# GraspVLA (Galbot), brain

Galbot's grasping foundation model, GraspVLA (launched Jan 2025): an end-to-end Vision-Language-Action model pre-trained on SynGrasp-1B, a billion-frame synthetic grasping dataset with photorealistic rendering and domain randomization. Enables zero-shot generalization to new grasping tasks without additional training, powering dexterous manipulation on Galbot's robots.

- **Slug:** graspvla
- **Type:** Foundation model
- **Maturity (DEPLOY ladder):** Research
- **Open source:** no

## Developed by (1)

- [Galbot](/companies/galbot.md)


## Powers (1)

- [Galbot G1](/models/galbot-g1.md) (Galbot)


## Sources (2)

1. **GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data (arXiv)** · https://arxiv.org/abs/2505.03233
2. **Galbot raises $151M to scale embodied-AI humanoid robots** · https://roboticsandautomationnews.com/2025/07/03/galbot-raises-151-million-to-scale-embodied-ai-humanoid-robots-partners-with-bosch-investment-arm/92864/


_API: GET /v1/brains/6ab6bd66-6794-4509-bb25-12479104d5a2 · canonical URL: /brains/graspvla_