Tengyang Xie

Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits

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

Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective

Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF

Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization

Reinforce LLM Reasoning through Multi-Agent Reflection

Towards Principled Representation Learning from Videos for Reinforcement Learning

Harnessing Density Ratios for Online Reinforcement Learning