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~~

高校专区

University of Washington(华盛顿大学)

2026-02-26 至 2026-02-26 共收录 5
2412.06966 2026-02-26 cs.LG cs.AI cs.CY

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research

机器去学习并不如你所想:生成式AI政策与研究的启示

A. Feder Cooper, Christopher A. Choquette-Choo, Miranda Bogen, Kevin Klyman, Matthew Jagielski, Katja Filippova, Ken Liu, Alexandra Chouldechova, Jamie Hayes, Yangsibo Huang, Eleni Triantafillou, Peter Kairouz, Nicole Elyse Mitchell, Niloofar Mireshghallah, Abigail Z. Jacobs, James Grimmelmann, Vitaly Shmatikov, Christopher De Sa, Ilia Shumailov, Andreas Terzis, Solon Barocas, Jennifer Wortman Vaughan, danah boyd, Yejin Choi, Sanmi Koyejo, Fernando Delgado, Percy Liang, Daniel E. Ho, Pamela Samuelson, Miles Brundage, David Bau, Seth Neel, Hanna Wallach, Amy B. Cyphert, Mark A. Lemley, Nicolas Papernot, Katherine Lee

机构 * The GenLaw Center(GenLaw中心) Microsoft Research(微软研究院) Stanford University(斯坦福大学) Google DeepMind(谷歌DeepMind) Center for Democracy & Technology(民主与科技中心) Princeton(普林斯顿) Google(谷歌) University of Washington(华盛顿大学) University of Michigan(密歇根大学) Cornell Tech(康奈尔科技) Cornell Law School(康奈尔法学院) Cornell University(康奈尔大学) Lighthouse Stanford Law School(斯坦福法学院) UC Berkeley(伯克利大学) Independent(独立研究者) Northeastern University(东北大学) Harvard Business School(哈佛商学院) W. Virginia University College of Law(维珍尼亚大学法学院)

AI总结 本文指出机器去学习并非通用解决方案,揭示其在生成式AI政策与研究中的局限性。

Comments NeurIPS 2025 (Oral)

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.21442 2026-02-26 cs.LG cs.AI

MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning

MINAR: 图神经网络中神经算法推理的机制可解释性

Jesse He, Helen Jenne, Max Vargas, Davis Brown, Gal Mishne, Yusu Wang, Henry Kvinge

机构 * Pacific Northwest National Laboratory, Richland, WA(太平洋西北国家实验室) Halıcıoğlu Data Science Institute, University of California, San Diego, San Diego, CA(哈利奇奥格鲁数据科学研究所,加州大学圣地亚哥分校) Department of Computer and Information Science, University of Pennsylvania, Pennsylvaina, PA(计算机与信息科学系,宾夕法尼亚大学) Department of Mathematics, University of Washington, Seattle, WA(数学系,华盛顿大学)

AI总结 MINAR是一种用于图神经网络中神经算法推理的机制可解释性工具,通过归因修补方法发现电路,揭示训练过程中的电路形成和剪枝机制。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.13551 2026-02-26 cs.CL

Small Reward Models via Backward Inference

通过反向推理的小奖励模型

Yike Wang, Faeze Brahman, Shangbin Feng, Teng Xiao, Hannaneh Hajishirzi, Yulia Tsvetkov

机构 * University of Washington(华盛顿大学) Allen Institute for Artificial Intelligence(人工智能研究院)

AI总结 FLIP通过反向推理实现无需参考和评分标准的奖励建模,在多个领域中显著提升性能并增强鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.22037 2026-02-26 cs.CL cs.LG

ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality

ATLAS:适应性迁移缩放定律用于多语言预训练、微调和解码的多语言诅咒

Shayne Longpre, Sneha Kudugunta, Niklas Muennighoff, I-Hung Hsu, Isaac Caswell, Alex Pentland, Sercan Arik, Chen-Yu Lee, Sayna Ebrahimi

机构 * MIT(麻省理工学院) University of Washington(华盛顿大学) Stanford University(斯坦福大学) Google Cloud AI(谷歌云人工智能) Google DeepMind(谷歌DeepMind)

AI总结 ATLAS提出了一种适应性迁移缩放定律,用于多语言预训练、微调和解码,解决了多语言学习中的性能瓶颈和计算优化问题。

Comments Published as a conference paper at ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.10947 2026-02-26 cs.AI cs.LG

Spurious Rewards: Rethinking Training Signals in RLVR

虚假奖励:重新思考强化学习中的训练信号

Rulin Shao, Shuyue Stella Li, Rui Xin, Scott Geng, Yiping Wang, Sewoong Oh, Simon Shaolei Du, Nathan Lambert, Sewon Min, Ranjay Krishna, Yulia Tsvetkov, Hannaneh Hajishirzi, Pang Wei Koh, Luke Zettlemoyer

机构 * University of Washington, Seattle, WA, USA(华盛顿大学) Allen Institute for Artificial Intelligence, Seattle, WA, USA(人工智能研究院) University of California, Berkeley, Berkeley, CA, USA(加州大学伯克利分校)

AI总结 该研究发现,即使使用随机分配的虚假奖励,强化学习方法也能在某些模型上显著提升性能,凸显了验证训练信号的重要性。

详情

展开后加载摘要…

URL PDF HTML 收藏