Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912981174976512 |
|---|---|
| author | Cai, Rui Guo, Jun He, Xinze Jin, Piaopiao Li, Jie Lin, Bingxuan Liu, Futeng Liu, Wei Ma, Fei Ma, Kun Qiu, Feng Qu, Heng Su, Yifei Sun, Qiao Wang, Dong Wang, Donghao Wang, Yunhong Wu, Rujie Xiang, Diyun Yang, Yu Ye, Hangjun Zhang, Yuan Zhou, Quanyun |
| author_facet | Cai, Rui Guo, Jun He, Xinze Jin, Piaopiao Li, Jie Lin, Bingxuan Liu, Futeng Liu, Wei Ma, Fei Ma, Kun Qiu, Feng Qu, Heng Su, Yifei Sun, Qiao Wang, Dong Wang, Donghao Wang, Yunhong Wu, Rujie Xiang, Diyun Yang, Yu Ye, Hangjun Zhang, Yuan Zhou, Quanyun |
| contents | In this report, we introduce Xiaomi-Robotics-0, an advanced vision-language-action (VLA) model optimized for high performance and fast and smooth real-time execution. The key to our method lies in a carefully designed training recipe and deployment strategy. Xiaomi-Robotics-0 is first pre-trained on large-scale cross-embodiment robot trajectories and vision-language data, endowing it with broad and generalizable action-generation capabilities while avoiding catastrophic forgetting of the visual-semantic knowledge of the underlying pre-trained VLM. During post-training, we propose several techniques for training the VLA model for asynchronous execution to address the inference latency during real-robot rollouts. During deployment, we carefully align the timesteps of consecutive predicted action chunks to ensure continuous and seamless real-time rollouts. We evaluate Xiaomi-Robotics-0 extensively in simulation benchmarks and on two challenging real-robot tasks that require precise and dexterous bimanual manipulation. Results show that our method achieves state-of-the-art performance across all simulation benchmarks. Moreover, Xiaomi-Robotics-0 can roll out fast and smoothly on real robots using a consumer-grade GPU, achieving high success rates and throughput on both real-robot tasks. To facilitate future research, code and model checkpoints are open-sourced at https://xiaomi-robotics-0.github.io |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12684 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution Cai, Rui Guo, Jun He, Xinze Jin, Piaopiao Li, Jie Lin, Bingxuan Liu, Futeng Liu, Wei Ma, Fei Ma, Kun Qiu, Feng Qu, Heng Su, Yifei Sun, Qiao Wang, Dong Wang, Donghao Wang, Yunhong Wu, Rujie Xiang, Diyun Yang, Yu Ye, Hangjun Zhang, Yuan Zhou, Quanyun Robotics Machine Learning In this report, we introduce Xiaomi-Robotics-0, an advanced vision-language-action (VLA) model optimized for high performance and fast and smooth real-time execution. The key to our method lies in a carefully designed training recipe and deployment strategy. Xiaomi-Robotics-0 is first pre-trained on large-scale cross-embodiment robot trajectories and vision-language data, endowing it with broad and generalizable action-generation capabilities while avoiding catastrophic forgetting of the visual-semantic knowledge of the underlying pre-trained VLM. During post-training, we propose several techniques for training the VLA model for asynchronous execution to address the inference latency during real-robot rollouts. During deployment, we carefully align the timesteps of consecutive predicted action chunks to ensure continuous and seamless real-time rollouts. We evaluate Xiaomi-Robotics-0 extensively in simulation benchmarks and on two challenging real-robot tasks that require precise and dexterous bimanual manipulation. Results show that our method achieves state-of-the-art performance across all simulation benchmarks. Moreover, Xiaomi-Robotics-0 can roll out fast and smoothly on real robots using a consumer-grade GPU, achieving high success rates and throughput on both real-robot tasks. To facilitate future research, code and model checkpoints are open-sourced at https://xiaomi-robotics-0.github.io |
| title | Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2602.12684 |