PixelRefer-Lite-7B

Alibaba-DAMO-Academy/PixelRefer-Lite-7B

PixelRefer-Lite-7B is a video-text-to-text model from Alibaba-DAMO-Academy. Use it for the video-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

<p align="center" <img src="https://cdn-uploads.huggingface.co/production/uploads/64a3fe3dde901eb01df12398/CiwESNwyy7VTooOifRgiQ.png" width="70%" style="margin-bottom: 0.2;"/ <p

Downloads · 30 days

6% of all-time downloads

All-time downloads

459

Public

Repo size

32.3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin16.1 GB · 100%

At a glance

Task: Video-Text-to-Text
Library: transformers
License: apache-2.0
Model type: pixelreferlite_qwen2
Access: Public
Created: Oct 27, 2025
Updated: Oct 28, 2025
SHA: e15b61fa

Base models

DAMO-NLP-SG/VideoLLaMA3-2B-Image

Model card

From the Hugging Face model README

<p align="center"> <img src="https://cdn-uploads.huggingface.co/production/uploads/64a3fe3dde901eb01df12398/CiwESNwyy7VTooOifRgiQ.png" width="70%" style="margin-bottom: 0.2;"/> <p> <h3 align="center"><a href="http://arxiv.org/abs/2510.23603" style="color:#4D2B24"> PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity</a></h3> <div align=center>

</div>

📰 News

[2025.10.28] 🔥We release PixelRefer.
[2025.6.19] 🔥We release the demo of VideoRefer-VideoLLaMA3, hosted on HuggingFace. Feel free to try it!
[2025.6.18] 🔥We release a new version of VideoRefer(VideoRefer-VideoLLaMA3-7B and VideoRefer-VideoLLaMA3-2B), which are trained based on VideoLLaMA3.
[2025.4.22] 🔥Our VideoRefer-Bench has been adopted in Describe Anything Model (NVIDIA & UC Berkeley).
[2025.2.27] 🔥VideoRefer Suite has been accepted to CVPR2025!
[2025.2.18] 🔥We release the VideoRefer-700K dataset on HuggingFace.
[2025.1.1] 🔥We release VideoRefer-7B, the code of VideoRefer and the VideoRefer-Bench.

🌏 Model Zoo

Model Name	Visual Encoder	Language Decoder
PixelRefer-7B	VL3-SigLIP-NaViT	Qwen2.5-7B-Instruct
PixelRefer-2B	VL3-SigLIP-NaViT	Qwen2.5-1.5B-Instruct
PixelRefer-Lite-7B	VL3-SigLIP-NaViT	Qwen2.5-7B-Instruct
PixelRefer-Lite-2B	VL3-SigLIP-NaViT	Qwen2.5-1.5B-Instruct

📑 Citation

If you find VideoRefer Suite useful for your research and applications, please cite using this BibTeX:

@article{yuan2025pixelrefer,
  title     = {PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity},
  author    = {Yuqian Yuan and Wenqiao Zhang and Xin Li and Shihao Wang and Kehan Li and Wentong Li and Jun Xiao and Lei Zhang and Beng Chin Ooi},
  year      = {2025},
  journal   = {arXiv},
}

@inproceedings{yuan2025videorefer,
  title     = {Videorefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM},
  author    = {Yuqian Yuan and Hang Zhang and Wentong Li and Zesen Cheng and Boqiang Zhang and Long Li and Xin Li and Deli Zhao and Wenqiao Zhang and Yueting Zhuang and others},
  booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages     = {18970--18980},
  year      = {2025},
}

Task: Video-Text-to-Text
Library: transformers
Type: pixelreferlite_qwen2
License: apache-2.0
Languages: en
Created: Oct 27, 2025
Updated: Oct 28, 2025