xiaomi-open-source/

Xiaomi-MiMo-VL-Miloco-7B

Introduction

🤗 Why you’ll love it:

• Built on MiMo-VL-7B: a rock-solid vision–language backbone with reliable video understanding and instruction-following.
• Home-savvy by design: it spots everyday activities (esports, workouts, watching TV, reading, and more) and reads common hand gestures like the V sign, thumbs-up, open palm, OK, and even the shaka hand sign.
• Base skills intact: with a mix training strategy of SFT and RL, we boost home-scene smarts while keeping the model’s generality and transferability in great shape.

🌟 Training recipe:

Stage 1: Supervised Fine-Tuning (SFT)

• Chain-of-thought supervision: we add chain of reasoning so the model learns structured knowledge about home scenarios.
• Token-budget-aware reasoning: training with “budgeted” reasoning encourages concise, straight-to-the-point answers at inference.

Stage 2: Reinforcement Learning (RL)

• Efficient Training Data: we employed the Time-R1 data strategy (our work accepted at NeurIPS 2025) to build efficient training datasets across multiple domains.
• Keep-it-general: specialize for home tasks while preserving broad understanding and language generation.

😉 Model Recomendation

• MiMo-VL-Miloco-7B

  • Recommended for most users to experience and utilize.

• MiMo-VL-Miloco-7B-GGUF

  • This is the mixed-precision quantized version of MiMo-VL-Miloco-7B. It is recommended for evaluation and use in compute-constrained environments.

Performance

Evaluation of Home-Scenario Undersatnding Capabilities (F1-Score)

• MiMo-VL-Miloco-7B achieves leading performance in both gesture recognition and common household scene understanding.

Results of general capability evaluations

• Across three video benchmarks (Video-MME, Video-MMMU, Charades-STA), the base model shows clear improvements.
• On MMMU-Pro, a general-capabilities benchmark, the base model also saw significant improvements (10+%).
• Surprisingly, as video and image understanding improved, we observed corresponding gains on the text-only task MMLU-Pro.
• We see a modest performance dip on tasks such as document understanding, OCR, and mathematics; this is in line with expectations and does not affect the model’s intended use cases.

Citation

Contact