Biscue5/pi0-egoscaler-v2

This model accompanies our work on Developing Vision-Language-Action Model from Egocentric Videos.

• 🌐 Project page: https://biscue5.github.io/egovla-project-page/
• 📄 Paper: Developing Vision-Language-Action Model from Egocentric Videos (arXiv:2509.21986)
• 🧰 Format: LeRobot v2.0
• 🪪 License: Apache-2.0

---

Citation

If you use this dataset, please cite:

@article{yoshida2025developing,
  title   = {Developing Vision-Language-Action Model from Egocentric Videos},
  author  = {Yoshida, Tomoya and Kurita, Shuhei and Nishimura, Taichi and Mori, Shinsuke},
  journal = {arXiv preprint arXiv:2509.21986},
  year    = {2025}
}