Monash University

Intraoperative X-ray to CT registration that reads the preoperative volume as a second input, removing the per-patient training step entirely.

Protein-sequence-conditioned mixture-of-experts language model that designs small molecules and emits an explicit synthesis route for each one.

Conditional denoising diffusion model that designs antigen-specific TCR CDR3β sequences conditioned on peptide-MHC targets and germline V-genes.

Dirichlet flow-matching model for protein design that generates family-aware sequences from ancestral-reconstruction priors, not random noise.

Graph-transformer foundation model pretrained on 3M protein pockets and 5M molecules as E(3)-equivariant graphs for protein-ligand representation.

Small-molecule structure elucidation from tandem mass spectra, generating SMILES by conditional diffusion guided by fragmentation patterns.

5.6M-parameter multimodal foundation model fusing fMRI time series with diffusion-MRI structural connectivity in a shared ROI embedding space.

CLIP-based vision-language foundation model for eye imaging, enabling zero-shot disease detection and cross-modal retrieval across 11 modalities.

DNA and RNA language model with a data-driven 4,096-token unigram vocabulary, matching larger genomic foundation models at 89.2M parameters.

General medical vision-language model trained with reinforcement learning to reason step by step over medical images for diagnosis and visual QA.

Enzyme turnover number (kcat) prediction from sequence and substrate SMILES, scaling to genome-wide kinetic parameters for metabolic modeling.

Histology-anchored framework pairing an H&E foundation model with a cellular hypergraph to predict single-cell multi-omics from tissue images.

Vision-language assistant that reads a whole gigapixel pathology slide, answering diagnostic questions and writing slide-level descriptions.