All Competitors

Generative EHR foundation model that forecasts which clinical events come next and when, then adapts to pan-cancer risk stratification.

Shared MHC class II neoantigen design for breast cancer, pairing retrieval-augmented ProtT5 embeddings with an MCNN-BiLSTM immunogenicity classifier.

Crop phenotyping vision-language model that answers questions about arbitrarily shaped image regions, routing each task to its own expert branch.

Chest radiograph foundation model with a single latent state behind both diagnostic readout and report-conditioned image generation.

Cancer-registry encoder pretrained by masked field-value modelling on 9.4M SEER tumour records, carrying survival signal into unseen rare cancers.

Graph-grounded language model for antimicrobial resistance reasoning that judges gene-drug links from serialized multi-hop knowledge-graph paths.

Genomic language model for tomato pangenomes that conditions DNA tokens on graph node attributes and local adjacency as well as masked modelling.

Twelve-lead ECG foundation model aligned to clinician-overread report text, adapting to new cardiac tasks from as few as ten labels.

Longitudinal multimodal patient foundation model for oncology, fusing clinical records, DNA, RNA, and H&E pathology into one patient-state embedding.

EEG foundation model trained jointly across nine heterogeneous datasets, decoding by matching brain signals to language-model embeddings of labels.

Pan-cancer clinico-genomic model for treatment response and survival prediction, transferring zero-shot to unseen hospitals and cancer types.

Peptide-focused instruction-tuned LLM that describes function, designs sequences, predicts eight bioactivity properties and edits physicochemistry.

Medical imaging vision-language model for chest X-ray, CT and MRI that generates reports, localizes lesions and compares studies over time.

Vision-language foundation model for coronary angiography that aligns six-view cine studies with procedural reports for zero-shot lesion assessment.

EEG foundation model that decodes by matching neural activity to label text embeddings, with one instruction-tuned checkpoint covering seven tasks.

Virtual-cell model that compresses a transcriptome into eight discrete tokens in a reasoning LLM's vocabulary, predicting module-level drug response.

Medical language model compressed to ternary weights, running a 27B-class clinical and biomedical assistant offline from a single 8.48 GB file.

Endoscopy vision-language foundation model pretrained on 348K gastrointestinal examinations that pair routine clinical reports with image sets.

Chemistry embedding model placing SMILES strings and scientific prose in one vector space, top-tier on 43 of 48 molecular and text benchmarks.

Breast-specialized multimodal pathology foundation model for core needle biopsy diagnosis, with conformal risk control gating report release.

Optical chemical structure recognition model that turns molecule images into SMILES, reaching 93.8% exact match on USPTO with full stereochemistry.

Vision-language model that parses Markush structures from patents in a single stage, turning whole-image drawings into machine-readable CXSMILES.

Protein function captioning model fusing sequence, Foldseek structure tokens, and text through a BLIP-2 Q-Former for open-ended free-text annotation.