Back to List
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
Pythonom-ai-lab/VLM-R1

VLM-R1

Solve Visual Understanding with Reinforced VLMs

55.4/100
5.9KForks: 377
View on GitHub
Loading report...

Similar Projects

Skywork-R1V

62

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.

Python3.2K

ms-swift

88

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...) (AAAI 2025).

Python13.0K

ART

90

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

Python9.0K

xtuner

86

A Next-Generation Training Engine Built for Ultra-Large MoE Models

Python5.1K
Back to List