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}
}
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support