Multimodal model

Xiaomi Robotics 0

Xiaomi-Robotics-0 is a 4.7B-parameter open Vision-Language-Action model that uses a Mixture-of-Transformers design, combining a Qwen3-based vision-language brain with a diffusion transformer controller for smooth, real-time robot manipulation on benchmarks and real robots.

Xiaomi Multimodal Closed apache-2.0
Type
Multimodal
Weights
Closed
Downloads
611
Likes
16
Pipeline
robotics
License
apache-2.0

Model hub

XiaomiRobotics/Xiaomi-Robotics-0-LIBERO

Repo
XiaomiRobotics/Xiaomi-Robotics-0-LIBERO
Library
transformers
Access
Public
Technical tags and languages
transformers safetensors mibot feature-extraction vision-language-action vla robotic-manipulation robotics custom_code
Open on Hugging Face

Papers

1

More from Xiaomi

11

About Xiaomi

1

Consumer electronics and smart device company making smartphones, wearables, IoT products, home appliances, smart TVs, scooters, and connected lifestyle hardware.