Models (9)
Reinforcement learning framework that fine-tunes the ProGen2-OAS antibody language model with GRPO to cut germline bias in generated sequences.
Protein-protein docking model adapting AlphaFold-Multimer with a docking module and flow-matching training to assemble subunits without MSAs.
Schrödinger-bridge diffusion model for virtual multiplex staining, translating routine H&E histology into multiplex immunohistochemistry images.
BrainFM
Johns Hopkins University / Massachusetts General Hospital / Harvard Medical School / Danish Research Centre for Magnetic Resonance / University College London
Released August 30, 2025
Modality-agnostic foundation model for human brain imaging that runs five core neuroimaging tasks across uncalibrated CT and MRI without retraining.
Med-R1
Emory University / University of Southern California / University of Tokyo / Johns Hopkins University / Georgia Institute of Technology
Released March 18, 2025
Medical vision-language model trained with reinforcement learning for generalizable reasoning across eight imaging modalities and five question types.
GenomeOcean
DOE Joint Genome Institute / Northwestern University / Johns Hopkins University / University of California, Merced / University of California, Berkeley / Miami University / Illumina
Released February 5, 2025
4B-parameter generative genome foundation model trained on assembled environmental metagenomes for microbial representation and de novo DNA design.
Diffusion model for protein-protein docking that unifies pose sampling and energy-based ranking, works without MSAs, and generalizes to new targets.
Mixture-of-Experts foundation model for medical image segmentation that generalizes across imaging modalities and clinical centers.
CLIP-Driven Universal Model
City University of Hong Kong / Johns Hopkins University / NVIDIA
Released October 1, 2023
Abdominal CT segmentation model driven by CLIP text embeddings, covering 25 organs and 6 tumor types with zero-shot extension to new categories.