Uppsala University

Multimodal foundation model for cardiac biosignals, pretrained by masked modeling on ECG, PPG, and clinical text from ~1.7 million individuals.

Contrastive k-mer embedding model for sequencing reads whose latent space encodes genomic position, matching BWA-aln accuracy on ancient DNA mapping.

Molecular conformation description language encoding 3D geometry as SMILES plus internal-coordinate tokens, turning 3D modeling into a sequence task.

Spider silk protein language model that generates MaSp repeat sequences from target mechanical properties and predicts those properties from sequence.

Cell type annotation from multiplexed tissue images, using a pretrained Vision Transformer ensemble that runs on new panels without fine-tuning.