Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
zhibinlan
/
UME-R1-2B
like
5
Image-Text-to-Text
Transformers
Safetensors
English
qwen2_vl
image-to-text
Sentence Similarity
Embedding
zero-shot-image-classification
video-text-to-text
conversational
text-generation-inference
arxiv:
2511.00405
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
UME-R1-2B
/
figures
565 kB
2 contributors
History:
1 commit
zhibinlan
update readme
e0110ca
about 1 month ago
main_result.png
Safe
271 kB
xet
update readme
about 1 month ago
scaling.png
Safe
295 kB
xet
update readme
about 1 month ago