Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model
Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements for multi-view consistency, geometric coherence, and robot embodiment constraints. Existing methods typically adapt foundation models with limited robot data, often sacrificing visual knowledge acquired during large-scale pre-training. We present Xiaomi-Robotics-U0, a 38-billion-parameter multimodal autoregressive model for unified embodied synthesis. It treats embodied generation as an extension of foundation image a
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 70%Xiaomi Open-Sources Robotics-U0: A 38B-Parameter Embodied Generative Model That Unifies Four Robot Tasks - Pandaily →
- LinkedLinked via arxiv author · 85%Xinghang Li →
“Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model”
- LinkedLinked via arxiv author · 85%Jun Guo →
“Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model”
- LinkedLinked via arxiv author · 85%Qiwei Li →
“Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model”
- LinkedLinked via arxiv author · 85%Long Qian →
“Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model”
- LinkedLinked via arxiv author · 85%Hang Lai →
“Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model”
- LinkedLinked via arxiv author · 85%Yueze Wang →
“Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model”
- LinkedLinked via arxiv author · 85%Hongyu Yan →
“Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model”