University of California, San Diego（加州大学圣迭戈分校）

2510.13055 2025-10-16 cond-mat.mtrl-sci cs.LG physics.chem-ph physics.comp-ph

Reciprocal Space Attention for Learning Long-Range Interactions

Hariharan Ramasubramanian, Alvaro Vazquez-Mayagoitia, Ganesh Sivaraman, Atul C. Thakur

机构 * Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213（机械工程系，卡内基梅隆大学）； Computational Science Division, Argonne National Laboratory, Lemont, IL 60439（计算科学 division，阿贡国家实验室）； Department of Materials Design and Innovation, University at Buffalo, Buffalo, NY 14260（材料设计与创新系，布法罗大学）； Aiiso Yufeng Li Family Department of Chemical and Nano Engineering, University of California, San Diego, CA 92093（李艾索家庭化学与纳米工程系，加州大学圣地亚哥分校）

Comments 13 pages including references with 6 figures and 1 table

2510.12803 2025-10-16 cs.SE cs.AI cs.CL cs.PL

AutoCode: LLMs as Problem Setters for Competitive Programming

Shang Zhou, Zihan Zheng, Kaiyuan Liu, Zeyu Shen, Zerui Cheng, Zexing Chen, Hansen He, Jianzhu Yao, Huanzhi Mao, Qiuyang Mang, Tianfu Fu, Beichen Li, Dongruixuan Li, Wenhao Chai, Zhuang Liu, Aleksandra Korolova, Peter Henderson, Natasha Jaques, Pramod Viswanath, Saining Xie, Jingbo Shang

机构 * University of California San Diego（加州大学圣地亚哥分校）； New York University（纽约大学）； University of Washington（华盛顿大学）； Princeton University（普林斯顿大学）； University of California Berkeley（加州大学伯克利分校）； OpenAI ； Massachusetts Institute of Technology（麻省理工学院）； University of Waterloo（滑铁卢大学）； Sentient Labs

Comments Project page: https://livecodebenchpro.com/projects/autocode/overview

2510.02340 2025-10-16 cs.CL cs.LG

Can Prompts Rewind Time for LLMs? Evaluating the Effectiveness of Prompted Knowledge Cutoffs

Xin Gao, Ruiyi Zhang, Daniel Du, Saurabh Mahindre, Sai Ashish Somayajula, Pengtao Xie

机构 * UC San Diego（UC圣迭戈大学）； SUNY Buffalo（纽约州立大学布法罗分校）

Comments Published at EMNLP 2025; Code and data available at https://github.com/gxx27/time_unlearn