Hengguang Zhou PRO

Dolphin42

·

https://hengguangzhou.github.io/

AI & ML interests

Multi-modal Multi-agent Systems

Recent Activity

upvoted a paper 17 days ago

Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards

upvoted a paper 17 days ago

ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning

upvoted a paper 27 days ago

ReCAST: Reward Credit Assignment across Timesteps for Online Diffusion Reinforcement

View all activity

Organizations

upvoted 2 papers 17 days ago

Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards

Paper • 2610.02967 • Published 24 days ago • 44

ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning

Paper • 2609.35433 • Published 28 days ago • 19

upvoted a paper 27 days ago

ReCAST: Reward Credit Assignment across Timesteps for Online Diffusion Reinforcement

Paper • 2609.13425 • Published Sep 11 • 11