All Competitors

Surface-EMG wristband models that decode hand gestures, handwriting, and wrist movement, generalizing across users without per-person calibration.

Protein language models trained on billions of natural and synthetic sequences for de novo design and zero-shot mutation-effect prediction.

Attention-based multiple instance learning heads for whole-slide pathology, pretrained on a 108-way pan-cancer slide classification task.

Single-cell transcriptomics foundation model that encodes gene regulatory network structure into self-attention through graph signal processing.

Zebrafish single-cell foundation model built on the Geneformer framework, producing frozen gene and cell embeddings for developmental analysis.

Open medical multimodal models from Google, built on Gemma 3 with a medically tuned SigLIP vision encoder for clinical text and image understanding.

Medically tuned SigLIP encoder from Google that maps medical images and text into one embedding space for zero-shot classification and retrieval.

Single-sequence protein structure predictor that adapts image diffusion to generate 2D inter-residue templates, folding proteins without an MSA.

Multimodal all-atom generative model for zero-shot de novo antibody and protein-binder design, validated by wet-lab hit rates from small batches.

Protein-protein interaction predictor that adds contact-guided dual attention and a geometric encoder to frozen protein language model embeddings.

Single-cell perturbation-response model that predicts transcriptomic and imaging outcomes of unseen genetic perturbations via a VAE with attention.

Multimodal foundation model for cardiac biosignals, pretrained by masked modeling on ECG, PPG, and clinical text from ~1.7 million individuals.

Family of CNN foundation models pretrained on multimodal radiology images, a domain-specific alternative to ImageNet transfer learning weights.

Biomedical vision-language assistant for medical visual question answering, pairing Phi-2 with a vision encoder in a 4.2B-parameter model.

Apple's foundation model trained on behavioral signals from wearables, modeling 27 HealthKit metrics to improve predictions across 57 health tasks.

DNA foundation model that predicts thousands of functional genomic tracks, from expression and splicing to chromatin, at single base-pair resolution.

Multi-scale ECG-language model that aligns 12-lead ECG signals with clinical text at token, beat, and rhythm levels for zero-shot cardiac diagnosis.

Virtual cell transformer that predicts how cells respond to genetic, chemical, or signaling perturbations, generalizing to unseen cellular contexts.

Bimodal masked language model that jointly encodes bulk RNA-seq expression and DNA methylation into patient-level embeddings for cancer genomics.

Decoder-only transformer that recasts ancestral recombination graph inference as next-token prediction, estimating coalescence times from variation.

5.6M-parameter multimodal foundation model fusing fMRI time series with diffusion-MRI structural connectivity in a shared ROI embedding space.

CLIP-based vision-language foundation model for eye imaging, enabling zero-shot disease detection and cross-modal retrieval across 11 modalities.

Medical multimodal LLM (2B and 8B) trained for generalizable, step-by-step clinical reasoning via Mentor-Intern Collaborative Search.

Multimodal viral foundation model over nucleotide and protein sequence, built for virus discovery, function annotation, and antibody design.