Xiaomi-Robotics-1 (XR-1, 5B)
Paper 2026-07-16 (arXiv 2607.15330); weights on HF 2026-07-28; code 2026-08-03. Predecessor: xiaomi-robotics-0 (Feb 2026, arXiv 2602.12684). Companion world model: xiaomi-robotics-u0 (July/Sept 2026). Changelog 2026-09-29: linked the new model files.
- Input
- image, text
- Output
- action
- License
- apache-2.0
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Hugging Face | XiaomiRobotics/Xiaomi-Robotics-1-5B | huggingface.co/XiaomiRobotics/Xiaomi-Robotics-1-5B | — |
| GitHub | — | github.com/XiaomiRobotics/Xiaomi-Robotics-1 | docs |
Notable capabilities (2)
- VLA pretrained on 100K+ hours of real trajectories: Pretrained on 100K+ hours of embodiment-free UMI trajectories across 1,700+ scenarios (per Xiaomi project materials), then post-trained on 10K+ hours of cross-embodiment data, for out-of-the-box mobile manipulation in unseen environments. source
- Open-weight SOTA on sim benchmarks: RoboCasa 74.5%, RoboCasa365 57.4%, VLABench 59.1%, RoboDojo 13.93% in the GitHub table (the arXiv abstract cites a 20.07 RoboDojo average score — different metric/version), each ahead of the runner-up per the authors. source
Timeline entry
- Xiaomi open-sources Xiaomi-Robotics-1, a VLA trained on 100K+ hours of real trajectories ★★★
Xiaomi published Xiaomi-Robotics-1 on 2026-07-16, a 5B vision-language-action model pretrained on over 100K hours of real-world UMI manipulation trajectories and post-trained on 10K+ hours of cross-embodiment data; weights (Apache-2.0) followed on Hugging Face on 2026-07-28 with top open results…
Other Xiaomi models
Xiaomi-Robotics-U0 (38B) / U0-4B · Xiaomi-Robotics-0 (4.7B VLA)