All Competitors

Swin transformer foundation model for fluorescence microscopy image restoration, unifying denoising, super-resolution, and volumetric reconstruction.

Drug combination synergy prediction across cancer cell lines, from LLM text embeddings of drugs and cell lines rather than structures or expression.

RNA language model pretrained on 231 bacterial and archaeal RNA families that generates full-length rRNA and scores mutations for thermostability.

Genomic language model trained on metagenomic scaffolds that learns protein co-regulation and function by modeling gene context and operon structure.

Transformer language model for 5' UTR sequences that predicts mRNA translation efficiency, ribosome loading, and protein expression levels.

Multimodal large language model for 3D medical imaging that handles report generation, visual question answering, and segmentation on CT volumes.

Structure-based drug design that steers a frozen 3D molecule diffusion model with user-supplied pharmacophore points inside a protein pocket.

Protein language model-based sequence search that detects remote homologs with threefold higher sensitivity than MMseqs2 at comparable speed.

Equivariant graph network that embeds a protein domain structure as a 128-dimensional vector, turning fold recognition into nearest-neighbour search.

Vision-language model for 3D chest CT that aligns whole volumes with radiology reports for zero-shot abnormality detection and case retrieval.

Separable 4D CNN that strips rotational streak artifacts from respiration-resolved cone-beam CT, processing all ten breathing phases in one pass.

Transformer encoder self-supervised on 100,000 hours of dual-accelerometer data, used as a frozen feature extractor for human activity recognition.

Five DINO and DINOv2 tile encoders pretrained on 29k open-access TCGA slides, sampled online at four magnifications instead of a fixed patch set.

Histopathology vision-language foundation model pretrained on 1.17 million image-caption pairs with contrastive and captioning objectives.

Computational pathology foundation model (ViT-L/16, DINOv2) pretrained on over 100 million H&E tiles from more than 100,000 whole-slide images.

Self-supervised CNN pretrained on 700,000 person-days of UK Biobank accelerometer data for human activity recognition across devices and cohorts.

Bulk tumor transcriptome model ensembling hundreds of variational autoencoders into interpretable cancer-specific latent spaces for 18 cancers.

RNA language model that builds base-pairing constraints into self-attention, pretrained on 20.4 million sequences for structure and function tasks.

3D molecule generation that models atom coordinates and element types as distribution parameters updated by Bayesian inference, not by denoising.

Protein language models pretrained on Rosetta biophysics simulations rather than evolutionary data, then finetuned on small experimental assays.

Self-supervised 3D CT foundation model that extracts general-purpose tumor representations for cancer imaging biomarker discovery and prognosis.

Transformer neural speech decoder for intracranial ECoG and sEEG contacts at arbitrary cortical positions, generalizing to unseen participants.

Genome annotation model that labels 14 genic and regulatory element classes at single-nucleotide resolution across DNA windows up to 50 kb.