Zhijian Zhou

The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward

Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards

SIPO: Stabilized and Improved Preference Optimization for Aligning Diffusion Models

PUM-Net: Plastic Unified Memory Network with Associative Interaction for Long-Context State Space Models

Distributional Reinforcement Learning for Large Language Models

Unleashing Flow Policies with Distributional Critics

Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation

Guiding Diffusion Models with Reinforcement Learning for Stable Molecule Generation