Vision-OPD — Project Page

Bilingual (EN / 中文) project page for Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation.

🔗 Live: https://visionopd.github.io/ 📄 Paper: https://arxiv.org/abs/2605.18740 💻 Code: https://github.com/VisionOPD/Vision-OPD