All Competitors

Self-supervised Siamese network for cryo-electron tomography, enabling zero-shot denoising, segmentation, and macromolecule detection in tomograms.

Pathology foundation model that fuses global patch and cell-level tokens via joint-weighted attention pooling for H&E-based biomarker detection.

Genomics foundation model that unifies sequence-to-function prediction, DNA language modeling, and generative regulatory design in one backbone.

Multi-target drug discovery framework pairing a diffusion-transformer generator with evolutionary latent-space search and synthesis-aware scoring.

Transformer foundation model for single-cell ATAC-seq that embeds both cells and cis-regulatory elements for annotation and batch correction.

Latent diffusion model for generating single-cell gene expression profiles, pairing a permutation-invariant autoencoder with a diffusion transformer.

Digital pathology foundation models from PathAI, spanning a 22M-parameter variant and a 1.1B-parameter flagship trained on 551K whole-slide images.

Hierarchical transformer with 1.2 billion parameters that predicts personalized gene expression from diploid genomes for variant effect prediction.

Histopathology foundation model extracting general-purpose features from H&E patches by distilling the UNI, Phikon, and CONCH pathology encoders.

Foundation model for tandem mass spectrometry that embeds MS/MS spectra into a learned chemical space, resolving isomers and classifying disease.

Protein-ligand cofolding model that predicts 3D complex structures with SO(3)-equivariant diffusion, trained on physics-based synthetic data.

Open-source Apache-2.0 reproduction of AlphaFold3 that predicts all-atom structures of proteins, RNA, DNA, small molecules, and their complexes.

EEG foundation model whose learned queries map any electrode montage into a fixed latent space, scaling linearly in the number of channels.

Multimodal EHR foundation model that fuses polygenic risk scores into a GPT-2-style backbone by cross-attention for zero-shot disease risk prediction.

Perturbation-trained single-cell foundation models (up to 3B parameters) that jointly model genes, cells, and compounds for precision oncology tasks.

Vision Transformer foundation model for spatial metabolomics, pretrained on ~4,000 curated METASPACE mass spectrometry imaging datasets.

Multimodal LLM that tokenizes single cells into discrete VQ-VAE codebook tokens, letting one model reason jointly over transcriptomes and text.

fMRI foundation model of the human brain connectome: 1.2B parameters and brain-environment interaction tokens for behavior and disease prediction.

EEG foundation model for brain-computer interfaces, pairing masked pretraining with a mixture-of-experts transformer across electrode montages.

fMRI foundation model trained on cortical flat-map videos with masked autoencoding, showing power-law scaling on brain activity reconstruction.

Efficient sequence-to-function transformer for regulatory genomics, matching Borzoi-class models while training in about a day on a single GPU.

Proprietary family of multimodal protein language models (up to 102B parameters) for sequence and structure generation, editing, and design.

Self-supervised single-cell foundation model that predicts masked gene embeddings in latent space using a joint-embedding predictive architecture.

Protein foundation model with 3B parameters, pretrained jointly on sequence and 3D structure via masked language modeling and diffusion denoising.