MiMo-V2.6 builds and interacts with 3D worlds from text, images, or video

Xiaomi's MiMo-V2.6 combines 3D spatial reasoning, multimodal perception, and computer use to turn text, images, or video into playable 3D worlds.

The model coordinates agents to build scenes, write interaction logic, and refine results, and can create Blender objects for animation, 3D printing, and games.

It also controls a Franka Panda arm in simulation via visual feedback and uses desktop tools to process data, inspecting results to adjust its next actions.