Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
OX-PIXL
/
SpatialThinker-3B
like
2
Follow
Perceptual Intelligence and Extended Reality Lab
6
Image-Text-to-Text
Safetensors
English
qwen2_5_vl
spatial-reasoning
multimodal
vision-language
scene-graph
reinforcement-learning
conversational
arxiv:
2511.07403
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
4
main
SpatialThinker-3B
/
merges.txt
Commit History
Upload folder using huggingface_hub
3358e8b
verified
hunarbatra
commited on
Nov 7, 2025
hunarbatra
commited on
