Peng Chen

Weak policies can achieve up to 18.6% better performance with PATS, a training framework that dynamically adapts guidance based on evolving policy needs.

A unified computational framework reveals how efficient computing can dramatically enhance medical image reconstruction across multiple imaging modalities.

CRAFT reduces traffic collisions and violations by over 30% by aligning local observations with global context in traffic simulations.

NOVA reduces silent failures in recommender systems by over 13x while boosting performance metrics by up to 2.02% in online A/B testing.

Multi-scale clustering can significantly improve anomaly detection accuracy by balancing reconstruction fidelity and generalization.