metadata
license: mit
Grounding Vision–Language–Action Models in Scientific Laboratories
Model Description
LabVLA is the first vision–language–action (VLA) model designed for scientific laboratory environments. It combines a Qwen3-VL-4B-Instruct vision–language backbone with a DiT flow-matching action expert, trained with the π0.5 recipe to enable real-time robot control in lab settings.
How to Use
Download
huggingface-cli download zjunlp/LabVLA --local-dir LabVLA
Deployment
Serve the model over the OpenPI msgpack WebSocket protocol:
git clone https://github.com/zjunlp/LabVLA.git
cd LabVLA
bash deployment/deploy.sh
For training, data preparation, and more details, please refer to our GitHub repository.