MMODELYST
People/Tong Zheng
PPL

Tong Zheng

Papers (4)
G-Zero: Self-Play for Open-Ended Generation from Zero DataDeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and VerificationReinforcing Multimodal Reasoning Against Visual DegradationLLMs Improving LLMs: Agentic Discovery for Test-Time Scaling