Learning to Answer from Correct Demonstrations

Nathan Srebro
May 11, 2026

Fisher Random Walk: Automatic Preference Inference for Language Models

Junwei Lu
April 24, 2026

PPO Fine-Tuning of Diffusion Models: Provable Convergence across Interpolated Trajectories

Yingbin Liang
April 24, 2026

Stochastic Zeroth-Order Policy Optimization for RLHF

Lei Ying
April 24, 2026

What structures make model-free RL possible? an elliptic theory for controlled Markov diffusions

Wenlong Mou
April 23, 2026

Deterministic Policy Gradient for Reinforcement Learning with Continuous Time and Space

Xin Guo
April 23, 2026

Optimal offline policy learning under unknown confounding factors

Zhimei Ren
April 23, 2026

Toward efficient exploration for language models

Dylan Foster
April 23, 2026

On the Learning Dynamics of RLVR at the Edge of Competence

Yuejie Chi
April 22, 2026