Hugging Face's logo

PAPOGalaxy
/
PAPO-H-Qwen2.5-VL-3B

Safetensors
Model card Files
xet
Community
1

PAPO Model

Model Source

This is the official model released for paper PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning (arxiv.org/abs/2507.06448)

Model Version

PAPO-H (γ=0.02)

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train PAPOGalaxy/PAPO-H-Qwen2.5-VL-3B

Collections including PAPOGalaxy/PAPO-H-Qwen2.5-VL-3B