Shenao Zhang

Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning

Learning to Reason as Action Abstractions with Scalable Mid-Training RL

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

How Can LLM Guide RL? A Value-Based Approach

Provably Efficient and Practical Self-Play for Better LLM Alignment

Self-Exploring Language Models: Active Preference Elicitation for Online Alignment

Hindsight Planner: A Closed-loop few-shot planner for Embodied Instruction Following