NeurIPS - arXivDaily 期刊&会议

2606.12747 2026-06-12 cs.AI 新提交

Prefill Awareness in Large Language Models

大型语言模型中的预填充感知

Andy Wang, Parv Mahajan, David Demitri Africa, Alexandra Souly, Jordan Taylor, Robert Kirk

机构 * Constellation University of Wisconsin-Madison（威斯康星大学麦迪逊分校星座研究所）； Constellation Georgia Institute of Technology（佐治亚理工学院星座研究所）； UK AI Security Institute（英国人工智能安全研究所）

AI总结研究大型语言模型能否识别并响应其助手消息被预填充或篡改，发现前沿模型具有显著预填充感知能力，可能影响安全评估方法。

Comments Submitted to NeurIPS 2026

2509.03340 2026-06-12 cs.LG cs.AI cs.CE physics.comp-ph 版本更新

Equivariant Flow Matching for Symmetry-Breaking Bifurcation Problems

等变流匹配用于对称破缺分岔问题

Fleur Hendriks, Ondřej Rokoš, Martin Doškář, Marc G. D. Geers, Vlado Menkovski

机构 * Department of Mechanical Engineering, Eindhoven University of Technology（埃因霍温理工大学机械工程系）； DIFFER – Dutch Institute for Fundamental Energy Research（荷兰基础能源研究所）； Faculty of Civil Engineering, Department of Mechanics, Czech Technical University in Prague（布拉格捷克技术大学土木工程学院力学系）； Department of Mathematics and Computer Science, Eindhoven University of Technology（埃因霍温理工大学数学与计算机科学系）

AI总结针对非线性动力系统中对称破缺导致的多稳态共存问题，提出等变流匹配方法，结合等变架构与最优传输耦合机制，准确捕捉多模态分布和对称破缺分岔，优于非概率和变分方法。

Comments 9 pages, 7 figures including appendices. Accepted to Machine Learning and the Physical Sciences Workshop, NeurIPS 2025 (https://ml4physicalsciences.github.io/2025/). Repository with corresponding code: https://github.com/FHendriks11/bifurcationML/. Video explanation: https://www.youtube.com/watch?v=wsL3h17KtjY