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

NeurIPS

Conference on Neural Information Processing Systems · 会议 · Machine Learning

2026-02-26 至 2026-02-26 共收录 4
2506.19881 2026-02-26 cs.CR cs.CY cs.LG

Blameless Users in a Clean Room: Defining Copyright Protection for Generative Models

清洁房间中的无责用户:为生成模型定义版权保护

Aloni Cohen

机构 * Department of Computer Science University of Chicago(计算机科学系芝加哥大学)

AI总结 本文提出清洁房间版权保护框架,通过定义无责版权保证,解决生成模型训练数据版权侵权问题,并证明差分隐私在特定条件下可保障版权保护。

Comments Appeared at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.19610 2026-02-26 cs.CV

JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models

JailBound: 视觉语言模型内部安全边界的劫持

Jiaxin Song, Yixu Wang, Jie Li, Rui Yu, Yan Teng, Xingjun Ma, Yingchun Wang

机构 * Shanghai Jiao Tong University(上海交通大学) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Fudan University(复旦大学) Xuan Tong(宣通) NSFOCUS

AI总结 JailBound通过在视觉语言模型的潜在空间中探索安全边界,提出了一种新的劫持框架,有效提升了白盒和黑盒攻击成功率,揭示了模型的安全风险。

Comments The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
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
2602.21467 2026-02-26 cs.LG

Geometric Priors for Generalizable World Models via Vector Symbolic Architecture

基于向量符号架构的几何先验用于通用世界模型

William Youngwoo Chung, Calvin Yeung, Hansen Jin Lillemark, Zhuowen Zou, Xiangjian Liu, Mohsen Imani

机构 * University of California Irvine(加州大学伊文斯分校) University of California San Diego(加州大学圣地亚哥分校)

AI总结 本文提出基于向量符号架构的几何先验方法,通过学习复数空间的群结构,实现高效且可解释的世界模型,提升多步组合和泛化能力。

Comments 9 pages, accepted to Neurips 2025 Workshop Symmetry and Geometry in Neural Representations

详情

展开后加载摘要…

URL PDF HTML 收藏