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
- Tesla’s summer update lets Grok make calls, control climate, and play music — Polymarket · 2026-07-22
- Hugging Face Teases Agentic Training Environments with OpenEnv for August Launch — mervenoyann · 2026-07-22
- NVIDIA shows 22 SIGGRAPH papers and Omniverse tools for robot simulation — facontidavide · 2026-07-22
- Nothing phone mockup turns a film joke into a modular design meme — ZeYanjie · 2026-07-22
- Lightwheel AI Launches SimReadyGen: Text-to-Physics-Accurate Robot Sim Assets — ZeYanjie · 2026-07-22
- Humanoid robot sorting packages in a warehouse sparks debate over job loss — MonaJalal_ · 2026-07-22