AI RESEARCH
The Learnability Gap in Medical Latent Diffusion
arXiv CS.CV
•
ArXi:2605.17087v1 Announce Type: new Generative data augmentation with latent diffusion models is a promising strategy for addressing class imbalance in medical imaging, yet current approaches focus on perceptual fidelity and domain-specific autoencoder fine-tuning while neglecting a fundamental bottleneck.