Skip to content

Latest commit

 

History

History
44 lines (35 loc) · 1.36 KB

File metadata and controls

44 lines (35 loc) · 1.36 KB

Thinking with Spatial Code for Physical-World Video Reasoning

Jieneng Chen*, Wenxin Ma*, Ruisheng Yuan*, Yunzhi Zhang*, Jiajun Wu†, Alan Yuille† Johns Hopkins University & Stanford University

Paper

Spatial Code — Transform visual scenes into structured, executable 3D representations for spatial reasoning.

🗓️ Release Timeline

Stay tuned!

  • arXiv paper — released on March 5arXiv:2603.05591
  • Codebase — releasing by March 17
  • Reinforcement training details — releasing by March 22
  • Reproducible models — releasing by March 31

📖 Citation

If you find this work useful, please consider citing:

@article{chen2025spatialcode,
  title={Thinking with Spatial Code for Physical-World Video Reasoning},
  author={Chen, Jieneng and Ma, Wenxin and Yuan, Ruisheng and Zhang, Yunzhi and Wu, Jiajun and Yuille, Alan},
  journal={arXiv preprint arXiv:2603.05591},
  year={2025}
}