Australian National University

Flow cytometry foundation model that reads heterogeneous antibody panels through a universal marker embedding to predict sample-level phenotypes.

Single-nucleotide-resolution RNA foundation model pretrained on non-coding RNAs with ELECTRA-style replaced-token detection for regulatory inference.

Genomic DNA foundation model using ELECTRA-style replaced-token detection and single-nucleotide tokenization; 93M parameters rival 2.5B baselines.

T-cell receptor specificity prediction that separates general antigens from autoimmune-related ones using ESM-2 embeddings and a topology-aware graph.

Physics-guided all-atom diffusion model for protein-ligand complex prediction, reaching 95.3% success on PoseBusters redocking with a known pocket.

RNA secondary structure prediction that turns phylogenetic compensatory-substitution evidence into attention priors over frozen RiNALMo embeddings.

Histopathology model predicting gene expression and DNA methylation from H&E slides across 23 cancer types, fusing FFPE and fresh-frozen predictors.