unitreerobotics/UnifoLM-VLM-Base

UnifoLM-VLA-0: A Vision-Language-Action (VLA) Framework under UnifoLM Family

<p style="font-size: 1.2em;"> <a href="https://unigen-x.github.io/unifolm-vla.github.io"><strong>Project Page</strong></a> | <a href="https://huggingface.co/unitreerobotics/models"><strong>Models</strong></a> | <a href="https://huggingface.co/unitreerobotics/datasets"><strong>Datasets</strong></a> </p> <div align="center"> <p align="right"> <span> 🌎English </span> | <a href="https://github.com/unitreerobotics/unifolm-vla/blob/main/README_cn.md"> 🇨🇳中文 </a> </p> </div>

UnifoLM-VLA-0 is a Vision–Language–Action (VLA) large model in the UnifoLM series, designed for general-purpose humanoid robot manipulation. It goes beyond the limitations of conventional Vision–Language Models (VLMs) in physical interaction. Through continued pre-training on robot manipulation data, the model evolves from "vision-language understanding" to an "embodied brain" equipped with physical common sense.

<table width="100%"> <tr> <th width="50%">Spatial Semantic Enhancement</th> <th width="50%">Manipulation Generalization</th> </tr> <tr> <td valign="top"> To address the requirements for instruction comprehension and spatial understanding in manipulation tasks, the model deeply integrates textual instructions with 2D/3D spatial details through continued pre-training, <strong>substantially strengthening its spatial perception and geometric understanding capabilities.</strong> </td> <td valign="top"> By leveraging full dynamics prediction data, the model achieves strong generalization across diverse manipulation tasks. In real-robot validation, <strong>it can complete 12 categories of complex manipulation tasks with high quality using only a single policy.</strong> </td> </tr> </table>

<div align="center"> <img src="https://raw.githubusercontent.com/unitreerobotics/unifolm-vla/main/assets/gif/UnifoLM-VLA-0.gif" style="width:100%; max-width:1000px; height:auto;" alt="UnifoLM-VLA Demo" /> </div>

📝 Citation

@misc{unifolm-vla-0,
  author       = {Unitree},
  title        = {UnifoLM-VLA-0: A Vision-Language-Action (VLA) Framework under UnifoLM Family},
  year         = {2026},
}

License

The model is released under the CC BY-NC-SA 4.0 license as found in the LICENSE. You are responsible for ensuring that your use of Unitree AI Models complies with all applicable laws.