Hengguang Zhou PRO

Dolphin42

·

https://hengguangzhou.github.io/

AI & ML interests

Multi-modal Multi-agent Systems

Recent Activity

upvoted a paper 8 days ago

How Far Can Coding Agents Go in Visual Generation?

submitted a paper 8 days ago

How Far Can Coding Agents Go in Visual Generation?

upvoted a paper 26 days ago

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

View all activity

Organizations

upvoted a paper 8 days ago

How Far Can Coding Agents Go in Visual Generation?

Paper • 2610.19025 • Published 23 days ago • 19

submitted a paper to Daily Papers 8 days ago

How Far Can Coding Agents Go in Visual Generation?

Paper • 2610.19025 • Published 23 days ago • 19

upvoted 2 papers 26 days ago

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

Paper • 2610.02967 • Published Oct 2 • 31

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

Paper • 2609.35433 • Published Sep 28 • 12

upvoted a paper about 1 month ago

ReCAST: Reward Credit Assignment across Timesteps for Online Diffusion Reinforcement

Paper • 2609.13425 • Published Sep 11 • 11