Ke Fan

Interpretable Reinforcement Learning with Self-Abstraction and Refinement

SciTS: Scientific Time Series Understanding and Generation with LLMs

ReSIP: Reinforcement Learning with Symbolic Inductive Planning for Interpretable and Generalizable Pixel-Based Control

Continual Learning via Continual Weighted Sparsity and Meta-Plasticity Scheduling

Safety-Polarized and Prioritized Reinforcement Learning

Continual Learning via Continual Weighted Sparsity and Meta-Plasticity Scheduling