Zhihan Liu

Agent Learning via Early Experience

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

Progressive LLM Alignments Using Two-Player Games

Provably Efficient and Practical Self-Play for Better LLM Alignment

How Can LLM Guide RL? A Value-Based Approach

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

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