Xiaomi launched Xiaomi-Robotics-U0, a 38-billion-parameter multimodal autoregressive model for unified embodied synthesis. This model views embodied genera...
Xiaomi launched Xiaomi-Robotics-U0, a 38-billion-parameter multimodal autoregressive model for
unified embodied synthesis. This model views embodied generation as an extension of basic image and video generation, jointly optimizing text-to-image, image editing, embodied scene generation, embodied migration, and embodied video generation. It is the first model to support high-quality multi-view scene generation across various robot forms, introducing structured, controllable embodiment migration. The model achieves SOTA in single-step and sequential generation tasks, surpasses GPT-Image-2.0 in human evaluation of embodied scene generation and transfer, ranks first in embodied video generation in World Arena, and increases pi_0.5's out-of-distribution success rate on real-world manipulation tasks from 36.9% to 63.2%. The code and checkpoints are open source.
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs ：https://info.arxiv.org/labs/index.html.
材料摘要称，小米推出380亿参数多模态自回归模型Xiaomi-Robotics-U0，将图像、视频与多类具身生成任务纳入联合优化，并已开源代码与检查点。
该模型把具身生成视为基础图像和视频生成的延伸，覆盖文生图、图像编辑、具身场景生成、具身迁移与具身视频生成。正文摘录仅介绍arXivLabs，未提供论文技术细节。
Aioga判断，其主要编辑价值在于尝试以单一自回归模型统一多种具身合成任务，并强调跨机器人形态和结构化控制；但现有材料中的性能结论主要来自摘要，仍需论文实验细节支撑。
若摘要所述结果可复现，该方法可能降低不同机器人形态间场景与视频数据生成的割裂程度，并为真实世界操控的分布外泛化提供辅助；目前不能据此推断其已具备通用机器人控制能力。 值得关注论文对训练数据、评测协议、基线设置、人类评估流程及真实世界任务的披露，并核验World Arena排名、与GPT-Image-2.0的比较，以及36.9%至63.2%的提升能否独立复现。
The readable text on this page was extracted from the public source and organized with attribution, publication time and the original link. Copyright remains with the original author and publisher.
Ingestion channel: Summary aggregation · Source domain: arxiv.org
Source: HuggingFace Daily Papers（社区热门论文）
Original link: Open original source
Aioga archive: Open intelligence page
Content record: source-page · Updated: 2026-07-13T14:57:58.000Z
统一接入主流 AI 模型 API，为开发、测试与生产环境提供稳定调用入口。
立即访问 api.w173.com
Scan to open this articleAioga aggregates global AI updates and preserves source information for verification and citation.