We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in both Autonomous Driving and Embodied AI. MiMo-Embodied sets new records across 17 embodied AI benchmarks in Task Planning, Affordance Prediction and Spatial Understanding, while also excelling in 12 autonomous driving benchmarks across Environmental Perception, Status Prediction, and Driving Planning. Across these tasks, MiMo-Embodied significantly outperforms existing open-source, closed-source, and specialized baselines. Our results indicate that through multi-stage learning, curated data construction, and CoT/RL fine-tuning, these two domains exhibit strong positive transfer and mutually reinforce one another. We provide a detailed analysis of our model design and training methodologies to facilitate further research. Code and models are available at https://github.com/XiaomiMiMo/MiMo-Embodied.
@article{arxiv.2511.16518,
title = {MiMo-Embodied: X-Embodied Foundation Model Technical Report},
author = {Xiaoshuai Hao and Lei Zhou and Zhijian Huang and Zhiwen Hou and Yingbo Tang and Lingfeng Zhang and Guang Li and Zheng Lu and Shuhuai Ren and Xianhui Meng and Yuchen Zhang and Jing Wu and Jinghui Lu and Chenxu Dang and Jiayi Guan and Jianhua Wu and Zhiyi Hou and Hanbing Li and Shumeng Xia and Mingliang Zhou and Yinan Zheng and Zihao Yue and Shuhao Gu and Hao Tian and Yuannan Shen and Jianwei Cui and Wen Zhang and Shaoqing Xu and Bing Wang and Haiyang Sun and Zeyu Zhu and Yuncheng Jiang and Zibin Guo and Chuhong Gong and Chaofan Zhang and Wenbo Ding and Kun Ma and Guang Chen and Rui Cai and Diyun Xiang and Heng Qu and Fuli Luo and Hangjun Ye and Long Chen},
journal= {arXiv preprint arXiv:2511.16518},
year = {2026}
}