V
VLM-R1
om-ai-lab/VLM-R1
Solve Visual Understanding with Reinforced VLMs
★6.0kstars
Python
Apache-2.0
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?Models project leveraging deepseek-r1 and grpo, built with Python, open-source
Who made it?Maintained by om-ai-lab team, 6K⭐ on GitHub, #249 out of 3201 in Models
Why does it exist?The om-ai-lab team recognized that existing deepseek-r1 tools in Models were hard to use. VLM-R1 was designed to make grpo more accessible.
What can it do?Key use cases: llm, multimodal, multimodal-r1
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/om-ai-lab/VLM-R1
🔗 github.com/om-ai-lab/VLM-R1
Topics
deepseek-r1grpollmmultimodalmultimodal-r1qwenr1-zeroreinforcement-learningvlmvlm-r1