--- license: apache-2.0 datasets: - BAAI-Humanoid/MOSAIC_Dataset pipeline_tag: reinforcement-learning tags: - humanoid - motion-tracking - teleoperation - reinforcement-learning arxiv: 2602.08594 --- # MOSAIC Model [**Project Page**](https://baai-humanoid.github.io/MOSAIC/) | [**Paper**](https://arxiv.org/abs/2602.08594) | [**Code**](https://github.com/BAAI-Humanoid/MOSAIC) | [**Dataset**](https://huggingface.co/datasets/BAAI-Humanoid/MOSAIC_Dataset) | [**Model**](https://huggingface.co/BAAI-Humanoid/MOSAIC_Model) This repository releases **deployment-ready ONNX models** for **MOSAIC**, introduced in: **[MOSAIC: Bridging the Sim-to-Real Gap in Generalist Humanoid Motion Tracking and Teleoperation with Rapid Residual Adaptation](https://arxiv.org/abs/2602.08594)** In MOSAIC, a **general motion tracker** is trained in simulation, and **interface-specific adaptation** is handled via a lightweight **residual adaptor** that injects action-space corrections while preserving the general policy’s capabilities. It includes models: 1. **gmt.onnx**: the general motion tracking policy 2. **noitom_teleop.onnx**: the adaptor policy for teleoperation using Noitom inertial mocap suit 3. **pico_teleop.onnx**: the adaptor policy for teleoperation using PICO VR device --- ## How to download ### Option A: Download a single ONNX file ```python from huggingface_hub import hf_hub_download onnx_path = hf_hub_download( repo_id="BAAI-Humanoid/MOSAIC_Model", filename="pico_teleop.onnx", # or "noitom_teleop.onnx" ) print("Downloaded to:", onnx_path) ``` ### Option B: Download all files in this model repo ```python from huggingface_hub import snapshot_download local_dir = snapshot_download( repo_id="BAAI-Humanoid/MOSAIC_Model", ) print("Downloaded to:", local_dir) ``` --- ## Usage For constructing the correct deployable observations and mapping model outputs to Unitree G1 control targets, please use the official [MOSAIC codebase](https://github.com/BAAI-Humanoid/MOSAIC) and [RobotBridge Deployment framework](https://github.com/BAAI-Humanoid/RobotBridge). --- ## Citation If you use these models for your research, please cite our paper: ```bibtex @article{sun2026mosaic, title = {MOSAIC: Bridging the Sim-to-Real Gap in Generalist Humanoid Motion Tracking and Teleoperation with Rapid Residual Adaptation}, author = {Zhenguo Sun and Bo-Sheng Huang and Yibo Peng and Xukun Li and Jingyu Ma and Yu Sun and Zhe Li and Haojun Jiang and Biao Gao and Zhenshan Bing and Xinlong Wang and Alois Knoll}, journal = {arXiv preprint arXiv:2602.08594}, year = {2026} } ``` --- ## License This dataset is released under Apache-2.0.