Cover Image

MiMo-Embodied: X-Embodied Foundation Model Technical Report

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hao, Xiaoshuai, Zhou, Lei, Huang, Zhijian, Hou, Zhiwen, Tang, Yingbo, Zhang, Lingfeng, Li, Guang, Lu, Zheng, Ren, Shuhuai, Meng, Xianhui, Zhang, Yuchen, Wu, Jing, Lu, Jinghui, Dang, Chenxu, Guan, Jiayi, Wu, Jianhua, Hou, Zhiyi, Li, Hanbing, Xia, Shumeng, Zhou, Mingliang, Zheng, Yinan, Yue, Zihao, Gu, Shuhao, Tian, Hao, Shen, Yuannan, Cui, Jianwei, Zhang, Wen, Xu, Shaoqing, Wang, Bing, Sun, Haiyang, Zhu, Zeyu, Jiang, Yuncheng, Guo, Zibin, Gong, Chuhong, Zhang, Chaofan, Ding, Wenbo, Ma, Kun, Chen, Guang, Cai, Rui, Xiang, Diyun, Qu, Heng, Luo, Fuli, Ye, Hangjun, Chen, Long
Format:	Preprint
Published:	2025
Subjects:	Robotics Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866908996449861632
author	Hao, Xiaoshuai Zhou, Lei Huang, Zhijian Hou, Zhiwen Tang, Yingbo Zhang, Lingfeng Li, Guang Lu, Zheng Ren, Shuhuai Meng, Xianhui Zhang, Yuchen Wu, Jing Lu, Jinghui Dang, Chenxu Guan, Jiayi Wu, Jianhua Hou, Zhiyi Li, Hanbing Xia, Shumeng Zhou, Mingliang Zheng, Yinan Yue, Zihao Gu, Shuhao Tian, Hao Shen, Yuannan Cui, Jianwei Zhang, Wen Xu, Shaoqing Wang, Bing Sun, Haiyang Zhu, Zeyu Jiang, Yuncheng Guo, Zibin Gong, Chuhong Zhang, Chaofan Ding, Wenbo Ma, Kun Chen, Guang Cai, Rui Xiang, Diyun Qu, Heng Luo, Fuli Ye, Hangjun Chen, Long
author_facet	Hao, Xiaoshuai Zhou, Lei Huang, Zhijian Hou, Zhiwen Tang, Yingbo Zhang, Lingfeng Li, Guang Lu, Zheng Ren, Shuhuai Meng, Xianhui Zhang, Yuchen Wu, Jing Lu, Jinghui Dang, Chenxu Guan, Jiayi Wu, Jianhua Hou, Zhiyi Li, Hanbing Xia, Shumeng Zhou, Mingliang Zheng, Yinan Yue, Zihao Gu, Shuhao Tian, Hao Shen, Yuannan Cui, Jianwei Zhang, Wen Xu, Shaoqing Wang, Bing Sun, Haiyang Zhu, Zeyu Jiang, Yuncheng Guo, Zibin Gong, Chuhong Zhang, Chaofan Ding, Wenbo Ma, Kun Chen, Guang Cai, Rui Xiang, Diyun Qu, Heng Luo, Fuli Ye, Hangjun Chen, Long
contents	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.
format	Preprint
id	arxiv_https___arxiv_org_abs_2511_16518
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	MiMo-Embodied: X-Embodied Foundation Model Technical Report Hao, Xiaoshuai Zhou, Lei Huang, Zhijian Hou, Zhiwen Tang, Yingbo Zhang, Lingfeng Li, Guang Lu, Zheng Ren, Shuhuai Meng, Xianhui Zhang, Yuchen Wu, Jing Lu, Jinghui Dang, Chenxu Guan, Jiayi Wu, Jianhua Hou, Zhiyi Li, Hanbing Xia, Shumeng Zhou, Mingliang Zheng, Yinan Yue, Zihao Gu, Shuhao Tian, Hao Shen, Yuannan Cui, Jianwei Zhang, Wen Xu, Shaoqing Wang, Bing Sun, Haiyang Zhu, Zeyu Jiang, Yuncheng Guo, Zibin Gong, Chuhong Zhang, Chaofan Ding, Wenbo Ma, Kun Chen, Guang Cai, Rui Xiang, Diyun Qu, Heng Luo, Fuli Ye, Hangjun Chen, Long Robotics Computation and Language Computer Vision and Pattern Recognition 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.
title	MiMo-Embodied: X-Embodied Foundation Model Technical Report
topic	Robotics Computation and Language Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2511.16518