Xiaomi MiMo-VL-Miloco Technical Report
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911331324526592 |
|---|---|
| author | Li, Jiaze Chen, Jingyang Qu, Yuxun Xu, Shijie Lin, Zhenru Zhu, Junyou Xu, Boshen Tan, Wenhui Fu, Pei Ju, Jianzhong Luo, Zhenbo Luan, Jian |
| author_facet | Li, Jiaze Chen, Jingyang Qu, Yuxun Xu, Shijie Lin, Zhenru Zhu, Junyou Xu, Boshen Tan, Wenhui Fu, Pei Ju, Jianzhong Luo, Zhenbo Luan, Jian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_17436 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Xiaomi MiMo-VL-Miloco Technical Report Li, Jiaze Chen, Jingyang Qu, Yuxun Xu, Shijie Lin, Zhenru Zhu, Junyou Xu, Boshen Tan, Wenhui Fu, Pei Ju, Jianzhong Luo, Zhenbo Luan, Jian Computer Vision and Pattern Recognition 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. |
| title | Xiaomi MiMo-VL-Miloco Technical Report |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.17436 |