CFPO - a RavenInJuly Collection

RavenInJuly 's Collections

CFPO

updated 8 days ago

CFPO: Counterfactual Policy Optimization for Multimodal Reasoning

Paper • 2606.23206 • Published 22 days ago
RavenInJuly/CFPO-G-Qwen2.5-VL-3B

Reinforcement Learning • 4B • Updated 8 days ago • 40
RavenInJuly/CFPO-D-Qwen2.5-VL-3B

Reinforcement Learning • 4B • Updated 8 days ago • 35
RavenInJuly/CFPO_Datasets

Preview • Updated 8 days ago • 133