Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model

• URL: http://arxiv.org/abs/2607.11643v1
• Date: Mon, 13 Jul 2026 14:57:58 GMT
• Title: Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model
• Abstract summary: Xiaomi-Robotics-U0 is a multimodal autoregressive model for unified embodied synthesis.<n>It treats embodied generation as an extension of foundation image and video generation.<n>It is the first model to support high-quality multi-view scene generation across multiple robot embodiments.
• Score: 43.03635193896585
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 and video generation and jointly optimizes text-to-image generation, image editing, embodied scene generation, embodied transfer, and embodied video generation. This unified framework preserves the generalization of the pre-trained world foundation model while adapting it to embodied settings. Xiaomi-Robotics-U0 is the first model to support high-quality multi-view scene generation across multiple robot embodiments and to introduce structured, controllable embodied transfer for fine-grained editing while preserving multi-view consistency and interaction dynamics. It achieves state-of-the-art results on single-step and sequential generation tasks, outperforming GPT-Image-2.0 in human evaluations of embodied scene generation and transfer, ranking first on World Arena for embodied video generation, and improving the out-of-distribution success rate of pi_0.5 from 36.9% to 63.2% on challenging real-world manipulation tasks. These results show that foundation world models can serve both as embodied world models and scalable data engines for embodied intelligence. Code and checkpoints are available at https://robotics.xiaomi.com/xiaomi-robotics-u0.html.

Related papers

• RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation [48.828787848144806]
  We introduce digital teleoperation, a paradigm that decouples data collection from physical constraints by replacing real robot with a generative world model.<n>We instantiate this paradigm in RynnWorld-Teleop, a system that integrates depth-aware skeletal conditioning, progressive human-to-robot training on a video Diffusion Transformer, and streaming autoregressive distillation.<n>This pipeline compresses the generative process into a single-pass inference, enabling 40+ FPS, real-time interactive generation on a single H100 GPU.
  arXiv  Detail & Related papers  (2026-07-07T17:58:11Z)
• MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data [125.43597497646444]
  MetaWorld is a novel framework that scales multi-agent video world models to open-domain environments directly from single-view videos.<n>It achieves superior cross-view consistency and identity fidelity, establishing a highly scalable, physics-driven paradigm for multi-agent video world modeling.
  arXiv  Detail & Related papers  (2026-06-01T18:20:20Z)
• MotuBrain: An Advanced World Action Model for Robot Control [23.733029557644354]
  We present MotuBrain, a unified World Action Model that jointly models video and action under a UniDiffuser formulation.<n>A single model supports policy learning, world modeling, video generation, inverse dynamics, and joint video-action prediction.<n>Building on Motus, MotuBrain further introduces unified multiview modeling, an independent text stream for stronger language-action coupling.<n>Our inference stack combines step reduction, compilation, FP8 quantization, DiT caching, V2A-style action-only inference, and real-time chunked closed-loop execution.
  arXiv  Detail & Related papers  (2026-04-30T12:34:44Z)
• DuoGen: Towards General Purpose Interleaved Multimodal Generation [65.13479486098419]
  DuoGen is a general-purpose interleaved generation framework that addresses data curation, architecture design, and evaluation.<n>We build a large-scale, high-quality instruction-tuning dataset by combining multimodal conversations rewritten from curated raw websites.<n>A two-stage decoupled strategy first instruction-tunes the MLLM, then aligns DiT with it using curated interleaved image-text sequences.
  arXiv  Detail & Related papers  (2026-01-31T04:35:15Z)
• IC-World: In-Context Generation for Shared World Modeling [61.69655562995357]
  Video-based world models have recently garnered increasing attention for their ability to synthesize diverse and dynamic visual environments.<n>In this paper, we focus on shared world modeling, where a model generates multiple videos from a set of input images, each representing the same underlying world in different camera poses.<n>We propose IC-World, a novel generation framework, enabling parallel generation for all input images.
  arXiv  Detail & Related papers  (2025-12-01T16:52:02Z)
• Image Generation as a Visual Planner for Robotic Manipulation [0.0]
  Generating realistic robotic manipulation videos is an important step toward unifying perception, planning, and action in embodied agents.<n>We propose a two-part framework that includes: (1) text-conditioned generation, which uses a language instruction and the first frame, and (2) trajectory-conditioned generation, which uses a 2D trajectory overlay and the same initial frame.<n>Our findings indicate that pretrained image generators encode transferable temporal priors and can function as video-like robotic planners under minimal supervision.
  arXiv  Detail & Related papers  (2025-11-29T15:54:16Z)
• EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer [35.27100635173712]
  Vision-language-action (VLA) models increasingly rely on diverse training data to achieve robust generalization.<n>We propose Embodied Manipulation Media Adaptation (EMMA), a VLA policy enhancement framework that integrates a generative data engine with an effective training pipeline.<n>DreamTransfer enables text-controlled visual editing of robot videos, transforming foreground, background, and lighting conditions without compromising 3D structure or geometrical plausibility.<n>AdaMix is a hard-sample-aware training strategy that dynamically reweights training batches to focus optimization on perceptually or kinematically challenging samples.
  arXiv  Detail & Related papers  (2025-09-26T14:34:44Z)
• Learning Primitive Embodied World Models: Towards Scalable Robotic Learning [50.32986780156215]
  We propose a novel paradigm for world modeling--Primitive Embodied World Models (PEWM)<n>By restricting video generation to fixed short horizons, our approach enables fine-grained alignment between linguistic concepts and visual representations of robotic actions.<n>Our framework bridges the gap between fine-grained physical interaction and high-level reasoning, paving the way toward scalable, interpretable, and general-purpose embodied intelligence.
  arXiv  Detail & Related papers  (2025-08-28T14:31:48Z)
• DreamGen: Unlocking Generalization in Robot Learning through Video World Models [120.25799361925387]
  DreamGen is a pipeline for training robot policies that generalize across behaviors and environments through neural trajectories.<n>Our work establishes a promising new axis for scaling robot learning well beyond manual data collection.
  arXiv  Detail & Related papers  (2025-05-19T04:55:39Z)
• RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models [22.042487298092883]
  RealGeneral is a novel framework that reformulates image generation as a conditional frame prediction task.<n>It mitigates a 14.5% improvement in subject similarity for customized generation and a 10% enhancement in image quality for canny-to-image task.
  arXiv  Detail & Related papers  (2025-03-13T14:31:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.