach,Zhonglin Cao,Jason Yim,Mario Geiger,Christian Dallago,Emine Kucukbenli,Arash Vahdat,Karsten Kreis
类目: Machine Learning (cs.LG)
*备注: ICLR 2025 Oral. Project page: this https URL

点击查看摘要

[LG-83] ransformer Meets Twicing: Harnessing Unattended Residual Information

链接: https://arxiv.org/abs/2503.00687
作者: Laziz Abdullaev,Tan Nguyen
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-84] owards Refining Developer Questions using LLM -Based Named Entity Recognition for Developer Chatroom Conversations

链接: https://arxiv.org/abs/2503.00673
作者: Pouya Fathollahzadeh,Mariam El Mezouar,Hao Li,Ying Zou,Ahmed E. Hassan
类目: oftware Engineering (cs.SE); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-85] he Role Trends and Applications of Machine Learning in Undersea Communication: A Bangladesh Perspective

链接: https://arxiv.org/abs/2503.00669
作者: Yousuf Islam,Sumon Chandra Das,Md. Jalal Uddin Chowdhury
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-86] Discrete Codebook World Models for Continuous Control ICLR2025

链接: https://arxiv.org/abs/2503.00653
作者: Aidan Scannell,Mohammadreza Nakhaei,Kalle Kujanpää,Yi Zhao,Kevin Sebastian Luck,Arno Solin,Joni Pajarinen
类目: Machine Learning (cs.LG)
*备注: 38 pages, 21 figures, published in The Thirteenth International Conference on Learning Representations, ICLR 2025

点击查看摘要

[LG-87] he Hidden Cost of Waiting for Accurate Predictions ICLR2025

链接: https://arxiv.org/abs/2503.00650
作者: Ali Shirali,Ariel Procaccia,Rediet Abebe
类目: Machine Learning (cs.LG); Theoretical Economics (econ.TH)
*备注: Published as a conference paper at ICLR 2025 (Oral Presentation)

点击查看摘要

[LG-88] Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning

链接: https://arxiv.org/abs/2503.00639
作者: Zijian Li,Shunxing Fan,Yujia Zheng,Ignavier Ng,Shaoan Xie,Guangyi Chen,Xinshuai Dong,Ruichu Cai,Kun Zhang
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-89] Learning Automata of PLCs in Production Lines Using LSTM

链接: https://arxiv.org/abs/2503.00631
作者: Iyas AlTalafha,Yaprak Yalcin,Gulcihan Ozdemir
类目: Machine Learning (cs.LG); Systems and Control (eess.SY)
*备注: 6 pages, 7 figures, 1 table, 15 references

点击查看摘要

[LG-90] Dissecting the Impact of Model Misspecification in Data-Driven Optimization

链接: https://arxiv.org/abs/2503.00626
作者: Adam N. Elmachtoub,Henry Lam,Haixiang Lan,Haofeng Zhang
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-91] Large Engagement Networks for Classifying Coordinated Campaigns and Organic Twitter Trends

链接: https://arxiv.org/abs/2503.00599
作者: Atul Anand Gopalakrishnan,Jakir Hossain,Tugrulcan Elmas,Ahmet Erdem Sariyuce
类目: ocial and Information Networks (cs.SI); Machine Learning (cs.LG)
*备注: 14 Pages

点击查看摘要

[LG-92] SolidMark: Evaluating Image Memorization in Generative Models

链接: https://arxiv.org/abs/2503.00592
作者: Nicky Kriplani,Minh Pham,Gowthami Somepalli,Chinmay Hegde,Niv Cohen
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-93] Channel-Attentive Graph Neural Networks

链接: https://arxiv.org/abs/2503.00578
作者: Tuğrul Hasan Karabulut,İnci M. Baytaş
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-94] Polyconvex Physics-Augmented Neural Network Constitutive Models in Principal Stretches

链接: https://arxiv.org/abs/2503.00575
作者: Adrian Buganza Tepole,Asghar Jadoon,Manuel Rausch,Jan N. Fuhg
类目: Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG)
*备注: 16 pages, 11 figures

点击查看摘要

[LG-95] Communication-Efficient Device Scheduling for Federated Learning Using Lyapunov Optimization

链接: https://arxiv.org/abs/2503.00569
作者: Jake B. Perazzone,Shiqiang Wang,Mingyue Ji,Kevin Chan
类目: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (stat.ML)
*备注: Accepted in IEEE/ACM Transactions on Networking

点击查看摘要

[LG-96] Heatwave increases nighttime light intensity in hyperdense cities of the Global South: A double machine learning study

链接: https://arxiv.org/abs/2503.00557
作者: Ramit Debnath,Taran Chandel,Fengyuan Han,Ronita Bardhan
类目: Machine Learning (cs.LG); Computers and Society (cs.CY)
*备注: 4 figures 2 tables

点击查看摘要

[LG-97] Performance Heterogeneity in Graph Neural Networks: Lessons for Architecture Design and Preprocessing

链接: https://arxiv.org/abs/2503.00547
作者: Lukas Fesser,Melanie Weber
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-98] Scalable Reinforcement Learning for Virtual Machine Scheduling

链接: https://arxiv.org/abs/2503.00537
作者: Junjie Sheng,Jiehao Wu,Haochuan Cui,Yiqiu Hu,Wenli Zhou,Lei Zhu,Qian Peng,Wenhao Li,Xiangfeng Wang
类目: Machine Learning (cs.LG)
*备注: 23 pages, 12 figures

点击查看摘要

[LG-99] BodyGen: Advancing Towards Efficient Embodiment Co-Design ICLR2025

链接: https://arxiv.org/abs/2503.00533
作者: Haofei Lu,Zhe Wu,Junliang Xing,Jianshu Li,Ruoyu Li,Zhe Li,Yuanchun Shi
类目: Robotics (cs.RO); Machine Learning (cs.LG)
*备注: ICLR 2025 (Spotlight). Project Page: this https URL , Code: this https URL

点击查看摘要

[LG-100] Periodic Materials Generation using Text-Guided Joint Diffusion Model ICLR2025

链接: https://arxiv.org/abs/2503.00522
作者: Kishalay Das,Subhojyoti Khastagir,Pawan Goyal,Seung-Cheol Lee,Satadeep Bhattacharjee,Niloy Ganguly
类目: Machine Learning (cs.LG); Materials Science (cond-mat.mtrl-sci)
*备注: ICLR 2025

点击查看摘要

[LG-101] Projection Head is Secretly an Information Bottleneck

链接: https://arxiv.org/abs/2503.00507
作者: Zhuo Ouyang,Kaiwen Hu,Qi Zhang,Yifei Wang,Yisen Wang
类目: Machine Learning (cs.LG); Information Theory (cs.IT)
*备注:

点击查看摘要

[LG-102] Shaping Laser Pulses with Reinforcement Learning

链接: https://arxiv.org/abs/2503.00499
作者: Francesco Capuano,Davorin Peceli,Gabriele Tiboni
类目: Machine Learning (cs.LG); Computational Physics (physics.comp-ph)
*备注: 14 pages

点击查看摘要

[LG-103] Homomorphism Expressivity of Spectral Invariant Graph Neural Networks

链接: https://arxiv.org/abs/2503.00485
作者: Jingchu Gai,Yiheng Du,Bohang Zhang,Haggai Maron,Liwei Wang
类目: Machine Learning (cs.LG)
*备注: 42 pages

点击查看摘要

[LG-104] Bayesian Active Learning for Multi-Criteria Comparative Judgement in Educational Assessment

链接: https://arxiv.org/abs/2503.00479
作者: Andy Gray,Alma Rahat,Tom Crick,Stephen Lindsay
类目: Machine Learning (cs.LG); Information Retrieval (cs.IR)
*备注:

点击查看摘要

[LG-105] G-OSR: A Comprehensive Benchmark for Graph Open-Set Recognition

链接: https://arxiv.org/abs/2503.00476
作者: Yicong Dong,Rundong He,Guangyao Chen,Wentao Zhang,Zhongyi Han,Jieming Shi,Yilong Yin
类目: Machine Learning (cs.LG)
*备注: 10 pages,2 figures

点击查看摘要

[LG-106] Using Machine Learning for move sequence visualization and generation in climbing

链接: https://arxiv.org/abs/2503.00458
作者: Thomas Rimbot,Martin Jaggi,Luis Barba
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-107] Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update

链接: https://arxiv.org/abs/2503.00419
作者: Jing Wang,Yu-Jie Zhang,Peng Zhao,Zhi-Hua Zhou
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-108] Asynchronous Personalized Federated Learning through Global Memorization

链接: https://arxiv.org/abs/2503.00407
作者: Fan Wan,Yuchen Li,Xueqi Qiu,Rui Sun,Leyuan Zhang,Xingyu Miao,Tianyu Zhang,Haoran Duan,Yang Long
类目: Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
*备注:

点击查看摘要

[LG-109] Improving internal cluster quality evaluation in noisy Gaussian mixtures

链接: https://arxiv.org/abs/2503.00379
作者: Renato Cordeiro de Amorim,Vladimir Makarenkov
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-110] owards Understanding the Benefit of Multitask Representation Learning in Decision Process

链接: https://arxiv.org/abs/2503.00345
作者: Rui Lu,Yang Yue,Andrew Zhao,Simon Du,Gao Huang
类目: Machine Learning (cs.LG)
*备注: arXiv admin note: substantial text overlap with arXiv:2205.15701

点击查看摘要

[LG-111] DeepONet Augmented by Randomized Neural Networks for Efficient Operator Learning in PDEs

链接: https://arxiv.org/abs/2503.00317
作者: Zhaoxi Jiang,Fei Wang
类目: Machine Learning (cs.LG); Numerical Analysis (math.NA)
*备注:

点击查看摘要

[LG-112] Remasking Discrete Diffusion Models with Inference-Time Scaling MDM

链接: https://arxiv.org/abs/2503.00307
作者: Guanghan Wang,Yair Schiff,Subham Sekhar Sahoo,Volodymyr Kuleshov
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注: Project page: this https URL

点击查看摘要

[LG-113] Cauchy Random Features for Operator Learning in Sobolev Space

链接: https://arxiv.org/abs/2503.00300
作者: Chunyang Liao,Deanna Needell,Hayden Schaeffer
类目: Machine Learning (cs.LG); Numerical Analysis (math.NA); Machine Learning (stat.ML)
*备注: 31 pages

点击查看摘要

[LG-114] Synthetic data enables context-aware bioacoustic sound event detection

链接: https://arxiv.org/abs/2503.00296
作者: Benjamin Hoffman,David Robinson,Marius Miron,Vittorio Baglione,Daniela Canestrari,Damian Elias,Eva Trapote,Olivier Pietquin
类目: ound (cs.SD); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-115] Armijo Line-search Makes (Stochastic) Gradient Descent Go Fast

链接: https://arxiv.org/abs/2503.00229
作者: Sharan Vaswani,Reza Babanezhad
类目: Machine Learning (cs.LG); Optimization and Control (math.OC); Machine Learning (stat.ML)
*备注: 33 pages

点击查看摘要

[LG-116] Seeing Eye to AI? Applying Deep-Feature-Based Similarity Metrics to Information Visualization

链接: https://arxiv.org/abs/2503.00228
作者: Sheng Long,Angelos Chatzimparmpas,Emma Alexander,Matthew Kay,Jessica Hullman
类目: Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
*备注: Accepted at CHI 2025

点击查看摘要

[LG-117] AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit Topologies ICLR2025

链接: https://arxiv.org/abs/2503.00205
作者: Jian Gao,Weidong Cao,Junyi Yang,Xuan Zhang
类目: Machine Learning (cs.LG)
*备注: ICLR 2025 camera ready

点击查看摘要

[LG-118] ProDapt: Proprioceptive Adaptation using Long-term Memory Diffusion ICRA2025

链接: https://arxiv.org/abs/2503.00193
作者: Federico Pizarro Bejarano,Bryson Jones,Daniel Pastor Moreno,Joseph Bowkett,Paul G. Backes,Angela P. Schoellig
类目: Robotics (cs.RO); Machine Learning (cs.LG); Systems and Control (eess.SY)
*备注: 7 pages, 8 figures. Accepted to IEEE ICRA 2025. Code is publicly available at this https URL

点击查看摘要

[LG-119] Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks

链接: https://arxiv.org/abs/2503.00187
作者: Hanjiang Hu,Alexander Robey,Changliu Liu
类目: Machine Learning (cs.LG); Cryptography and Security (cs.CR)
*备注: 28 pages, 10 figures, 7 tables

点击查看摘要

[LG-120] Optimal Transfer Learning for Missing Not-at-Random Matrix Completion

链接: https://arxiv.org/abs/2503.00174
作者: Akhil Jalan,Yassir Jedra,Arya Mazumdar,Soumendu Sundar Mukherjee,Purnamrita Sarkar
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-121] Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation NEURIPS2024

链接: https://arxiv.org/abs/2503.00152
作者: Keqiang Yan,Xiner Li,Hongyi Ling,Kenna Ashen,Carl Edwards,Raymundo Arróyave,Marinka Zitnik,Heng Ji,Xiaofeng Qian,Xiaoning Qian,Shuiwang Ji
类目: Machine Learning (cs.LG); Materials Science (cond-mat.mtrl-sci)
*备注: This paper has been accepted as a NeurIPS 2024 Poster

点击查看摘要

[LG-122] DISCO: Internal Evaluation of Density-Based Clustering

链接: https://arxiv.org/abs/2503.00127
作者: Anna Beer,Lena Krieger,Pascal Weber,Martin Ritzert,Ira Assent,Claudia Plant
类目: Machine Learning (cs.LG); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-123] Gaussian process surrogate model to approximate power grid simulators – An application to the certification of a congestion management controller

链接: https://arxiv.org/abs/2503.00094
作者: Pierre Houdouin,Manuel Ruiz,Lucas Saludjian
类目: Machine Learning (cs.LG)
*备注: 6 pages, 7 figures, conference

点击查看摘要

[LG-124] Enhancing Collaborative Filtering-Based Course Recommendations by Exploiting Time-to-Event Information with Survival Analysis

链接: https://arxiv.org/abs/2503.00072
作者: Alireza Gharahighehi,Achilleas Ghinis,Michela Venturini,Frederik Cornillie,Celine Vens
类目: Computers and Society (cs.CY); Information Retrieval (cs.IR); Machine Learning (cs.LG)
*备注: 19 pages, 1 figure

点击查看摘要

[LG-125] ADAGE: Active Defenses Against GNN Extraction

链接: https://arxiv.org/abs/2503.00065
作者: Jing Xu,Franziska Boenisch,Adam Dziedzic
类目: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-126] Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents NAACL2025

链接: https://arxiv.org/abs/2503.00061
作者: Qiusi Zhan,Richard Fang,Henil Shalin Panchal,Daniel Kang
类目: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
*备注: 17 pages, 5 figures, 6 tables (NAACL 2025 Findings)

点击查看摘要

[LG-127] optimizn: a Python Library for Developing Customized Optimization Algorithms

链接: https://arxiv.org/abs/2503.00033
作者: Akshay Sathiya,Rohit Pandey
类目: Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-128] Cauchy-Schwarz Regularizers ICLR2025

链接: https://arxiv.org/abs/2503.01639
作者: Sueda Taner,Ziyi Wang,Christoph Studer
类目: Optimization and Control (math.OC); Machine Learning (cs.LG)
*备注: Accepted to ICLR 2025

点击查看摘要

[LG-129] he Role of Deep Learning in Financial Asset Management: A Systematic Review

链接: https://arxiv.org/abs/2503.01591
作者: Pedro Reis,Ana Paula Serra,João Gama
类目: General Finance (q-fin.GN); Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-130] Improving the statistical efficiency of cross-conformal prediction

链接: https://arxiv.org/abs/2503.01495
作者: Matteo Gasparin,Aaditya Ramdas
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Applications (stat.AP)
*备注:

点击查看摘要

[LG-131] Primer C-VAE: An interpretable deep learning primer design method to detect emerging virus variants

链接: https://arxiv.org/abs/2503.01459
作者: Hanyu Wang,Emmanuel K. Tsinda,Anthony J. Dunn,Francis Chikweto,Alain B. Zemkoho
类目: Genomics (q-bio.GN); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-132] A Linearly Convergent Frank-Wolfe-type Method for Smooth Convex Minimization over the Spectrahedron

链接: https://arxiv.org/abs/2503.01441
作者: Dan Garber
类目: Optimization and Control (math.OC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-133] Reconstruction of muon bundles in KM3NeT detectors using machine learning methods

链接: https://arxiv.org/abs/2503.01433
作者: Piotr Kalaczyński(on behalf of the KM3NeT Collaboration)
类目: High Energy Physics - Experiment (hep-ex); Machine Learning (cs.LG)
*备注: 16 pages, 12 figures, proceedings of the 2nd International Workshop on Machine Learning and Quantum Computing Applications in Medicine and Physics, accepted for publication in Computer Science Journal

点击查看摘要

[LG-134] Statistical physics analysis of graph neural networks: Approaching optimality in the contextual stochastic block model

链接: https://arxiv.org/abs/2503.01361
作者: O. Duranthon,L. Zdeborová
类目: Disordered Systems and Neural Networks (cond-mat.dis-nn); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-135] Pre-training Graph Neural Networks with Structural Fingerprints for Materials Discovery

链接: https://arxiv.org/abs/2503.01227
作者: Shuyi Jia,Shitij Govil,Manav Ramprasad,Victor Fung
类目: Materials Science (cond-mat.mtrl-sci); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-136] Dementia Insights: A Context-Based MultiModal Approach

链接: https://arxiv.org/abs/2503.01226
作者: Sahar Sinene Mehdoui,Abdelhamid Bouzid,Daniel Sierra-Sosa,Adel Elmaghraby
类目: Neurons and Cognition (q-bio.NC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-137] Large AI Model for Delay-Doppler Domain Channel Prediction in 6G OTFS-Based Vehicular Networks

链接: https://arxiv.org/abs/2503.01116
作者: Jianzhe Xue,Dongcheng Yuan,Zhanxi Ma,Tiankai Jiang,Yu Sun,Haibo Zhou,Xuemin Shen
类目: ignal Processing (eess.SP); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-138] Learning Stochastic Dynamical Systems with Structured Noise

链接: https://arxiv.org/abs/2503.01077
作者: Ziheng Guo,James Greene,Ming Zhong
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Numerical Analysis (math.NA)
*备注:

点击查看摘要

[LG-139] Vector Copula Variational Inference and Dependent Block Posterior Approximations

链接: https://arxiv.org/abs/2503.01072
作者: Yu Fu,Michael Stanley Smith,Anastasios Panagiotelis
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Econometrics (econ.EM); Methodology (stat.ME)
*备注:

点击查看摘要

[LG-140] Powerful rank verification for multivariate Gaussian data with any covariance structure

链接: https://arxiv.org/abs/2503.01065
作者: Anav Sood
类目: Methodology (stat.ME); Machine Learning (cs.LG); Statistics Theory (math.ST); Machine Learning (stat.ML)
*备注:

点击查看摘要

[LG-141] Data-Efficient Kernel Methods for Learning Differential Equations and Their Solution Operators: Algorithms and Error Analysis

链接: https://arxiv.org/abs/2503.01036
作者: Yasamin Jalalian,Juan Felipe Osorio Ramirez,Alexander Hsu,Bamdad Hosseini,Houman Owhadi
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Numerical Analysis (math.NA)
*备注:

点击查看摘要

[LG-142] PABBO: Preferential Amortized Black-Box Optimization ICLR2025

链接: https://arxiv.org/abs/2503.00924
作者: Xinyu Zhang,Daolang Huang,Samuel Kaski,Julien Martinelli
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: 25 pages, 17 figures. Accepted at the Thirteenth International Conference on Learning Representations (ICLR 2025)

点击查看摘要

[LG-143] Impact of Fasteners on the Radar Cross-Section performance of Radar Absorbing Air Intake Duct

链接: https://arxiv.org/abs/2503.00914
作者: Vijay Kumar Sutrakar,Anjana P K
类目: ignal Processing (eess.SP); Materials Science (cond-mat.mtrl-sci); Other Condensed Matter (cond-mat.other); Machine Learning (cs.LG); Applied Physics (physics.app-ph)
*备注:

点击查看摘要

[LG-144] Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure ICLR2025

链接: https://arxiv.org/abs/2503.00856
作者: Samet Demir,Zafer Dogan
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: ICLR 2025, 27 pages, 9 figures

点击查看摘要

[LG-145] Insights into dendritic growth mechanisms in batteries: A combined machine learning and computational study

链接: https://arxiv.org/abs/2503.00836
作者: Zirui Zhao,Junchao Xia,Si Wu,Xiaoke Wang,Guanping Xu,Yinghao Zhu,Jing Sun,Hai-Feng Li
类目: Computational Physics (physics.comp-ph); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-146] -cell receptor specificity landscape revealed through de novo peptide design

链接: https://arxiv.org/abs/2503.00648
作者: Gian Marco Visani,Michael N. Pun,Anastasia A. Minervina,Philip Bradley,Paul Thomas,Armita Nourmohammad
类目: Quantitative Methods (q-bio.QM); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-147] Asymptotic Theory of Eigenvectors for Latent Embeddings with Generalized Laplacian Matrices

链接: https://arxiv.org/abs/2503.00640
作者: Jianqing Fan,Yingying Fan,Jinchi Lv,Fan Yang,Diwen Yu
类目: Machine Learning (stat.ML); Information Theory (cs.IT); Machine Learning (cs.LG); Statistics Theory (math.ST)
*备注: 104 pages, 12 figures

点击查看摘要

[LG-148] Real-Time Personalization with Simple Transformers

链接: https://arxiv.org/abs/2503.00608
作者: Lin An,Andrew A. Li,Vaisnavi Nemala,Gabriel Visotsky
类目: Optimization and Control (math.OC); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-149] Semi-Parametric Batched Global Multi-Armed Bandits with Covariates

链接: https://arxiv.org/abs/2503.00565
作者: Sakshi Arya,Hyebin Song
类目: Machine Learning (stat.ML); Machine Learning (cs.LG); Statistics Theory (math.ST); Methodology (stat.ME)
*备注:

点击查看摘要

[LG-150] rajectory Inference with Smooth Schrödinger Bridges

链接: https://arxiv.org/abs/2503.00530
作者: Wanli Hong,Yuliang Shi,Jonathan Niles-Weed
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-151] On the Saturation Effects of Spectral Algorithms in Large Dimensions

链接: https://arxiv.org/abs/2503.00504
作者: Weihao Lu,Haobo Zhang,Yicheng Li,Qian Lin
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-152] Stable and Accurate Orbital-Free DFT Powered by Machine Learning

链接: https://arxiv.org/abs/2503.00443
作者: Roman Remme,Tobias Kaczun,Tim Ebert,Christof A. Gehrig,Dominik Geng,Gerrit Gerhartz,Marc K. Ickler,Manuel V. Klockow,Peter Lippmann,Johannes S. Schmidt,Simon Wagner,Andreas Dreuw,Fred A. Hamprecht
类目: Chemical Physics (physics.chem-ph); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-153] Convergence of energy-based learning in linear resistive networks

链接: https://arxiv.org/abs/2503.00349
作者: Anne-Men Huijzer,Thomas Chaffey,Bart Besselink,Henk J. van Waarde
类目: Optimization and Control (math.OC); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Systems and Control (eess.SY)
*备注:

点击查看摘要

[LG-154] Generalization Bounds for Equivariant Networks on Markov Data

链接: https://arxiv.org/abs/2503.00292
作者: Hui Li,Zhiguo Wang,Bohui Chen,Li Sheng
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: Submitted for possible publication

点击查看摘要

[LG-155] Particle-based plasma simulation using a graph neural network

链接: https://arxiv.org/abs/2503.00274
作者: Marin Mlinarević(1),George K. Holt(2),Adriano Agnello(2) ((1) University College London, (2) STFC Hartree Centre)
类目: Plasma Physics (physics.plasm-ph); Machine Learning (cs.LG); Computational Physics (physics.comp-ph)
*备注: 23 pages, 11 figures

点击查看摘要

[LG-156] Evolution of Information in Interactive Decision Making: A Case Study for Multi-Armed Bandits

链接: https://arxiv.org/abs/2503.00273
作者: Yuzhou Gu,Yanjun Han,Jian Qian
类目: Machine Learning (stat.ML); Information Theory (cs.IT); Machine Learning (cs.LG)
*备注:

点击查看摘要

[LG-157] An interpretation of the Brownian bridge as a physics-informed prior for the Poisson equation

链接: https://arxiv.org/abs/2503.00213
作者: Alex Alberts,Ilias Bilionis
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: 43 pages, 2 figures

点击查看摘要

[LG-158] RecCrysFormer: Refined Protein Structural Prediction from 3D Patterson Maps via Recycling Training Runs

链接: https://arxiv.org/abs/2503.00143
作者: Tom Pan,Evan Dramko,Mitchell D. Miller,George N. Phillips Jr.,Anastasios Kyrillidis
类目: Quantitative Methods (q-bio.QM); Machine Learning (cs.LG); Optimization and Control (math.OC)
*备注: 16 pages, 9 figures. To be published in Proceedings of CPAL 2025

点击查看摘要

[LG-159] Approaching the Harm of Gradient Attacks While Only Flipping Labels

链接: https://arxiv.org/abs/2503.00140
作者: Abdessamad El-Kabid,El-Mahdi El-Mhamdi
类目: Machine Learning (stat.ML); Machine Learning (cs.LG)
*备注: 17 pages, 25 figures

点击查看摘要

[LG-160] Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders

链接: https://arxiv.org/abs/2503.00131
作者: Farouk Mokhtar,Joosep Pata,Michael Kagan,Dolores Garcia,Eric Wulff,Mengke Zhang,Javier Duarte
类目: High Energy Physics - Experiment (hep-ex); Machine Learning (cs.LG); High Energy Physics - Phenomenology (hep-ph); Data Analysis, Statistics and Probability (physics.data-an); Instrumentation and Detectors (physics.ins-det)
*备注: 20 pages, 13 figures

点击查看摘要

[LG-161] Exploring the Potential of QEEGNet for Cross-Task and Cross-Dataset Electroencephalography Encoding with Quantum Machine Learning

链接: https://arxiv.org/abs/2503.00080
作者: Chi-Sheng Chen,Samuel Yen-Chi Chen,Huan-Hsin Tseng
类目: Quantum Physics (quant-ph); Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC)
*备注:

点击查看摘要

信息检索

[IR-0] Hierarchical Causal Transformer with Heterogeneous Information for Expandable Sequential Recommendation

链接: https://arxiv.org/abs/2503.01469
作者: Hao Deng,Haibo Xing,Kanefumi Matsuyama,Yulei Huang,Jinxin Hu,Hong Wen,Jia Xu,Zulong Chen,Yu Zhang,Xiaoyi Zeng,Jing Zhang
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-1] Streaming Piano Transcription Based on Consistent Onset and Offset Decoding with Sustain Pedal Detection

链接: https://arxiv.org/abs/2503.01362
作者: Weixing Wei,Jiahao Zhao,Yulun Wu,Kazuyoshi Yoshii
类目: ound (cs.SD); Information Retrieval (cs.IR); Multimedia (cs.MM); Audio and Speech Processing (eess.AS)
*备注: Accepted to ISMIR 2024

点击查看摘要

[IR-2] HI-Series Algorithms A Hybrid of Substance Diffusion Algorithm and Collaborative Filtering

链接: https://arxiv.org/abs/2503.01305
作者: Yu Peng,Ya-Hui An
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-3] Can We Find the Code? An Empirical Study of Google Scholars Code Retrieval

链接: https://arxiv.org/abs/2503.01031
作者: Shi-Shun Chen
类目: Digital Libraries (cs.DL); Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-4] owards An Efficient LLM Training Paradigm for CTR Prediction

链接: https://arxiv.org/abs/2503.01001
作者: Allen Lin,Renqin Cai,Yun He,Hanchao Yu,Jing Qian,Rui Li,Qifan Wang,James Caverlee
类目: Information Retrieval (cs.IR)
*备注:

点击查看摘要

[IR-5] Federated Conversational Recommender System ECIR2024

链接: https://arxiv.org/abs/2503.00999
作者: Allen Lin,Jianling Wang,Ziwei Zhu,James Caverlee
类目: Information Retrieval (cs.IR)
*备注: ECIR 2024

点击查看摘要

[IR-6] Passage Query Methods for Retrieval and Reranking in Conversational Agents

链接: https://arxiv.org/abs/2503.00238
作者: Victor De Lima. Grace Hui Yang
类目: Information Retrieval (cs.IR)
*备注: 7 pages, 3 figures. In Proceedings of the Thirty-Third Text Retrieval Conference (TREC 2024), November 18-22, 2024, Rockville, MD, USA

点击查看摘要

[IR-7] DeepRetrieval: Powerful Query Generation for Information Retrieval with Reinforcement Learning

链接: https://arxiv.org/abs/2503.00223
作者: Pengcheng Jiang
类目: Information Retrieval (cs.IR)
*备注: Ongoing work

点击查看摘要

附件下载

点击下载今日全部论文列表

Arxiv今日论文 | 2025-03-04

目录

概览 (2025-03-04)

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