Cornell University

Phylogeny-informed transformer that detects episodic diversifying selection in codon alignments, amortizing maximum-likelihood dN/dS tests.

Tandem mass spectrum prediction that builds explicit fragmentation pathways, mapping unknown spectra onto 800 million predicted PubChem spectra.

Long-context plant DNA language model, 676M parameters on a Mamba2 backbone, pretrained on 65 angiosperm genomes for cross-species variant annotation.

Multi-species genomics foundation model spanning representation learning, functional-track prediction, and sequence generation at 1 Mb context.

Missense variant pathogenicity predictor that also ranks candidate diseases, aligning ESM-2 protein embeddings with PubMedBERT disease text.

Autoregressive graph transformer generating molecules as node and edge token sequences, fine-tunable for goal-directed design and property prediction.

Long-context protein language model on a bidirectional Mamba backbone, outperforming ESM-2 by up to 30% at matched training token budgets.

Keypoint-based foundation model for brain MRI registration, pretrained on over 100,000 3D volumes for rigid, affine, and deformable alignment.

Convolutional ensemble that predicts where and how much transcription initiates from human DNA sequence at single-nucleotide resolution.

Bidirectional, reverse-complement equivariant DNA language models built on Mamba state space models for long-range variant effect prediction.

Medical image segmentation model that solves unseen segmentation tasks in context from a few labeled examples, with no retraining or fine-tuning.