Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Alibaba-DAMO-Academy
/
PixelRefer-2B
like
3
Follow
DAMO Academy
68
Video-Text-to-Text
Transformers
PyTorch
English
pixelrefer_qwen2
text-generation
multimodal large language model
large video-language model
arxiv:
2510.23603
arxiv:
2504.16072
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
main
PixelRefer-2B
/
pytorch_model.bin
Commit History
Add files using upload-large-folder tool
f0de86e
verified
CircleRadon
commited on
Oct 27, 2025