Cheng Chen

Bures-Isotropy Alignment: Manifold Learning of Generalized Category Discovery

DREAM: Decoupled Reinforcement Learning with Reward Measurement for Large Language Model Test-time Training

REFLEX-Med: Reinforcement for Label-Free Explainability in Unified Medical Reasoning

Gestalt Generalized Category Discovery

Retrieval Instead of Fine-tuning: A Retrieval-based Parameter Ensemble for Zero-shot Learning

Learning Under Multi-dimensional Domain Shifts: A Ensemble of Mixtures of Experts Approach