We're excited to announce improvements to our MiMo-VL (MiMo-VL-7B-RL-2508 and MiMo-VL-7B-SFT-2508), featuring enhanced performance across multiple benchmarks, improved thinking control capabilities, and better user experience.
MiMo-VL-7B-RL-2508 demonstrates consistent improvements across both image and video benchmarks, achieving notable milestones of 70.6 on MMMU and 70.8 on VideoMME.
<think>...</think>
To determine the appealing features of the Xiaomi SU7, we analyze visual elements and context from the video:
1. Aesthetic Design
- The car boasts a sleek, aerodynamic exterior with smooth, modern lines.
- Distinctive lighting (sharp headlights and a continuous, glowing taillight strip) enhances its futuristic and sporty look.
- Vibrant color and polished finish make it visually striking.
2. Performance & Speed
- Multiple dynamic shots of the car driving at high speeds on diverse roads (desert, forest, city) emphasize agility and power.
- Close - ups of spinning wheels and the engine (with lightning-like effects) suggest advanced engineering and high-performance capabilities (likely electric or tech-driven).
3. Versatility
- The car is shown in varied environments (desert at dusk, forested roads, urban streets), highlighting its adaptability to different terrains and use cases.
4. Technological Innovation
- The engine close-up with electric-like lightning effects implies cutting-edge technology, positioning the car as a tech-forward vehicle (aligning with Xiaomi’s tech brand identity).
5. Brand Appeal
Prominent “Xiaomi SU7” branding leverages Xiaomi’s reputation in consumer tech, adding credibility and allure for tech-savvy audiences.
In summary, the Xiaomi SU7 appeals through its striking design, high-performance capabilities, versatility, technological innovation, and strong brand association.
Users can control the thinking mode by appending /no_think to queries:
Thinking mode query (default): "What is the answer to the question in the image?"
Non-thinking mode query: "Identify the text in the image. /no_think"
❗️Important: The /no_think command must be the very last part of user message, which means after /no_think, there shouldn't be any user content like image or video.
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.
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.
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.
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.
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.
You are solely responsible for your use of XiaomiMiMo/MiMo-VL-7B-RL-2508 and any outputs, actions, or consequences arising therefrom, and you agree not to use the XiaomiMiMo/MiMo-VL-7B-RL-2508 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-2508 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.
XiaomiMiMo <huggingface.co/XiaomiMiMo>Newsgroups: alt.freeweights.mimoSubject: 
unsloth 
mlx-community