Nan Jiang

6 papers University of Illinois at Urbana-Champaign

• A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning
• A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning
• Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
• Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol
• Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL
• Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction