Lei Jun: The Future Main Breakthrough Direction of Xiaomi's Large Model Technology is 'Lightweight and Local Deployment'


China includes AI glasses in national consumer subsidy pilot, offering up to 15% off with an 800 yuan cap per unit from Q1 2026, marking the first state-level support for such advanced smart hardware.....
Xiaomi announced that the free public testing period of its self-developed large model MiMo-V2-Flash has been extended by 20 days, until January 20, 2026. The model has 309 billion parameters, with 15 billion activated parameters, and performs excellently in reasoning and code generation. This move aims to provide users with a longer experience period and demonstrate Xiaomi's continuous investment and confidence in the AI field.
Xiaomi releases the open-source large model MiMo-V2-Flash, which is designed for high speed and efficiency, showing outstanding performance in tasks such as inference and code generation, with response speed surpassing multiple popular domestic models. The model adopts a sparse activation architecture, with 309 billion parameters, and the weights and code are open-sourced under the MIT license.
Xiaomi officially released the embodied large model MiMo-Embodied and announced that the model will be fully open-sourced. This move marks an important step for Xiaomi in the field of general embodied intelligence research.
Xiaomi updates Super Xiao Ai to version 7.8.50, adding the 'Random Photo Editing' feature. Users can use natural language instructions to let the AI model automatically edit photos, supporting multimodal interaction to recognize screen and camera images. The operation methods include waking up Xiao Ai in the album or uploading photos via the App and inputting text, allowing the system to automatically complete color enhancement, background blur, and other processing.