Xiaomi MiMo-VL-Miloco Technical Report

TL;DR

This paper introduces MiMo-VL-Miloco, a vision-language model optimized for smart-home environments that achieves high performance in home-scenario understanding and multimodal reasoning, with a novel training pipeline and open-source resources.

Contribution

The paper presents a specialized vision-language model for smart homes, a two-stage training method combining supervised fine-tuning and reinforcement learning, and open-source tools for real-world deployment.

Findings

Achieves leading F1 scores in gesture recognition and home-scenario understanding.

Outperforms baselines on multimodal reasoning benchmarks.

Enhances text reasoning through targeted home-scenario training.

Abstract

We open-source MiMo-VL-Miloco-7B and its quantized variant MiMo-VL-Miloco-7B-GGUF, a pair of home-centric vision-language models that achieve strong performance on both home-scenario understanding and general multimodal reasoning. Built on the MiMo-VL-7B backbone, MiMo-VL-Miloco-7B is specialized for smart-home environments, attaining leading F1 scores on gesture recognition and common home-scenario understanding, while also delivering consistent gains across video benchmarks such as Video-MME, Video-MMMU, and Charades-STA, as well as language understanding benchmarks including MMMU-Pro and MMLU-Pro. In our experiments, MiMo-VL-Miloco-7B outperforms strong closed-source and open-source baselines on home-scenario understanding and several multimodal reasoning benchmarks. To balance specialization and generality, we design a two-stage training pipeline that combines supervised fine-tuning with reinforcement learning based on Group Relative Policy Optimization, leveraging efficient multi-domain data. We further incorporate chain-of-thought supervision and token-budget-aware reasoning, enabling the model to learn knowledge in a data-efficient manner while also performing reasoning efficiently. Our analysis shows that targeted home-scenario training not only enhances activity and gesture understanding, but also improves text-only reasoning with only modest trade-offs on document-centric tasks. Model checkpoints, quantized GGUF weights, and our home-scenario evaluation toolkit are publicly available at https://github.com/XiaoMi/xiaomi-mimo-vl-miloco to support research and deployment in real-world smart-home applications.