Xiaomi open-sources Xiaomi-Robotics-U0, a 38B unified world model that generates multi-view robot scenes and training data
Confirmed
Status
- Claim
Confirmed
- Our reporting
- High confidence
- Importance
- 2 of 5
- Last verified
- 29 September 2026
Your AI and this story
- GPT-6 Astra74 days after its cutoff
- Claude Opus 5.513 days after its cutoff
- Gemini 4 Hydrogen104 days after its cutoff
- Grok 4.743 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 13 days before it.
Key facts
- 38B params per paper (HF README says 34B); initialized from Emu3.5; shared discrete visual tokenizer
- Authors: beats GPT-Image-2.0 in human evals of embodied scene generation and transfer; #1 on World Arena for embodied video generation
- Used as a data engine: π0.5 OOD success 36.9% -> 63.2% on hard real-world manipulation tasks
- FlashAR decoding: 5.44 s per 1024x1024 image on one H20 (82.86x faster than eager AR)
- U0-4B, U0-Sequence, U0-4B-Sequence weights and FSDP training code released 2026-09-08
What happened
Three days before its Xiaomi-Robotics-1 VLA, Xiaomi released an open world model that treats robot-scene generation as an extension of general image and video generation. The goal is to keep the general visual knowledge of a large pretrained generator while adding multi-view consistency and robot embodiment constraints.
Why it matters
Like NVIDIA’s Cosmos, it bets that generated data can offset the shortage of real robot data. Xiaomi reports a large gain in π0.5’s generalization from U0 data, which is a concrete measure of whether synthetic data helps real robots. The figures are the authors’ own.
Sources
4 sources from 3 sites. Numbers match the chips in the text.
4 sources: 4 primary
Primary
- arXiv 2607.11643: Xiaomi-Robotics-U0arxiv.org, paper
- Hugging Face: Xiaomi-Robotics-U0huggingface.co, code
- Hugging Face: Xiaomi-Robotics-U0-4Bhuggingface.co, code
- Project pagerobotics.xiaomi.com, official
Changes
- Filed