Xiaomi has open-sourced the MiMo-V2.6 Pro and Flash omnimodal models, which are designed to coordinate agents for constructing and visually testing interactive 3D scenes. These models can generate Blender assets, control robotic arms from camera feeds, produce frontends and presentations, assemble videos, and compose music as scores and MIDI.

  • The models are available in AI Studio, MiMo Code, MiMo Desktop, Xiaomi's MiMo API Platform, and OpenRouter.
  • Xiaomi has published the technical report, training environments, and RL code alongside the models.
  • The MiMo-V2.6 series scales reinforcement learning compute to advance model intelligence while maintaining stability through frozen MoE routers and reward hacking defenses.

The open-sourcing of the training dynamics, RL environments, and framework aims to facilitate reproduction and further research on scaled RL and model self-improvement.