Skip to content
embodied.guide

Back to the AI models

XiaomiChina2026

Xiaomi-Robotics-U0

An AI model: a vision-language-action model (VLA) takes camera images and an instruction and turns them into movements for a robot. This page describes the software, not a robot.

Robotsnot stated

Key figures as stated by the developer

4 of 6 stated · 2 gaps
  • Model type not stated
  • Controls not stated
  • Inputs ⁠A camera language
  • Access ⁠A open download
  • Parameters ⁠B 38,000,000,000
  • Base model ⁠A EMU3.5
How to read the figures
14kgA30.9lbA
The letter in the grey square after a figure points to the source the figure came from. Robots with several sources carry several letters.
74.5lb
Imperial figures are our own conversion unless the manufacturer states an imperial figure itself. The source letter always belongs to the metric figure — a conversion has no source of its own.

The four states

Versions and notes in the key figures (6)

Model type

Note The developer calls it something else and does not label it vision-language-action or world action model: "Xiaomi-Robotics-U0 is a 38B autoregressive world foundation model continually trained for embodied intelligence.".

Controls

Note The model produces images and video, not robot motion: it "jointly optimizes text-to-image generation, image editing, embodied scene generation, embodied transfer, and embodied video generation".

Inputs

"Scene and task description → multi-view embodied observations." "Conditioned embodied observation → target RGB multi-view scene."

Access

"Released Xiaomi-Robotics-U0 and Xiaomi-Robotics-U0-FlashAR weights."

Parameters

The paper describes "a 38-billion-parameter multimodal autoregressive model".

Base model

The model card says the model is "initialized from EMU3.5".

Full specifications

5 of 12 fields stated
The letter points to the source at the foot of the page. Fields without a figure are dashed: the developer does not state them — that is not the same as zero, and not the same as no.
Field Value Source and caveats
Input and output
Model typenot stated

Note The developer calls it something else and does not label it vision-language-action or world action model: "Xiaomi-Robotics-U0 is a 38B autoregressive world foundation model continually trained for embodied intelligence.". ⁠C

Inputscamera languageA

"Scene and task description → multi-view embodied observations." "Conditioned embodied observation → target RGB multi-view scene."

Controlsnot stated

Note The model produces images and video, not robot motion: it "jointly optimizes text-to-image generation, image editing, embodied scene generation, embodied transfer, and embodied video generation". ⁠B

Degrees of freedom controllednot stated
Size and speed
Parameters38,000,000,000B

The paper describes "a 38-billion-parameter multimodal autoregressive model".

Control ratenot stated
Where it runs and what it is built on
Runs wherenot stated
Base modelEMU3.5A

The model card says the model is "initialized from EMU3.5".
Openness
Accessopen downloadA

"Released Xiaomi-Robotics-U0 and Xiaomi-Robotics-U0-FlashAR weights."

LicenseApache 2.0A

The Hugging Face model card says "license: apache-2.0".
The developer’s own claims
Learns new tasksnot stated
Works across robotsnot stated

Note The model generates scenes of several robots but does not run on them: it is the "first model to support high-quality multi-view scene generation across multiple robot embodiments". ⁠B

Yes only if the developer itself says the model runs on different robot models, for example robots from two manufacturers or two of one manufacturer’s models. Several units of the same robot do not count.

Notes

  • Xiaomi calls Xiaomi-Robotics-U0 a world foundation model trained for embodied intelligence; it generates images and video of robot scenes.
  • Xiaomi presents it as a data engine for robot learning.
  • A separate accelerated version, Xiaomi-Robotics-U0-FlashAR, is released as its own weights; the video checkpoint is not yet released.

Sources

One line per source, not per figure: a source has one retrieval date. The letter beside a figure points to the line it came from.