AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
Paper • 2605.12495 • Published • 27
Minbin Huang
centaurus-alpha
AI & ML interests
None yet
Recent Activity
upvoted a paper about 16 hours ago
AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward upvoted a paper 1 day ago
Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning commentedon a paper 6 days ago
UniPool: A Globally Shared Expert Pool for Mixture-of-ExpertsOrganizations
None yet