Chest X-ray models: pre-trained encoders and task heads for VQA, DiffVQA, RRG, detection, and grounding on MIMIC-CXR.
Denis Musinguzi
dmusingu
AI & ML interests
Multi-modal learning, computer vision and robotics
Recent Activity
published a model about 11 hours ago
dmusingu/cxr-vitl14-lgc updated a model about 13 hours ago
dmusingu/cxr-vitl14-lgc updated a model 7 days ago
dmusingu/diffvqa-qwen3-0.6b-multiobjective-regsteps