OX-PIXL
SpatialThinker-3B
Based on Qwen/Qwen2.5-VL-3B-Instruct
Tags
- safetensors
- qwen2_5_vl
- spatial-reasoning
- multimodal
- vision-language
- scene-graph
- reinforcement-learning
- conversational
- en
- arxiv:2511.07403
- base_model:Qwen/Qwen2.5-VL-3B-Instruct
- base_model:finetune:Qwen/Qwen2.5-VL-3B-Instruct
Languages
en
- Author
- OX-PIXL
- Task
- image-text-to-text
- Architecture
- qwen2_5_vl
- License
- apache-2.0
- Base model
- Qwen/Qwen2.5-VL-3B-Instruct
- Downloads
- 31
- Likes
- 4