TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

Xiaomi Robotics 0

By Xiaomi
Xiaomi-Robotics-0 is an open 4.7B-parameter Vision-Language-Action model for embodied robots. It adopts a Mixture-of-Transformers architecture with a Qwen3-based multimodal brain and a separate motion head, trained on billions of actions so it can interpret language, perceive scenes and stream low-latency action chunks at 30 Hz on tasks like LIBERO, CALVIN and SimplerEnv.
New Multimodal Gen 3
Released: February 12, 2026

Overview

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.

About Xiaomi

Fondată în aprilie 2010 ca o companie producătoare de electronice de larg consum și dispozitive smart, cu smartphone-uri și hardware smart conectate prin intermediul platformei IoT.

Website: mi.com
View Company Profile

Tools using Xiaomi Robotics 0

No tools found for this model yet.

Last updated: February 13, 2026
0 AIs selected
Clear selection
#
Name
Task