Massachusetts Institute of Technology（麻省理工学院）

P-DRUM: Post-hoc Descriptor-based Residual Uncertainty Modeling for Machine Learning Potentials

Shih-Peng Huang, Nontawat Charoenphakdee, Yuta Tsuboi, Yong-Bin Zhuang, Wenwen Li

机构 * Massachusetts Institute of Technology（麻省理工学院） ； Preferred Networks 纠错

Comments Accepted to 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Machine Learning and the Physical Sciences (ML4PS)

Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning

Yurun Yuan, Fan Chen, Zeyu Jia, Alexander Rakhlin, Tengyang Xie

机构 * UW-Madison（威斯康星大学麦迪逊分校） ； MIT（麻省理工学院） 纠错

Comments NeurIPS 2025

What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models

Keyon Vafa, Sarah Bentley, Jon Kleinberg, Sendhil Mullainathan

机构 * Harvard University（哈佛大学） ； MIT（麻省理工学院） ； Cornell University（康奈尔大学） 纠错

Diverse Preference Learning for Capabilities and Alignment

Stewart Slocum, Asher Parker-Sartori, Dylan Hadfield-Menell

机构 * MIT CSAIL（麻省理工学院计算机科学与人工智能实验室） 纠错

Journal ref 13th International Conference on Learning Representations (ICLR 2025)