Leitian Tao

RESTRAIN: From Spurious Votes to Signals — Self-Training RL with Self-Penalization

Hybrid Reinforcement: when reward is sparse, better to be dense

The Era of Real-World Human Interaction: RL from User Conversations

Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis

Your Weak LLM is Secretly a Strong Teacher for Alignment

CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement

How Reliable Is Human Feedback For Aligning Large Language Models?