Tian Lan

Lipschitz-Guided Monte Carlo Tree Search with Knowledge Transfer across Sequential Tasks

MINT: Minimal Information Neuro-Symbolic Tree for Objective-Driven Knowledge-Gap Reasoning and Active Human Elicitation

GUARD: Gold-Unchanged Anchored Distillation for Defending LLMs Against Membership Inference Attacks

MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning

Offline Reinforcement Learning with Closed-loop Policy Evaluation and Diffusion World-Model Adaptation

Federated Maximum Likelihood Inverse Reinforcement Learning with Convergence Guarantee