Xiaomi Robotics Releases U0 Embodied Model
XiaomiRobotics · hf · 2026-07-14
The Xiaomi Robotics team releases Xiaomi-Robotics-U0, a 38B parameter multimodal autoregressive model aimed at unified embodied synthesis.
It treats embodied generation as an extension of foundational image/video generation, jointly optimizing:
- Text-to-image
- Image editing
- Embodied scene generation
- Embodied transfer
- Embodied video generation
The paper emphasizes that this unified framework tries to retain the general capabilities of the pre-trained world foundation model while adapting to embodied scenarios. It reportedly excels in multi-view consistency, structural consistency, and controllable editing, achieving better results in embodied scene generation, transfer, and real-world manipulation tasks. Code and weights are open-sourced.
Related event: Xiaomi Robotics Unveils U0: a 38B Embodied World Foundation Model(3 posts)→
More from Embodied
- LIBERO-MAX: Robot Policies Drop 11–26 Points When the World Changes Mid-Task — drmapavone · 2026-10-27
- Photos from ROSCon UK: BBC's robotic whale, da Vinci surgical robot, PR2 and Baxter — kamathsblog · 2026-10-27
- Agility's Digit robot to expand into two more GXO US warehouses from early 2027 — jonstephens85 · 2026-10-27
- Real2Sem2Real turns one phone video into 2,000+ robot demos, matching 150 teleop demos — Scobleizer · 2026-10-27
- Wayve CEO argues end-to-end deep learning should power driving, safety and world models — alexgkendall · 2026-10-27
- Mundo turns a few room photos into an explorable, simulatable 3D world — at 1.5 FPS — mark_k · 2026-10-27