IXCLab@Shanghai AI Lab

AI & ML interests

None defined yet.

Recent Activity

yuhangzang  authored a paper about 14 hours ago

Intern-S2-Preview: Scientific Agentic Foundation Model

yuhangzang  authored a paper about 14 hours ago

AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO

yuhangzang  authored a paper about 2 months ago

CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning

View all activity

Papers

G^2RPO: Granular GRPO for Precise Reward in Flow Models

View all Papers

Team members 5