Instructions to use zaleni/WSA-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use zaleni/WSA-Base with LeRobot:
- Notebooks
- Google Colab
- Kaggle
Add model card and robotics metadata
#1
by nielsr HF Staff - opened
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: robotics
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# WSA: A 3D-Centric World-Spatial-Action Model for Generalizable Robot Control
|
| 7 |
+
|
| 8 |
+
This repository contains the weights for **WSA-Base**, a 3D-centric World-Spatial-Action embodied foundation model for generalizable robot control.
|
| 9 |
+
|
| 10 |
+
- **Paper:** [WSA$_1$: a 3D-Centric World-Spatial-Action Model for Generalizable Robot Control](https://huggingface.co/papers/2607.03941)
|
| 11 |
+
- **Project Page:** [https://zaleni.github.io/WSA1/](https://zaleni.github.io/WSA1/)
|
| 12 |
+
- **Repository:** [https://github.com/zaleni/WSA](https://github.com/zaleni/WSA)
|
| 13 |
+
|
| 14 |
+
## Overview
|
| 15 |
+
|
| 16 |
+
WSA (World-Spatial-Action) is an embodied foundation model that unifies instruction-aligned 2D visual planning, action-conditioned 3D world modeling, and 3D-aware action generation into a shared latent space. WSA-Base utilizes a Qwen3-VL-2B backbone and is pre-trained on diverse datasets to enable data-efficient, generalizable robot manipulation.
|
| 17 |
+
|
| 18 |
+
For details on how to set up the environment, run inference, or perform downstream fine-tuning, please refer to the [official GitHub repository](https://github.com/zaleni/WSA).
|