University of Wisconsin-Madison

Clinical EEG foundation model reading 17 findings — seizures, spikes, slowing, burst suppression, sleep stages — from one pretrained transformer.

3D brain MRI synthesis from separate hemisphere and cerebellum-brainstem diffusion priors, assembled and refined into one volume with editable parts.

Protein-protein interface prediction that summarizes molecular surface patches with persistent homology descriptors, at 0.77 test AUC.

Whole-body CT segmentation covering 235 fine-grained anatomies: 193 organs, 33 lymph node stations, and 9 lesion types from one unified network.

Cellular senescence prediction from protein sequence, pairing ESM-2 embeddings with a hybrid BiLSTM-CNN classifier at 86.43% test accuracy.

Text-guided molecule generation by linking a pretrained scientific text encoder to a frozen molecular language model with a cross-attention adapter.

Medical imaging embedding model spanning X-ray, CT, MRI, dermoscopy, OCT, fundus, ultrasound, histopathology and mammography in one encoder.

Genome language model that embeds a genome as a set of contextualized protein embeddings, pretrained on over 100,000 viruses for viromics.

Protein language models pretrained on Rosetta biophysics simulations rather than evolutionary data, then finetuned on small experimental assays.