Papers
Deep, long-form breakdowns of recent research in AI, machine learning, security & programming languages.
Exact Topological Compliance: Generating Persistence-Equivalent Graphs
by Mattie Ji, Indradyumna Roy, Vikas Garg
Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards
by Yuante Li, Junwei Quan, Kai Qiu, Kate Zhang, Yicheng Tao
MFG: Multi-turn Feedback Guided Molecular Optimization
by Trieu Nguyen, Frazier N. Baker, Ruoxi Gao, Daniel Adu-Ampratwum, Xia Ning
Who Improves the Robot? Toward Physical Recursive Self-Improvement
by Hai Zhou, Fan Yang, Zeyi Chen, Lejun Zhang, Chenyang Fu, Jianping Li, Jiayi Zhu, Xianyang Liu, Yingxuan Yang, Lili Meng, Lu Wang, Xinyang Han, Jiankai Sun, Weirui Ye, Guanchu Wang, Wanhua Li, Ming Zhou, Boyi Li, Ming Jin, Kun Shao, Muhao Chen, Guang Chen, Lei Ma, Joey Tianyi Zhou, Costas Spanos, Xia Hu, Mac Schwager, Weinan Zhang, Qian Feng, Shangding Gu
Fast Rates for Offline Q-Learning with KL Regularization
by Yize Hao, Guangxin Jiang, Shuang Qiu
Can Language Models Play the Wikipedia Game?
by Alexander Hickey, Joanna Knight, James Bishop
AI Models Can Provably Hide Arbitrary Capabilities
by Andis Draguns, Sumeet Ramesh Motwani, Raymond Douglas, Christian Schroeder de Witt
Goal-Oriented Bundle Management and Flow Control for Deep-Space Communications via Reinforcement Learning
by Sajjad Baghaeea, Aimin Lib, Shanmugarajan Balasubramanian, Elif Uysal
Designing Protein Structures from Natural Language
by Joseph Lee, Yanjing Li, Bo Qiang, Gregory Lau, Allyson Ettinger, Noah A. Smith, Rory Donovan-Maiye, David Baker, Hanna Hajishirzi, Pang Wei Koh
Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stopping
by Danil Rudenko, Georgii Bulgakov, Nikolay Kartashev, Ivan Rubachev, Daniil Krasylnikov, Artem Babenko