Add model card and robotics pipeline tag

README.md

@@ -0,0 +1,19 @@
+---
+pipeline_tag: robotics
+---
+
+# WSA-Large-LIBERO
+
+WSA-Large-LIBERO is a 3D-Centric World-Spatial-Action Model fine-tuned on the LIBERO benchmark, introduced in the paper:
+**[WSA$_1$: a 3D-Centric World-Spatial-Action Model for Generalizable Robot Control](https://huggingface.co/papers/2607.03941)**.
+
+* **Project Page:** https://zaleni.github.io/WSA1/
+* **Repository:** https://github.com/zaleni/WSA
+
+## Model Description
+WSA is an embodied foundation model built upon a 3D-Centric World-Spatial-Action modeling paradigm. It unifies instruction-aligned 2D visual planning, action-conditioned 3D world modeling, and 3D-aware action generation, allowing for robust behavior generalization on both simulation and real-world robot control tasks.
+
+This checkpoint corresponds to the **WSA-Large (6B)** variant (based on the Wan2.2-TI2V-5B backbone) fine-tuned on the LIBERO dataset.
+
+## Installation & Evaluation
+For codebase setup, evaluation workflows, and training instructions, please refer to the official [WSA GitHub Repository](https://github.com/zaleni/WSA).