ICML - arXivDaily 期刊&会议

2506.12352 2025-08-20 cs.AI cs.LG stat.ML

Efficient Network Automatic Relevance Determination

Hongwei Zhang, Ziqi Ye, Xinyuan Wang, Xin Guo, Zenglin Xu, Yuan Cheng, Zixin Hu, Yuan Qi

机构 * School of Data Science, Fudan University, Shanghai, China（复旦大学数据科学学院）； Incubation Institute, Fudan University, Shanghai, China（复旦大学孵化院）； Shanghai Academy of Artificial Intelligence for Science, Shanghai, China（上海人工智能科学研究院）； Eberly College of Science, Pennsylvania State University, PA, United State（宾夕法尼亚州立大学科学学院）； Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, United Kingdom（剑桥大学应用数学与理论物理系）； Zhongshan Hospital, Fudan University, Shanghai, China（复旦大学中山医院）

Comments ICML 2025

2505.04104 2025-08-20 cs.LG cs.AI cs.CY

Position: We Need Responsible, Application-Driven (RAD) AI Research

Sarah Hartman, Cheng Soon Ong, Julia Powles, Petra Kuhnert

机构 * Tech \& Policy Lab, Law School, University of Western Australia, Australia ； College of Systems ； Society, Australian National University, Australia ； Centre for Business Research, University of Cambridge, United Kingdom

Comments 12 pages, 1 figure, Final Camera Ready version for proceedings with updated figure color and reference, Accepted to Proceedings of the 41 st International Conference on Machine Learning, Vancouver, Canada. PMLR 267, 2025

2504.16438 2025-08-20 cs.LG cs.AI cs.CR cs.DC

POPri: Private Federated Learning using Preference-Optimized Synthetic Data

Charlie Hou, Mei-Yu Wang, Yige Zhu, Daniel Lazar, Giulia Fanti

机构 * Pittsburgh Supercomputing Center, Pittsburgh, USA（匹兹堡超级计算中心）； Department of ECE, Carnegie Mellon University, Pittsburgh, PA（电子工程系，卡内基梅隆大学）

Comments ICML 2025 camera-ready

2502.20033 2025-08-20 cs.LG

Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization

Suryanarayana Sankagiri, Jalal Etesami, Matthias Grossglauser

机构 * EPFL（瑞士联邦理工学院）； TUM（慕尼黑工业大学）

Comments Accepted for publication in ICML 2025

2412.04140 2025-08-20 cs.LG cs.AI

Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes

Dongjae Jeon, Dueun Kim, Albert No

机构 * Department of Computer Science, Yonsei University, Seoul, Korea（计算机科学系，延世大学，首尔，韩国）； Department of Artificial Intelligence, Yonsei University, Seoul, Korea（人工智能系，延世大学，首尔，韩国）

Comments Accepted at ICML 2025 (Spotlight). Code: https://github.com/Dongjae0324/sharpness_memorization_diffusion

2508.13204 2025-08-20 cs.AI

QuickMerge++: Fast Token Merging with Autoregressive Prior

Dong Liu, Yanxuan Yu

机构 * Yale University（耶鲁大学）； Columbia University（哥伦比亚大学）

Comments The paper has been accepted to ICML Tokshop at https://openreview.net/forum?id=dMdxHd0tRf