MiMo-VL-7B-RL

Image: Xiaomi-MiMo

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

MiMo-VL Technical Report

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

| 🤗 HuggingFace  | 🤖️ ModelScope  | 📔 Technical Report  | 📃 Paper  |

I. Introduction#

In this report, we share our efforts to build a compact yet powerful VLM, MiMo-VL-7B. MiMo-VL-7B comprises (1) a native resolution ViT encoder that preserves fine-grained visual details, (2) an MLP projector for efficient cross-modal alignment, and (3) our MiMo-7B language model, specifically optimized for complex reasoning tasks.

The development of MiMo-VL-7B involves two sequential training processes: (1) A four-stage pre-training phase, which includes projector warmup, vision-language alignment, general multi-modal pre-training, and long-context Supervised Fine-Tuning (SFT). This phase yields the MiMo-VL-7B-SFT model. (2) A subsequent post-training phase, where we introduce Mixed On-policy Reinforcement Learning (MORL), a novel framework that seamlessly integrates diverse reward signals spanning perception accuracy, visual grounding precision, logical reasoning capabilities, and human/AI preferences. This phase yields the MiMo-VL-7B-RL model.

Image: image

We open-source MiMo-VL-7B series, including checkpoints of the SFT and RL model. We believe this report along with the models will provide valuable insights to develop powerful reasoning VLMs that benefit the larger community.

🛤️ During this journey, we find#

• Incorporating high-quality, broad-coverage reasoning data from the pre-training stage is crucial for enhancing model performance
  • We curate high-quality reasoning data by identifying diverse queries, employing large reasoning models to regenerate responses with long CoT, and applying rejection sampling to ensure quality.
  • Rather than treating this as supplementary fine-tuning data, we incorporate substantial volumes of this synthetic reasoning data directly into the later pre-training stages, where extended training yields continued performance improvements without saturation.
• Mixed On-policy Reinforcement Learning further enhances model performance, while achieving stable simultaneous improvements remains challenging
  • We apply RL across diverse capabilities, including reasoning, perception, grounding, and human preference alignment, spanning modalities including text, images, and videos. While this hybrid training approach further unlock model’s potential, interference across data domains remains a challenge.

II. Model Details#

Image: image

Models are available at Huggingface Collections: MiMo-VL and ModelScope Collections: MiMo-VL

III. Evaluation Results#

General Capabilities#

In general visual-language understanding, MiMo-VL-7B models achieve state-of-the-art open-source results.

Image: image

Reasoning Tasks#

In multi-modal reasoning, both the SFT and RL models significantly outperform all compared open-source baselines across these benchmarks.

Image: image

Important. Results marked with \* are obtained using our evaluation framework. Tasks with ${\dagger}$ are evaluated by GPT-4o.

GUI Tasks#

MiMo-VL-7B-RL possess exceptional GUI understanding and grounding capabilities. As a general-purpose VL model, MiMo-VL achieves comparable or even superior performance to GUI-specialized models.

Image: image

Elo Rating#

With our in-house evaluation dataset and GPT-4o judgments, MiMo-VL-7B-RL achieves the highest Elo rating among all evaluated open-source vision-language models, ranking first across models spanning from 7B to 72B parameters.

Image: image

IV. Deployment#

The MiMo-VL-7B series maintain full compatibility with the Qwen2_5_VLForConditionalGeneration architecture for deployment and inference.

V. Citation#

@misc{coreteam2025mimovltechnicalreport,
      title={MiMo-VL Technical Report}, 
      author={LLM-Core-Team Xiaomi},
      year={2025},
      eprint={2506.03569},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.03569}, 
}

VI. Contact#

Please contact us at mimo@xiaomi.com or open an issue if you have any questions.

Use Restrictions#

You are solely responsible for your use of XiaomiMiMo/MiMo-VL-7B-RL and any outputs, actions, or consequences arising therefrom, and you agree not to use the XiaomiMiMo/MiMo-VL-7B-RL or any derivatives thereof:

• For any unlawful, fraudulent, or malicious purpose, or in any manner that violates any applicable laws or regulations；
• To infringe upon the intellectual property rights, privacy rights, publicity rights, or other lawful rights or interests of any third party;
• To exploit, harm, harass, defame, unlawfully discriminate against, or otherwise adversely affect any individual or group, including minors or vulnerable persons;
• For any military purpose or application;
• To engage in or facilitate malicious cyber activities, including but not limited to malware, ransomware, phishing, credential theft, or unauthorized access, or any activity intended to compromise or unlawfully control computer systems, networks, or encryption systems;
• To access, collect, process, disclose, or disseminate personal data or other protected information without appropriate authorization or lawful basis; or to access, interact with, scrape, or automate any third-party platform or service in violation of any applicable laws, policies, or authorization requirements;
• To use the XiaomiMiMo/MiMo-VL-7B-RL in a manner that autonomously executes high-risk actions without appropriate human oversight or authorization.

This notice is an informational reminder only and does not amend the applicable model licence or impose additional licence conditions. The permissions granted under that licence remain unaffected. Nothing in this notice restricts uses permitted by applicable law, including applicable exceptions and limitations.

Usage enquiries and complaints#

mimo-legal@xiaomi.com. For information on submitting a complaint, please visit the https://mimo.xiaomi.com.