arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Learning Representations · 会议 · Machine Learning

共收录 9454
2412.13341 2025-09-08 cs.LG cs.CR

Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing

Keltin Grimes, Marco Christiani, David Shriver, Marissa Connor

Comments Published at ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.03335 2025-09-05 cs.IT math.IT

Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision Processes

Haotian Wu, Gongpu Chen, Deniz Gündüz

Journal ref The International Conference on Learning Representations (ICLR) 2015

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.02746 2025-09-04 cs.LG cs.AI q-bio.NC

Mentality: A Mamba-based Approach towards Foundation Models for EEG

Saarang Panchavati, Corey Arnold, William Speier

机构 * Department of Radiology University of California(放射科系 加州大学)

Journal ref In Proceedings of the ICLR 2024 Workshop on Learning from Time Series for Health (2024). Retrieved from https://openreview.net/forum?id=O6T38rRiFp

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.15800 2025-09-04 cs.IR

FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation

Chanyeol Choi, Jihoon Kwon, Jaeseon Ha, Hojun Choi, Chaewoon Kim, Yongjae Lee, Jy-yong Sohn, Alejandro Lopez-Lira

Comments 10 pages, 3 figures, ICLR 2025 Workshop Advances in Financial AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.03742 2025-09-03 cs.CL cs.AI cs.LG

Beyond Scalar Reward Model: Learning Generative Judge from Preference Data

Ziyi Ye, Xiangsheng Li, Qiuchi Li, Qingyao Ai, Yujia Zhou, Wei Shen, Dong Yan, Yiqun Liu

机构 * Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系) Baichuan AI(拜智科技) University of Copenhagen(哥本哈根大学)

Journal ref The Thirteenth International Conference on Learning Representations 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2302.00935 2025-09-01 cs.AI

Policy Expansion for Bridging Offline-to-Online Reinforcement Learning

Haichao Zhang, We Xu, Haonan Yu

机构 * Horizon Robotics

Comments ICLR 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.14648 2025-08-29 cs.LG cs.AI

Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off

Futa Waseda, Ching-Chun Chang, Isao Echizen

机构 * The University of Tokyo(东京大学) National Institute of Informatics(日本信息处理学会)

Comments ICLR 2025 Accepted. Codes are available here: https://github.com/futakw/AR-AT

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.05229 2025-08-28 cs.LG cs.AI

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, Oncel Tuzel, Samy Bengio, Mehrdad Farajtabar

机构 * Apple(苹果公司) Washington State University(华盛顿州立大学)

Comments ICLR camera ready + additional discussion in the appendix

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.08738 2025-08-27 cs.LG physics.flu-dyn

MeshMask: Physics-Based Simulations with Masked Graph Neural Networks

Paul Garnier, Vincent Lannelongue, Jonathan Viquerat, Elie Hachem

机构 * Mines Paris - PSL University Centre for Material Forming (CEMEF)(巴黎矿学院-PSL大学材料成形中心(CEMEF))

Journal ref ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.05464 2025-08-27 cs.LG

Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs

Levi Rauchwerger, Stefanie Jegelka, Ron Levie

机构 * Technion – IIT Faculty of Mathematics(技术学院-理工学院数学系) MIT Dept of EECS and CSAIL(麻省理工学院电子工程与计算机科学系和计算机科学与人工智能实验室) TUM School of CIT MCML MDSI(技术大学计算机信息科技学院MCML MDSI)

Journal ref Proceedings of the Thirteenth International Conference on Learning Representations (ICLR 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.17815 2025-08-26 cs.LG q-bio.BM

Multi-domain Distribution Learning for De Novo Drug Design

Arne Schneuing, Ilia Igashov, Adrian W. Dobbelstein, Thomas Castiglione, Michael Bronstein, Bruno Correia

机构 * École Polytechnique Fédérale de Lausanne(瑞士联邦理工学院) VantAI, Inc.(VantAI公司) University of Oxford(牛津大学)

Journal ref ICLR 2025: https://openreview.net/forum?id=g3VCIM94ke

详情

展开后加载摘要…

URL PDF HTML 收藏
1911.02054 2025-08-26 cs.CV cs.LG

Federated Adversarial Domain Adaptation

Xingchao Peng, Zijun Huang, Yizhe Zhu, Kate Saenko

机构 * Boston University(波士顿大学) Columbia University(哥伦比亚大学) Rutgers University(罗格斯大学)

Comments Published as a conference paper at ICLR 2020

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.14280 2025-08-22 cs.CV

RESfM: Robust Deep Equivariant Structure from Motion

Fadi Khatib, Yoni Kasten, Dror Moran, Meirav Galun, Ronen Basri

机构 * Weizmann Institute of Science(魏茨曼科学研究所) NVIDIA(英伟达)

Comments Accepted to ICLR 2025. Project page: https://robust-equivariant-sfm.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.07829 2025-08-20 cs.LG cs.CV stat.ML

Disentangled Representation Learning with the Gromov-Monge Gap

Théo Uscidda, Luca Eyring, Karsten Roth, Fabian Theis, Zeynep Akata, Marco Cuturi

机构 * CREST-ENSAE Helmholtz Munich(海德堡-慕尼黑研究所) TU Munich(慕尼黑技术大学) Munich Center of Machine Learning(慕尼黑机器学习中心) Tubingen AI Center(图宾根人工智能中心) Apple(苹果公司)

Comments ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.17811 2025-08-19 cs.CL cs.AI cs.DB

Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models

Wenqi Pei, Hailing Xu, Hengyuan Zhao, Shizheng Hou, Han Chen, Zining Zhang, Pingyi Luo, Bingsheng He

Comments DL4C @ ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.01671 2025-08-18 cs.CL cs.AI

Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding

Yanming Liu, Xinyue Peng, Jiannan Cao, Yanxin Shen, Tianyu Du, Sheng Cheng, Xun Wang, Jianwei Yin, Xuhong Zhang

Comments ICLR 2025 camera ready version, with second updated metadata

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.03807 2025-08-18 cs.AI cs.CL cs.RO

Tool-Planner: Task Planning with Clusters across Multiple Tools

Yanming Liu, Xinyue Peng, Jiannan Cao, Yuwei Zhang, Xuhong Zhang, Sheng Cheng, Xun Wang, Jianwei Yin, Tianyu Du

Comments ICLR 2025 Camera Ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.00332 2025-08-14 cs.AI q-bio.NC

Vision Language Models Know Law of Conservation without Understanding More-or-Less

Dezhi Luo, Haiyun Lyu, Qingying Gao, Haoran Sun, Yijiang Li, Hokin Deng

机构 * University of Michigan(密歇根大学) University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校) Johns Hopkins University(约翰霍普金斯大学) University of California, San Diego(加州大学圣地亚哥分校) Carnegie Mellon University(卡内基梅隆大学)

Comments Published at the ICLR 2025 Workshop on Bidirectional Human-AI Alignment (BiAlign)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.00318 2025-08-14 cs.AI q-bio.NC

Probing Mechanical Reasoning in Large Vision Language Models

Haoran Sun, Qingying Gao, Haiyun Lyu, Dezhi Luo, Yijiang Li, Hokin Deng

机构 * Johns Hopkins University(约翰霍普金斯大学) University of North Carolina Chapel Hill(北卡罗来纳大学教堂山分校) University of Michigan(密歇根大学) University of California San Diego(加州大学圣地亚哥分校) Carnegie Mellon University(卡内基梅隆大学)

Comments Published at the ICLR 2025 Workshop on Bidirectional Human-AI Alignment (BiAlign)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.10216 2025-08-13 cs.LG cs.AI

Forget the Data and Fine-Tuning! Just Fold the Network to Compress

Dong Wang, Haris Šikić, Lothar Thiele, Olga Saukh

机构 * Graz University of Technology(格拉茨技术大学) ETH Zurich(苏黎世联邦理工学院) Complexity Science Hub Vienna(维也纳复杂科学中心)

Comments This paper has been accepted by The Thirteenth International Conference on Learning Representations(ICLR), 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.00324 2025-08-13 cs.AI

Vision Language Models See What You Want but not What You See

Qingying Gao, Yijiang Li, Haiyun Lyu, Haoran Sun, Dezhi Luo, Hokin Deng

机构 * Johns Hopkins University(约翰霍普金斯大学) University of California San Diego(加州大学圣地亚哥分校) University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校) University of Michigan(密歇根大学) Carnegie Mellon University(卡内基梅隆大学)

Comments Published at the ICLR 2025 Workshop on Bidirectional Human-AI Alignment (BiAlign)

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.03546 2025-08-13 stat.ML cs.LG

Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models

Marien Renaud, Jiaming Liu, Valentin de Bortoli, Andrés Almansa, Ulugbek S. Kamilov

机构 * Department of Electrical & Systems Engineering, Washington University in St. Louis, USA(华盛顿大学圣路易斯分校电气与系统工程系) Computer Science Department, ENS, PSL University, 75005, France(巴黎高等师范学院计算机科学系) MAP5, CNRS, Université Paris Cité, 75006, France(巴黎城市大学MAP5研究所) Department of Computer Science & Engineering, Washington University in St. Louis, USA(华盛顿大学圣路易斯分校计算机科学与工程系)

Journal ref (ICLR 2024) The Twelfth International Conference on Learning Representations,

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.08109 2025-08-12 cs.CL cs.AI cs.LG

A Closer Look at Machine Unlearning for Large Language Models

Xiaojian Yuan, Tianyu Pang, Chao Du, Kejiang Chen, Weiming Zhang, Min Lin

机构 * University of Science and Technology of China(中国科学技术大学) Sea AI Lab, Singapore(新加坡Sea AI实验室)

Comments ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.03363 2025-08-12 cs.CR cs.LG

TDDBench: A Benchmark for Training data detection

Zhihao Zhu, Yi Yang, Defu Lian

机构 * University of Science and Technology of China(中国科学技术大学) The Hong Kong University of Science and Technology(香港科技大学)

Comments Published as a conference paper at ICLR 2025

Journal ref The Thirteenth International Conference on Learning Representations, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.09032 2025-08-08 cs.LG cs.AI cs.CL

Teaching LLMs How to Learn with Contextual Fine-Tuning

Younwoo Choi, Muhammad Adil Asif, Ziwen Han, John Willes, Rahul G. Krishnan

机构 * University of Toronto(多伦多大学) Vector Institute(向量研究所)

Comments ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.09821 2025-08-08 cs.LG cs.CV

Towards Scalable Newborn Screening: Automated General Movement Assessment in Uncontrolled Settings

Daphné Chopard, Sonia Laguna, Kieran Chin-Cheong, Annika Dietz, Anna Badura, Sven Wellmann, Julia E. Vogt

机构 * ETH Zurich(苏黎世联邦理工学院) University of Zurich(苏黎世大学) University of Regensburg(莱茵河畔埃尔兰根大学) University Children’s Hospital(儿童医院) University Children’s Hospital Regensburg(埃尔兰根儿童医院)

Comments Paper at Proceedings of Machine Learning Research 298 1 22, 2025 Machine Learning for Healthcare. Iterations of previous versions accepted as oral and best paper award at ICLR 2025 Workshop on AI for Children and at the Findings track of the Machine Learning for Health (ML4H) symposium 2024

Journal ref Proceedings of Machine Learning Research 298 1-22, 2025 Machine Learning for Healthcare

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.05106 2025-08-08 math.OC cs.LG stat.ML

Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson-Romberg Extrapolation

Marina Sheshukova, Denis Belomestny, Alain Durmus, Eric Moulines, Alexey Naumov, Sergey Samsonov

机构 * HSE University(俄罗斯高等经济大学) Duisburg-Essen University(杜伊斯堡-埃森大学) CMAP, UMR 7641, Ecole Polytechnique(巴黎高等理工学院CMAP研究所) Mohamed Bin Zayed University of AI(马尔代夫人工智能大学) Skolkovo Institute of Science and Technology(斯克尔科沃科技研究院) Steklov Mathematical Institute of Russian Academy of Sciences(俄罗斯科学院斯克洛夫数学研究所)

Comments ICLR-2025, camera-ready version. Some typos and definitions of constants have been fixed in the appendix

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.03864 2025-08-08 cs.AI cs.CL cs.LG

DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search

Murong Yue, Wenlin Yao, Haitao Mi, Dian Yu, Ziyu Yao, Dong Yu

机构 * George Mason University(乔治·马歇尔大学) Tencent AI Lab(腾讯AI实验室)

Comments Accepted to ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.20720 2025-08-07 cs.CV

4D Gaussian Splatting: Modeling Dynamic Scenes with Native 4D Primitives

Zeyu Yang, Zijie Pan, Xiatian Zhu, Li Zhang, Jianfeng Feng, Yu-Gang Jiang, Philip H. S. Torr

机构 * Fudan University(复旦大学) University of Surrey(萨里大学) University of Oxford(牛津大学)

Comments Journal extension of ICLR 2024. arXiv admin note: text overlap with arXiv:2310.10642

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.09099 2025-08-07 cs.AI

Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models

Xiongye Xiao, Heng Ping, Chenyu Zhou, Defu Cao, Yaxing Li, Yi-Zhuo Zhou, Shixuan Li, Nikos Kanakaris, Paul Bogdan

机构 * University of Southern California(美国南加州大学) University of California(加州大学)

Comments Accepted at ICLR 2025. OpenReview: https://openreview.net/forum?id=nt8gBX58Kh

详情

展开后加载摘要…

URL PDF HTML 收藏