MiMo Embodied 7B
MiMo Embodied 7B is a research model that combines visual reasoning about embodied tasks and autonomous-driving scenes. It is published with weights and example tasks.
Research release
A shared visual model spans two research areas
Xiaomi evaluates the model on embodied tasks, driving-related benchmarks and general visual understanding. The examples include navigation and manipulation scenarios.MiMo-Embodied-7B official model card
Do not turn a benchmark result into a control guarantee
Practical guidance. Use the model to study scene interpretation or planning in a controlled environment. Physical action requires a separate control system and validation. A text plan about a road or robot scene does not establish safe real-world operation.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | MiMo-Embodied-7B |
| Embodied tasks | Task planning, affordance prediction and spatial understanding.MiMo-Embodied-7B official model card |
| Driving-related tasks | Environment perception, status prediction and driving planning.MiMo-Embodied-7B official model card |
| Licence | MIT.MiMo-Embodied-7B official model card |
Related models
- MiMo V2.6 Pro
Xiaomi · MiMo V2.6
MiMo V2.6 Pro accepts text, images, video and audio, then returns text.
Launch date not confirmedAPI · Downloadable · Provider product - MiMo VL 7B RL 2508
Xiaomi · MiMo VL
An updated MiMo VL 7B reasoning model for image and video tasks with an option to disable reasoning.
Launch date not confirmedDownloadable