| FALCON | From Spatial to Actions:
Grounding Vision-Language-Action Model in Spatial Foundation Priors (ICLR 2026)

Zhengshen Zhang   Hao Li   Yalun Dai   Zhengbang Zhu   Lei Zhou  
Chenchen Liu   Dong Wang   Francis E. H. Tay   Sijin Chen  
Ziwei Liu   Yuxiao Liu^*†   Xinghang Li^*   Pan Zhou^*  

^*Corresponding Author  ^†Project Lead

ByteDance Seed
National University of Singapore   Nanyang Technological University
Tsinghua University   Singapore Management University

---

Updates 🚀🚀🚀

• [26/01/2026] 🎊 Thrilled to share that our paper has been accepted to ICLR 2026! Code will be open-sourced soon. Stay tuned!

• [20/10/2025] Existing vision-language-action (VLA) models act in 3D real-world but are typically built on 2D encoders, leaving a spatial reasoning gap that limits generalization and adaptability. In this work, we introduce FALCON (From Spatial to Action), a novel paradigm that injects rich 3D spatial tokens into the action head of a VLA model, enabling robust spatial understanding and SOTA performance across diverse manipulation tasks without disrupting vision-language alignment. See our paper at here.

Contents

• Benchmark Performance Comparison
• TODO List
• Citation

💪 Benchmark Performance Comparison

CALVIN Benchmark

SimplerEnv WidowX Robot Experiments

SimplerEnv Google Robot Experiments

Real-World Experiments

💡 For more sim/real-world benchmark results, please refer to our paper.

🗒️ TODO List

• Release the code, model of FALCON.
• Release the CALVIN & SimplerEnv evaluation code and model weights for FALCON series.
• Release pre-training / fine-tuning code for FALCON series.
• Release the code for real-world deployment of FALCON via ManiUniCon.

🖊️ Citation

If you find this project useful in your research, please consider cite:

@article{zhang2025spatial,
  title={From spatial to actions: Grounding vision-language-action model in spatial foundation priors},
  author={Zhang, Zhengshen and Li, Hao and Dai, Yalun and Zhu, Zhengbang and Zhou, Lei and Liu, Chenchen and Wang, Dong and Tay, Francis EH and Chen, Sijin and Liu, Ziwei and others},
  journal={arXiv preprint arXiv:2510.17439},
  year={2025}
}