Heidelberg University Hospital

Genomic variant effect prediction from a bidirectional absorbing-diffusion model over human DNA, pretrained with entropy-guided span masking.

Histopathology model predicting 102 methylation-defined CNS tumor subtypes from H&E whole-slide images, with calibrated per-case confidence scores.

Slide-level histopathology encoder that contrastively aligns tile embeddings from several patch foundation models through a Mamba-2 aggregator.

Diffusion autoencoder framework that morphs H&E tiles until a pathology classifier flips, exposing the morphology behind the prediction.