VRPRM VRPRM: Process Reward Modeling via Visual Reasoning two-tiger/VRPRM-rl Image-Text-to-Text • 9B • Updated 6 days ago • 17 • 1 two-tiger/VRPRM-sft Image-Text-to-Text • 9B • Updated 6 days ago • 12 two-tiger/VRPRM-sft-data Viewer • Updated 6 days ago • 1.38k • 63 • 1
VRPRM VRPRM: Process Reward Modeling via Visual Reasoning two-tiger/VRPRM-rl Image-Text-to-Text • 9B • Updated 6 days ago • 17 • 1 two-tiger/VRPRM-sft Image-Text-to-Text • 9B • Updated 6 days ago • 12 two-tiger/VRPRM-sft-data Viewer • Updated 6 days ago • 1.38k • 63 • 1