Wen Sun

5 papers Cornell University and Databricks

• $Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
• Accelerating RL for LLM Reasoning with Optimal Advantage Regression
• Avoiding exp(R) scaling in RLHF through Preference-based Exploration
• Scaling Offline RL via Efficient and Expressive Shortcut Models
• Value-Guided Search for Efficient Chain-of-Thought Reasoning