Zongkai Liu

CPGD: Toward Stable Reinforcement Learning for Language Models

MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision

Distributional Reinforcement Learning for Large Language Models

Guiding Diffusion Models with Reinforcement Learning for Stable Molecule Generation

Conservative Offline Goal-Conditioned Implicit V-Learning