All Competitors

Family of transformer-based DNA language models using BPE tokenization and BigBird sparse attention to reach context lengths up to 36,000 base pairs.

Vision transformer for electrocardiograms that reads the printed 12-lead ECG as an image, enabling data-efficient diagnosis from few labeled examples.

Single-cell foundation model pretrained on about 30 million human transcriptomes, using rank-value encoding for context-aware gene network inference.

Multimodal pathology assistant that answers questions about histology and cytology images, pairing the PathCLIP vision encoder with a Vicuna-13B LLM.

Zero-shot antibody affinity maturation using ESM pseudolikelihood scoring. Improves binding up to 160-fold with no antigen-specific training data.

Single-cell foundation model pre-trained on 22 million transcriptomes, using rank-based gene encoding for clustering and trajectory inference.

Scalable and transferable U-Net family (14M–1.4B parameters) for 3D medical image segmentation, supervised-pretrained on TotalSegmentator.

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

Joint sequence-structure protein representation framework that fuses ESM-2 language model embeddings with GearNet geometric graph neural networks.

Biomedical vision-language model trained contrastively on 15M PubMed Central figure-caption pairs for zero-shot classification, retrieval, and VQA.

Medical vision-language pretraining unifying fusion-encoder and dual-encoder designs, handling image-only, text-only, and paired inputs in one model.

Masked DNA language model trained on over 800 vertebrate genomes and conditioned on species identity to learn conserved regulatory sequence features.

Masked DNA language model trained on 800+ species with explicit species conditioning, separating conserved regulatory motifs from background bias.

Parameter-efficient protein language model that matches larger models such as ESM-2 on protein prediction tasks using under 10% of the parameters.

DNA foundation models from 500M to 2.5B parameters, trained on 3,200+ human genomes and 850 species for variant effect prediction.

Transformer framework for single-cell multi-omics that predicts cross-modality relationships using heterogeneous graphs of cells, genes, and proteins.

Multi-modal protein language model trained on sequences paired with biomedical text, enabling zero-shot function prediction and text-based retrieval.

RNA language model pre-trained on 2M+ pre-mRNA sequences from 72 vertebrate species for splice-site prediction and variant effect analysis.

Antibody CDR design model that reprograms a frozen English BERT for sequence infilling, avoiding training a dedicated protein language model.

Text-conditioned latent diffusion model that generates synthetic chest X-rays from free-form radiology prompts by adapting Stable Diffusion.

Scientific large language model trained on 48 million papers, textbooks, and reference works to store, combine, and reason about scientific knowledge.

Genome-scale language model trained on prokaryotic genes and SARS-CoV-2 genomes to model viral evolution and flag emerging variants of concern.

Large-scale chemical language model trained on 1.1 billion SMILES strings using linear attention transformers for molecular property prediction.

Word2vec-based language model trained on 360 million microbial genes that predicts gene function from genomic context without sequence homology.