---
title: G0-VLA
canonical_url: "https://www.modelscope.cn/models/Galaxea/G0-VLA"
md_url: "https://www.modelscope.cn/models/Galaxea/G0-VLA.md"
repository: Galaxea/G0-VLA
last_updated: 2025-09-10
license: CC-BY-NC-SA-4.0
pipeline_tag: robotics
tasks:
  - robotics
library_name:
  - pytorch
frameworks:
  - Pytorch
downloads: 49
stars: 1
---

# G0-VLA

> G0-VLA - Galaxea 在 ModelScope 开源的模型。🚀 Galaxea Open-World Dataset and G0 Dual-System VLA Model

Galaxea/G0-VLA 是 ModelScope 魔搭社区上的robotics模型，采用 CC-BY-NC-SA-4.0 许可。

- **Repository**: Galaxea/G0-VLA
- **License**: CC-BY-NC-SA-4.0
- **Tasks**: robotics
- **Downloads**: 49
- **Stars**: 1
- **Last updated**: 2025-09-10

Source: https://www.modelscope.cn/models/Galaxea/G0-VLA

---

# 🚀 Galaxea Open-World Dataset and G0 Dual-System VLA Model
[![Project Page](https://img.shields.io/badge/Project%20Page-000000?style=for-the-badge&logo=github)](https://opengalaxea.github.io/G0/)
[![Paper](https://img.shields.io/badge/Paper-8A2BE2?style=for-the-badge&logo=arxiv)](https://arxiv.org/abs/2509.00576)
[![Videos](https://img.shields.io/badge/Videos-FF0000?style=for-the-badge&logo=youtube)](https://opengalaxea.github.io/G0/)
[![Visualizer](https://img.shields.io/badge/Visualizer-FF8C00?style=for-the-badge&logo=airplayvideo)](https://opengalaxea.github.io/G0/visualizer/index.html)
[![Huggingface](https://img.shields.io/badge/Huggingface-FF6B35?style=for-the-badge&logo=huggingface)](https://huggingface.co/OpenGalaxea)
[![Twitter](https://img.shields.io/badge/Twitter-FF6B35?style=for-the-badge&logo=x)](https://x.com/Galaxea_x)
[![Linkedin](https://img.shields.io/badge/Linkedin-1890FF?style=for-the-badge&logo=linkedin)](https://www.linkedin.com/company/galaxeadynamics/posts/?feedView=all&viewAsMember=true)


G0-VLA architecture and training pipeline: Stage 1 pre-trains a vision-language model on cross-embodiment data in an autoregressive manner. Stage 2 and post-train share the same model structure, trained on Galaxea open-world data with embodiment-specific views and high-level and subtask instructions, by supervising the Action Transformer’s action reconstruction with a flow- matching loss.


![image/png](https://cdn-uploads.huggingface.co/production/uploads/6788b21b8d4696a61ff6002c/eK9_KN0mQZArYrvGZYlIB.png)


In this repo, you can find:
- [x] model_pre.pt: **Model Weights after Stage2 Pretraining**  




## 📜 Citation

All the data and code within this repo are under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/). If you use our dataset or models, please cite:

```bibtex
@article{galaxea2025,
  title={Galaxea G0: Open-World Dataset and Dual-System VLA Model},
  author={Galaxea Team},
  journal={arXiv preprint arXiv:2509.00576},
  year={2025}
}