VGPO-RL - a MuMing0102 Collection

MuMing0102 's Collections

VGPO-RL

updated 4 days ago

[ACL 2026] Visually-Guided Policy Optimization for Multimodal Reasoning

Visually-Guided Policy Optimization for Multimodal Reasoning

Paper • 2604.09349 • Published Apr 10 • 2
MuMing0102/VGPO-RL-7B

Image-Text-to-Text • 8B • Updated 28 days ago • 24
MuMing0102/VGPO-RL-32B

Image-Text-to-Text • 33B • Updated 28 days ago • 24