All Competitors

A 4.7B-parameter Mixture-of-Experts genomic foundation model pretrained on ~1.2 trillion nucleotide tokens from human-associated microbial genomes.

A unified bio-language Mixture-of-Experts foundation model spanning DNA, protein sequence and structure, and biological text, applied across eight task families from a single checkpoint.

A 1.25B-parameter Mixture-of-Experts genomic foundation model for rice, pretrained on 422 Oryza genomes with a 1 Mbp context window.

A family of SE(3)-equivariant molecular foundation models pretrained on ~70M DFT conformers, reaching state of the art on TDC ADMET and MoleHB property-prediction benchmarks.

Generative virtual-cell engine that unifies clinical RNA-seq and perturbation-assay data to predict transcriptomic responses to unseen compounds and genetic perturbations across biological scales.

A pan-cancer generative model that predicts spatial gene expression from H&E histology using conditional flow matching with a mixture-of-experts velocity field.

Retrieval-augmented genomic foundation model that adds an explicit hash-based k-mer motif memory to transformer backbones, gaining up to 14% on functional genomics tasks.

A Mixture-of-Experts generative model that turns DNA sequence plus cell-type ATAC-seq into unified epigenomic, transcriptomic, and 3D chromatin profiles, generalizing to unseen cell types.

A 422M-parameter pan-viral genomic language model that produces fixed genome-level embeddings reused across viral classification tasks without re-training.

A lightweight plant genome foundation model pairing a bidirectional Mamba backbone with a sparse Mixture-of-Experts, pretrained on 25.4B nucleotides from 42 plant species.

EEG foundation model for brain-computer interfaces, using amplitude-aware masked pretraining and a progressive mixture-of-experts transformer across diverse electrode setups.

A self-supervised foundation model for structural brain MRI combining DenseNet and Vision Transformer with Mixture of Experts for multi-task brain disease diagnosis and brain age prediction.

Sparse mixture-of-experts autoregressive protein language model family pretrained on 1.5 trillion amino acid tokens with compute-optimal scaling.

Biomedical multimodal LLM with pixel-level insight, combining visual question answering, pixel-grounded prompts, and segmentation via a mixture-of-experts design.

A 16-billion-parameter mixture-of-experts protein language model pretrained on 1.2 trillion amino acids, the first MoE architecture applied to protein foundation modeling.

The first open foundation model for photoplethysmography (PPG), pretrained on ~20M PPG segments with morphology-aware representation learning for cardiovascular and health tasks.

A universal foundation model for brain lesion segmentation on multi-modal brain MRI, using a Mixture of Modality Experts to handle diverse modalities and lesion types.

A Mixture-of-Experts foundation model for medical multimodal image segmentation that generalizes across imaging modalities and clinical centers.

A lightweight mixture-of-experts medical vision-language model that routes between domain-specific experts for VQA and image classification while activating only 30-50% of parameters.