Sealbook

Osilly/Vision-R1

[ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incentivize reasoning capability.

License & maintenance

No license stated: by default nobody may reuse the code. Ask the authors before using it in a product.

Last code push 7 months ago.