Zhangyuan Yu

RavenInJuly

https://github.com/Raven-July

Raven-July

AI & ML interests

None yet

Recent Activity

authored a paper about 1 month ago

CFPO: Counterfactual Policy Optimization for Multimodal Reasoning

updated a model about 1 month ago

RavenInJuly/CFPO-D-Qwen2.5-VL-3B

updated a model about 1 month ago

RavenInJuly/CFPO-G-Qwen2.5-VL-3B

View all activity

Organizations

None yet

Collections 2

Papers 1

arxiv:2606.23206

models 2

RavenInJuly/CFPO-G-Qwen2.5-VL-3B

Reinforcement Learning • 4B • Updated Jul 5 • 8

RavenInJuly/CFPO-D-Qwen2.5-VL-3B

Reinforcement Learning • 4B • Updated Jul 5 • 7

datasets 1

RavenInJuly/CFPO_Datasets

Preview • Updated Jul 5 • 122