Haolin Liu

An Improved Model-free Decision-estimation Coefficient with Applications in Adversarial MDPs

Moving Out: Physically-grounded Human-AI Collaboration

On the Evolution of Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models

One Token to Fool LLM-as-a-Judge

Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback

Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback

Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification