arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

期刊&会议

International Conference on Machine Learning · 会议 · Machine Learning

2025-09-03 至 2025-09-03 共收录 5
2509.01433 2025-09-03 eess.IV cs.LG

Temporal Representation Learning for Real-Time Ultrasound Analysis

Yves Stebler, Thomas M. Sutter, Ece Ozkan, Julia E. Vogt

机构 * Department of Computer Science, ETH Zurich, Switzerland(苏黎世联邦理工学院计算机科学系) Department of Biomedical Engineering, University of Basel, Switzerland(巴塞尔大学生物医学工程系)

Comments ICMl 2025 Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00488 2025-09-03 cs.LG

Localizing and Mitigating Memorization in Image Autoregressive Models

Aditya Kasliwal, Franziska Boenisch, Adam Dziedzic

机构 * CISPA Helmholtz Center for Information Security(CISPA海德堡信息安全中心)

Comments Accepted at ICML 2025 Workshop on the Impact of Memorization on Trustworthy Foundation Models

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00083 2025-09-03 cs.LG cs.AI cs.CL

Data Cartography for Detecting Memorization Hotspots and Guiding Data Interventions in Generative Models

Laksh Patel, Neel Shanbhag

机构 * Illinois Mathematics and Science Academy(伊利诺伊数学与科学学院)

Comments 6 pages, 2 figures, 1 table; Presented at the 42nd International Conference on Machine Learning (ICML), winning the "Best Poster" award at ICML's workshop for data in generative models (DIG-BUGS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.09128 2025-09-03 stat.ML cs.LG

A Generalization Theory for Zero-Shot Prediction

Ronak Mehta, Zaid Harchaoui

机构 * University of Washington(华盛顿大学)

Comments Published at ICML '25 (Oral)

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.05304 2025-09-03 cs.LG cs.CV

Gaussian Mixture Flow Matching Models

Hansheng Chen, Kai Zhang, Hao Tan, Zexiang Xu, Fujun Luan, Leonidas Guibas, Gordon Wetzstein, Sai Bi

机构 * Stanford University(斯坦福大学) Adobe Research(Adobe研究)

Comments ICML 2025. Code: https://github.com/Lakonik/GMFlow

详情

展开后加载摘要…

URL PDF HTML 收藏