Xiaomi Robotics U0
A 38 billion parameter multimodal autoregressive model for unified embodied synthesis. It performs text to image generation, image editing, multi view robot scene generation, embodied scene transfer, and embodied video generation, extending foundation image and video generation into robotics settings.
- Type
- Multimodal
- Weights
- Open
- Downloads
- 63
- Likes
- 31
- Pipeline
- any to any
- License
- apache-2.0
Model hub
XiaomiRobotics/Xiaomi-Robotics-U0
- Repo
- XiaomiRobotics/Xiaomi-Robotics-U0
- Library
- transformers
- Access
- Public
Technical tags and languages
Papers
1
More from Xiaomi
11
-
99k DL
MiMo V2 Flash
Text
I cannot find public technical documentation for a distinct “MiMo v2 Flash” model beyond Xiaomi’s MiMo-7B and…
-
5.8k DL
MiMo V2.5 ASR
Multimodal
MiMo-V2.5-ASR is Xiaomi MiMo’s state-of-the-art end-to-end ASR model for robust transcription across Mandarin…
-
2k DL
MiMo V2.5 Pro
Text
MiMo-V2.5-Pro is Xiaomi’s latest agentic language model, built for stronger long-horizon coherence, complex s…
-
MiMo V2.5 Pro UltraSpeed
Text
MiMo-V2.5-Pro-UltraSpeed is Xiaomi MiMo’s 1T-parameter high-speed reasoning model variant built with TileRT t…
-
1.4M DL
OmniVoice
Audio
OmniVoice is a multilingual zero-shot text-to-speech model built for voice cloning, voice design, and general…
-
Pixel Perfect Depth
Image
Pixel-Perfect Depth is a monocular depth estimation model that uses pixel-space diffusion transformers to pre…
-
Xiaomi MiMo V2 Omni
Multimodal
MiMo-V2-Omni is an omni foundation model that unifies multimodal understanding with agentic capability, built…
-
Xiaomi MiMo V2 Pro
Text
MiMo-V2-Pro is Xiaomi’s flagship foundation model built for real-world agent workloads, designed to act as th…
About Xiaomi
1
Consumer electronics and smart device company making smartphones, wearables, IoT products, home appliances, smart TVs, scooters, and connected lifestyle hardware.