All Competitors

Generative medical visual question answering model that pairs a vision encoder with a language model, trained on the 227k-pair PMC-VQA dataset.

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.

Biomedical vision-language model trained contrastively on 1.6M figure-caption pairs mined from PubMed Central open-access articles.

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.

Self-supervised pretraining for 3D medical images that learns anatomical correspondences between scans, giving encoders transferable to segmentation.

AlphaFold fine-tuned on peptide-MHC and protein-peptide binding data for specificity prediction across MHC class I/II, PDZ, and SH3 domains.

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

Gene regulatory network inference from single-cell multi-omics, with in silico simulation of transcription factor perturbations across cell types.

Geometric relational graph neural network that encodes 3D protein structures through geometry-aware message passing and self-supervised pretraining.

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.

End-to-end single-cell multimodal analysis framework using deep parametric inference to integrate RNA and protein data into a unified latent space.

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.

Self-supervised pretraining framework for medical imaging that unifies pixel restoration with contrastive learning across 2D and 3D image backbones.

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.

Gene expression prediction from histone modifications, combining self-attention with dense convolutions and transfer learning across cell types.