Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos

Yicheng Feng^1,3, Wanpeng Zhang^1,3, Ye Wang^2,3, Hao Luo^1,3, Haoqi Yuan^1,3,
Sipeng Zheng³, Zongqing Lu^1,3†

¹Peking University    ²Renmin University of China    ³BeingBeyond

VIPA-VLA learns 2D–to–3D visual–physical grounding from human videos with spatial-aware VLA pretraining, enabling robot policies with stronger spatial understanding and generalization.

News

• [2025-12-15]: We publish VIPA-VLA! Check our paper here. Code is coming soon! 🔥🔥🔥

Citation

If you find our work useful, please consider citing us and give a star to our repository! 🌟🌟🌟

@article{feng2025vipa,
  title={Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos},
  author={Feng, Yicheng and Zhang, Wanpeng and Wang, Ye and Luo, Hao and Yuan, Haoqi and  Zheng, Sipeng and Lu, Zongqing},
  journal={arXiv preprint arXiv:2512.13080},
  year={2025}
}