arXiv · 2026 · Preprint

Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution

Ruisi Cai, Jun Guo, Xin He, Piao-Piao Jin, Jie Li, Bin Lin, Fu-Teng Liu, Wei Liu, Fei Ma, Kun Ma, Feng Qiu, Heng-Chao Qu, Yifei Su, Qiao Sun, Dong Wang, Dong-Hao Wang, Yun-Hao Wang, Ru-Jie Wu, Di-Yun Xiang, Yu Yang, Hang Ye, Yuan Zhang, Quan Zhou

Date
2026-02-13
Citations
34
arXiv
2602.12684
Cite
@misc{cai2026xiaomirobotics,
  title = {Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution},
  author = {Ruisi Cai and Jun Guo and Xin He and Piao-Piao Jin and Jie Li and Bin Lin and Fu-Teng Liu and Wei Liu and Fei Ma and Kun Ma and Feng Qiu and Heng-Chao Qu and Yifei Su and Qiao Sun and Dong Wang and Dong-Hao Wang and Yun-Hao Wang and Ru-Jie Wu and Di-Yun Xiang and Yu Yang and Hang Ye and Yuan Zhang and Quan Zhou},
  year = {2026},
  eprint = {2602.12684},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.12684},
}