spatial-grounding
HoliSpatial-3D-GroundingSGMRI-VQA
🧲🧠💬 SGMRI-VQA: Spatially Grounded MRI Visual Question Answering 🧲🧠💬
If you use SGMRI-VQA or the model (Qwen3-VL-8B-SGMRIVQA) in your research, please cite our paper. If you find this dataset useful, we also appreciate a ⭐ on our GitHub repository.
SGMRI-VQA: 41,307-pair VQA benchmark for multi-frame spatially grounded reasoning on MRI, built from expert radiologist annotations in the fastMRI+ dataset across brain and knee studies. Each QA pair is paired with a… See the full description on the dataset page: https://huggingface.co/datasets/SpatialGroundingVQA/SGMRI-VQA.SpatialGrounding
