Introduction

In this repository, we have publicly released five officially adapted scenarios from realmirror, each containing three model weights. The scenarios include:

Task1_Kitchen_Cleanup  
Task2_Cup_to_Cup_Transfer  
Task3_Assembly_Line_Sorting  
Task4_Can_Stacking  
Task5_Air_Fryer_Manipulation  

Each scenario includes the following models:

ACT  
Diffusion  
SmolVLA  

For more information, please refer to our GitHub homepage:
(https://github.com/terminators2025/RealMirror/tree/main)

Citation

If you find this work helpful in your research, please consider giving this repo a star โญ and citing our paper:

@article{tai2025realmirror,
  title={RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AI},
  author={Tai, Cong and Zheng, Zhaoyu and Long, Haixu and Wu, Hansheng and Xiang, Haodong and Long, Zhengbin and Xiong, Jun and Shi, Rong and Zhang, Shizhuang and Qiu, Gang and others},
  journal={arXiv preprint arXiv:2509.14687},
  year={2025}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support