CompDiff: Hierarchical Compositional Diffusion for Fair and Zero-Shot Intersectional Medical Image Generation

ArXi:2603.16551v1 Announce Type: cross Generative models are increasingly used to augment medical imaging datasets for fairer AI. Yet a key assumption often goes unexamined: that generators themselves produce equally high-quality images across graphic groups. Models trained on imbalanced data can inherit these imbalances, yielding degraded synthesis quality for rare subgroups and struggling with graphic intersections absent from