README.md

---
license: cc-by-nc-nd-4.0
library_name: peft
base_model: lmms-lab/LLaVA-Video-7B-Qwen2
tags:
  - video-understanding
  - long-video
  - visual-question-answering
  - lora
  - qwen2
  - llava
  - cvpr2026
datasets:
  - lmms-lab/LLaVA-Video-178K
pipeline_tag: video-text-to-text
---

# QViC-MF-7B

This is the official model for the paper **"Question-guided Visual Compression with Memory Feedback for Long-Term Video Understanding"** (CVPR 2026).

- **Paper:** [arXiv](https://arxiv.org/abs/2603.15167)
- **Code:** [GitHub](https://github.com/FujitsuResearch/QViC-MF)
- **Authors:** Sosuke Yamao\*, Natsuki Miyahara\*, Yuankai Qi, Shun Takeuchi
- **Affiliation:** Fujitsu Research / Macquarie University

## Model Description

QViC-MF-7B is a LoRA adapter trained on top of [LLaVA-Video-7B-Qwen2](https://huggingface.co/lmms-lab/LLaVA-Video-7B-Qwen2) for long-term video understanding. It introduces **Question-guided Multimodal Selective Attention (QMSA)**, which learns to preserve visual information related to the given question from both the current clip and past related frames stored in a context memory. The compressor and memory feedback work iteratively for each clip of the entire video, enabling strong performance on tasks that require understanding complete events (e.g., temporal ordering).

## How to Use

Please refer to the [official code repository](https://github.com/FujitsuResearch/QViC-MF) for inference and evaluation scripts.

## Model Details

| Property | Value |
|----------|-------|
| Base Model | [lmms-lab/LLaVA-Video-7B-Qwen2](https://huggingface.co/lmms-lab/LLaVA-Video-7B-Qwen2) |
| Architecture | LlavaQwenForCausalLM |
| Vision Encoder | SigLIP-SO400M (google/siglip-so400m-patch14-384) |
| LLM | Qwen2-7B |
| Adapter | LoRA (r=64, alpha=16) |
| Context Memory Length | 256 tokens |
| Precision | bfloat16 |

## Citation

```bibtex
@inproceedings{yamao2026qvicmf,
  title={Question-guided Visual Compression with Memory Feedback for Long-Term Video Understanding},
  author={Yamao, Sosuke and Miyahara, Natsuki and Qi, Yuankai and Takeuchi, Shun},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2026}
}
```

## License

This model is released under the [CC-BY-NC-ND-4.0](https://creativecommons.org/licenses/by-nc-nd/4.0/) license.