| pipeline_tag: robotics | |
| # WSA₁: A 3D-Centric World-Spatial-Action Model for Generalizable Robot Control | |
| WSA₁ is an embodied foundation model that introduces **World-Spatial-Action** modeling to unify instruction-aligned 2D visual planning, action-conditioned 3D world modeling, and 3D-aware action generation. | |
| - **Paper:** [WSA₁: a 3D-Centric World-Spatial-Action Model for Generalizable Robot Control](https://huggingface.co/papers/2607.03941) | |
| - **Project Page:** [https://zaleni.github.io/WSA1/](https://zaleni.github.io/WSA1/) | |
| - **Repository:** [https://github.com/zaleni/WSA](https://github.com/zaleni/WSA) | |
| ## Overview | |
| WSA₁ learns a shared 2D-3D latent space that connects instruction-aligned visual planning, action-conditioned 3D world prediction, and 3D-aware action generation. It delivers high manipulation performance across simulation environments (such as RoboTwin 2.0 and LIBERO) and real-world robot control tasks. | |
| For environment setup, pretraining, fine-tuning, and evaluation workflows, please refer to the official [GitHub repository](https://github.com/zaleni/WSA). |