Xiaomi Robotics World Model Boosts Efficiency
Scobleizer · x · 2026-07-14
A quote introduces Xiaomi-Robotics-U0: a 38B autoregressive world foundation model that trains general image/video generation alongside multi-view embodied synthesis to improve real robot policy performance.
The reported results show that synthetic data boosted the real robot's success rate on out-of-distribution tasks from 36.9% to 63.2%. The corresponding paper is titled Unified Embodied Synthesis with World Foundation Model.
Related event: Xiaomi Robotics Unveils U0: a 38B Embodied World Foundation Model(3 posts)→
More from Embodied
- DONIC hits 86.79% on bimanual dexterous tracking, crushing prior SOTA's 9.43% — liuziwei7 · 2026-10-27
- Bedrock Robotics raises $600M as its fully autonomous excavators do paid work on live job sites — Sethwinterroth · 2026-10-27
- AW-0 hits 80.8% on RoboTwin tasks, beating strongest baseline by 16 points — trevordarrell · 2026-10-27
- AW-0's code stream fixes world model prediction: picks mango where baseline grabs apple — trevordarrell · 2026-10-27
- AW-0 runs at 230ms on a single RTX 5090, 2.4x faster than autoregressive code planning — trevordarrell · 2026-10-27
- AW-0 debuts: one generative world action model plans in code, predicts, and controls robots — trevordarrell · 2026-10-27