This is the Epoch 2 SFT checkpoint trained on the SGMRIVQA dataset for spatially grounded visual question answering on volumetric MRI scans (brain and knee).

Model Details

Base Model: Qwen3-VL-8B-Instruct
Training: Supervised Fine-Tuning (SFT), Epoch 2
Task: Spatially Grounded MRI Visual Question Answering
Modalities: Brain MRI (axial), Knee MRI (sagittal)
Data Source: fastMRI+ dataset with clinical expert annotations

SpatialGroundingVQA/Qwen3-VL-8B-SGMRIVQA

Qwen3-8B-SGMRIVQA-SFT

Model Details

SpatialGroundingVQA/
Qwen3-VL-8B-SGMRIVQA