arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Machine Learning · 会议 · Machine Learning

2025-08-19 至 2025-08-19 共收录 19
2508.12576 2025-08-19 cs.LG cs.AI

Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg

Like Jian, Dong Liu

机构 * School of Cyber Science and Technology, Beihang University, Beijing, China(网络安全科学与技术学院,北京航空航天大学,北京,中国)

Comments Accepted by ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.07408 2025-08-19 q-fin.ST cs.CL cs.LG

Event-Aware Sentiment Factors from LLM-Augmented Financial Tweets: A Transparent Framework for Interpretable Quant Trading

Yueyi Wang, Qiyao Wei

机构 * Department of Physics, University of Cambridge, Cambridge, UK(剑桥大学物理系) Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, UK(剑桥大学应用数学与理论物理系)

Comments 16 pages, 12 figures, accepted at ICML 2025 New in ML Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06895 2025-08-19 cs.LG stat.ML

Scalable Gaussian Processes with Latent Kronecker Structure

Jihao Andreas Lin, Sebastian Ament, Maximilian Balandat, David Eriksson, José Miguel Hernández-Lobato, Eytan Bakshy

机构 * Meta University of Cambridge(剑桥大学) Max Planck Institute for Intelligent Systems, Tübingen(图宾根Max Planck智能系统研究所)

Comments International Conference on Machine Learning 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06280 2025-08-19 cs.LG cs.AI

Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias

Yuanzhe Hu, Kinshuk Goel, Vlad Killiakov, Yaoqing Yang

机构 * dartmouth(达特茅斯学院) ucsd(加州大学圣迭戈分校) srm(SRM科学与技术学院) ucb(加州大学伯克利分校)

Comments 29 pages, 14 figures, ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23194 2025-08-19 cs.LG

Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics

Shiwei Li, Xiandi Luo, Xing Tang, Haozhao Wang, Hao Chen, Weihong Luo, Yuhua Li, Xiuqiang He, Ruixuan Li

机构 * Huazhong University of Science and Technology(华中科技大学) Shenzhen Technology University(深圳科技大学) FiT, Tencent(FiT,腾讯)

Comments Accepted by ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23176 2025-08-19 cs.LG cs.DC

The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning

Shiwei Li, Xiandi Luo, Haozhao Wang, Xing Tang, Shijie Xu, Weihong Luo, Yuhua Li, Xiuqiang He, Ruixuan Li

机构 * Huazhong University of Science and Technology(华中科技大学) Shenzhen Technology University(深圳科技大学) FiT, Tencent(FiT,腾讯)

Comments Accepted by ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.01911 2025-08-19 cs.AI cs.CL cs.HC physics.comp-ph

Advancing AI-Scientist Understanding: Multi-Agent LLMs with Interpretable Physics Reasoning

Yinggan Xu, Hana Kimlee, Yijia Xiao, Di Luo

机构 * NSF Center for Quantum Network(NSF量子网络中心) University of California, Los Angeles(加州大学洛杉矶分校)

Comments ICML 2025 Workshop on MAS

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.19595 2025-08-19 cs.LG

Optimizing Language Models for Inference Time Objectives using Reinforcement Learning

Yunhao Tang, Kunhao Zheng, Gabriel Synnaeve, Rémi Munos

机构 * Meta GenAI(Meta 生成式人工智能) Meta FAIR

Comments Published as a conference paper at ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.06142 2025-08-19 stat.ML cs.LG

Linear Bandits with Partially Observable Features

Wonyoung Kim, Sungwoo Park, Garud Iyengar, Assaf Zeevi, Min-hwan Oh

机构 * Seoul National University, Seoul, Korea(首尔国立大学) Chung-Ang University, Seoul, Korea(Chung-Ang 大学) Columbia University, New York, USA(哥伦比亚大学)

Comments Accepted in ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.02516 2025-08-19 cs.LG cs.AI stat.ML

Adaptive Exploration for Multi-Reward Multi-Policy Evaluation

Alessio Russo, Aldo Pacchiano

机构 * Faculty of Computing and Data Sciences(计算与数据科学系) Boston University(波士顿大学) Broad Institute of MIT and Harvard(哈佛大学与麻省理工学院Broad研究所)

Comments Accepted at the International Conference on Machine Learning, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.20892 2025-08-19 cs.LG stat.ML

Rethinking Aleatoric and Epistemic Uncertainty

Freddie Bickford Smith, Jannik Kossen, Eleanor Trollope, Mark van der Wilk, Adam Foster, Tom Rainforth

机构 * University of Oxford(牛津大学)

Comments Published at ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.02083 2025-08-19 cs.CL cs.AI cs.CE cs.LG

Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models

Jonas Zausinger, Lars Pennig, Anamarija Kozina, Sean Sdahl, Julian Sikora, Adrian Dendorfer, Timofey Kuznetsov, Mohamad Hagog, Nina Wiedemann, Kacper Chlodny, Vincent Limbach, Anna Ketteler, Thorben Prein, Vishwa Mohan Singh, Michael Morris Danziger, Jannis Born

机构 * Technical University of Munich(慕尼黑技术大学) Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心(MCML)) IBM Research Europe(IBM欧洲研究院) ETH Zurich(苏黎世联邦理工学院)

Comments ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2307.14740 2025-08-19 cs.SE cs.AI

New Interaction Paradigm for Complex EDA Software Leveraging GPT

Xinyu Wang, Boyu Han, Zhenghan Tai, Jingrui Tian, Yifan Wang, Junyu Yan, Yidong Tian

机构 * McGill University, Canada(麦吉尔大学) Stanford University, USA(斯坦福大学) University of Toronto, Canada(多伦多大学) Tsinghua University, China(清华大学) Beihang University, China(北航大学) The University of Manchester, UK(曼彻斯特大学) University of California, Los Angeles, USA(加州大学洛杉矶分校) Beijing Smarton Empower Co., Ltd., China(北京Smarton赋能科技有限公司)

Comments Accepted to ICML 2025 Workshop on New In Machine Learning (NewInML), 9 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.11697 2025-08-19 cs.CV cs.AI

Separating Knowledge and Perception with Procedural Data

Adrián Rodríguez-Muñoz, Manel Baradad, Phillip Isola, Antonio Torralba

机构 * Massachusetts Institute of Technology(麻省理工学院)

Comments 17 pages, 18 figures, 3 tables, to be published in ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.03865 2025-08-19 cs.CL cs.AI cs.LG

OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference

Seungjun Shin, Jaehoon Oh, Dokwan Oh

机构 * Samsung Advanced Institute of Technology, Korea(三星先进技术研究所,韩国)

Comments ICML 2025 (final version)

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.03025 2025-08-19 cs.LG

Hierarchical Refinement: Optimal Transport to Infinity and Beyond

Peter Halmos, Julian Gold, Xinhao Liu, Benjamin J. Raphael

机构 * Department of Computer Science, Princeton University(普林斯顿大学计算机科学系) Center for Statistics and Machine Learning, Princeton University(普林斯顿大学统计与机器学习中心)

Comments 33 pages, 9 figures. Accepted to ICML 2025 (Oral). Comments are welcome!

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.13581 2025-08-19 cs.IR cs.LG

ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation

Yupeng Hou, Jianmo Ni, Zhankui He, Noveen Sachdeva, Wang-Cheng Kang, Ed H. Chi, Julian McAuley, Derek Zhiyuan Cheng

机构 * University of California, San Diego(加州大学圣地亚哥分校) Google DeepMind(谷歌DeepMind)

Comments ICML 2025 (Spotlight)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.00318 2025-08-19 cs.LG cs.NA math.NA

Sub-Sequential Physics-Informed Learning with State Space Model

Chenhui Xu, Dancheng Liu, Yuting Hu, Jiajie Li, Ruiyang Qin, Qingxiao Zheng, Jinjun Xiong

机构 * University at Buffalo, SUNY(布法罗大学,纽约州立大学) University of Notre Dame(诺丁汉大学)

Comments ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.10322 2025-08-19 cs.CV cs.LG

LieRE: Lie Rotational Positional Encodings

Sophie Ostmeier, Brian Axelrod, Maya Varma, Michael E. Moseley, Akshay Chaudhari, Curtis Langlotz

机构 * Computer Science Department, Stanford University, USA(斯坦福大学计算机科学系) Radiology Department, Stanford University, USA(斯坦福大学放射学系)

Comments Final proceedings version at ICML

详情

展开后加载摘要…

URL PDF HTML 收藏