Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
internlm
/
Spatial-SSRL-Qwen3VL-4B
like
9
Follow
Intern Large Models
879
Image-Text-to-Text
Transformers
Safetensors
internlm/Spatial-SSRL-81k
English
qwen3_vl
image-to-text
multimodal
spatial
sptial understanding
self-supervised learning
conversational
arxiv:
2510.27606
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Spatial-SSRL-Qwen3VL-4B
/
assets
20.8 MB
1 contributor
History:
4 commits
yuhangzang
Upload exp_result_new3.png
76de6a9
verified
2 months ago
111.txt
0 Bytes
Create assets/111.txt
2 months ago
case-qwen3vl.jpg
5.85 MB
xet
Upload 2 files
2 months ago
comparison_v2.png
3.37 MB
xet
Upload 3 files
2 months ago
eg1.jpg
69.7 kB
Upload 2 files
2 months ago
exp_result_new3.png
72.6 kB
Upload exp_result_new3.png
2 months ago
pipeline_1029final.png
7.84 MB
xet
Upload 3 files
2 months ago
teaser_1029final.png
3.58 MB
xet
Upload 3 files
2 months ago