AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
Paper • 2605.12495 • Published • 27
Tianyi Lu
Fitz135
·
AI & ML interests
None yet
Recent Activity
published a dataset about 5 hours ago
ShareLab-SII/aloha2_pick_cube_426 upvoted a paper about 11 hours ago
AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable RewardOrganizations
upvoted a paper about 11 hours ago