Skip to content

About

Official implementation of our serial spatial intelligence robotc foundation model (SLA & Spatial Forcing[ICLR2026]).

Topics

Resources

Stars

424 stars

Watchers

3 watching

Forks

Latest commit

 

History

63 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SLA

🌟 SLA (Spatial-Language-Action Model) Paper · ProjectPage · HuggingFace

🌟 SF (Spatial Forcing) Paper · ProjectPage · HuggingFace

The core work of these projects is led by Fuhao Li and Wenxuan Song . For communication, We provide WeChat Group.

📢 News!

  • [Soon] We plan to release SLA v2 arXiv, with formal version instead of SLA-Preview on Robodojo and RoboCasa365 results and checkpoints.
  • [2026/11/07] We released SLA on ArXiv.
  • [2026/07/07] We got the first place on the generalization dimension and second place on the average of all 5 dimensions of the comprehensive embodied leaderboard RoboDojo.
  • [2026/01/27] Spatial Forcing is accepted by ICLR 2026!🎉
  • [2025/10/28] We released our codes based on Pi_0 in real world! Everyone is welcome to use it!🎉
  • [2025/10/24] 🏆 Congradulations to Jialong! He and our SF got the second place in Agibot World Challenge as well as 5000$ prize💰!
  • [2025/10/18] Spatial Forcing won the 🥇first place in the daily list and 🥉third place in the weekly list in HF! ⭐
  • [2025/10/12] We released Spatial Forcing on ArXiv.

🚀 Get Started

SLA has become a superior replacement for Spatial Forcing. We recommand to use SLA in most cases.

  • (SLA) To reproduce SLA simulation and real-world results and deployments, ref to our SLA folder.

  • (Spatial Forcing) To reproduce SF simulation results, ref to our openvla-SF folder.

  • (Spatial Forcing) To deploy SF policy in real-world robots, ref to our openpi-SF folder.

🌏 Contact

For further discussion and collaboration, please feel free to contact us via Email and WeChat:

Author Email WeChat
Fuhao Li fli481@connect.hkust-gz.edu.cn haofuly
Wenxuan Song songwenxuan0115@gmail.com swx0757

❤️ Acknowledgement

We thank these great works and open-source codebases: OpenVLA-OFT & OpenPI & VGGT & REPA & OmniVGGT.

🖊 Citation

If you find this work useful, please cite:

@article{sla2026,
  title     = {SLA: Scaling Spatial-Language-Action Model via Continual Pre-training},
  author    = {Li, Fuhao and Song, Wenxuan and Huang, Qizhou and Zhou, Ziyang and Wang, Jingbo and E, Junwu and Wang, Pengwei and Wang, Yan and Zhou, Shunbo and Li, Haoang},
  journal   = {arXiv preprint arXiv:2611.08373},
  year      = {2026}
}
@article{spatialforcing2025,
  title     = {Spatial Forcing: Implicit Spatial Representation Alignment For Vision-Language-Action Model},
  author    = {Li Fuhao, Song Wenxuan, Zhao Han, Wang Jingbo, Ding Pengxiang, Wang Donglin, Zeng Long, Li Haoang},
  journal   = {arXiv preprint arXiv:2510.12276},
  year      = {2025},
}

About

Official implementation of our serial spatial intelligence robotc foundation model (SLA & Spatial Forcing[ICLR2026]).

Topics

Resources

Stars

424 stars

Watchers

3 watching

Forks

Releases

Packages

Contributors

Languages