---
title: WB-WAM
emoji: 🤖
colorFrom: blue
colorTo: blue
sdk: static
pinned: false
---

<div align="center">

<h1 style="line-height: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.35); margin-bottom: 0.4em;"><img src="https://huggingface.co/spaces/WB-WAM/README/resolve/main/assets/wbwam_logo_white.png" alt="WB-WAM" width="280" style="max-width: 100%; height: auto; margin-bottom: 0;" /></h1>

<p style="font-size: 1.15em; margin-top: 0;"><strong>Heterogeneous Body–Hand Pre-training for Humanoid Loco-Manipulation</strong></p>

<div style="display: flex; justify-content: center; align-items: center; gap: 8px; flex-wrap: nowrap; overflow-x: auto;">
<a target="_blank" rel="noopener noreferrer" href="https://arxiv.org/abs/2609.34199"><img src="https://img.shields.io/badge/arXiv-Paper-b31b1b?style=flat-square&logo=arxiv&logoColor=white" alt="arXiv" /></a>
<a target="_blank" rel="noopener noreferrer" href="https://wb-wam.github.io/"><img src="https://img.shields.io/badge/Project-Page-1f6feb?style=flat-square&logo=googlechrome&logoColor=white" alt="Project Page" /></a>
<a target="_blank" rel="noopener noreferrer" href="https://github.com/WB-WaM/WB-WAM-Official"><img src="https://img.shields.io/badge/GitHub-Code-181717?style=flat-square&logo=github&logoColor=white" alt="GitHub" /></a>
<a target="_blank" rel="noopener noreferrer" href="https://www.apache.org/licenses/LICENSE-2.0"><img src="https://img.shields.io/badge/License-Apache%202.0-4c1?style=flat-square" alt="License: Apache 2.0" /></a>
<a target="_blank" rel="noopener noreferrer" href="https://huggingface.co/spaces/WB-WAM/README/blob/main/README_zh.md"><img src="https://img.shields.io/badge/Language-%E4%B8%AD%E6%96%87-6b7280?style=flat-square" alt="中文" /></a>
</div>

<img src="https://huggingface.co/spaces/WB-WAM/README/resolve/main/teaser.webp" width="100%" style="width: 100%; height: auto;" alt="WB-WAM project teaser" />

</div>

WB-WAM is a world-action model for whole-body humanoid loco-manipulation. It unifies body, root, and dexterous-hand supervision and learns visual dynamics together with whole-body actions.