All Competitors

Self-supervised foundation model for 12-lead ECG, pairing masked autoencoder pretraining with contrastive regularization for robust diagnostics.

Multimodal generative protein language model reasoning jointly over protein sequence, structure, and function, trained at 98B parameters.

Self-supervised masked autoencoder for functional MRI that learns representations from BOLD time-series with per-ROI embeddings and graph attention.

DeepLabV3 segmentation model that separates tissue from glass background in H&E and IHC whole-slide images, as used by the HEST-Library.

Respiratory acoustic foundation models pretrained on roughly 136K cough and breathing recordings for disease detection and lung function estimation.

Blind peptide binder design from a protein sequence alone, evolving linear or cyclic binders against a frozen AlphaFold2 with no binding site given.

RNA tertiary structure prediction from sequence alone with a variational autoencoder over distance matrices, reaching 4.5 A RMSE on short RNAs.

Multimodal model fusing pre-trained DNA, RNA, and protein encoders through cross-attention to predict tissue-specific transcript isoform expression.

3D vision-transformer foundation model for multimodal neuroimage segmentation, pretrained self-supervised on brain MRI from 41,400 participants.

Fluorescence microscopy denoising for transient synaptic signals, done frame by frame so one checkpoint transfers across sensors and frame rates.

Scaling-law study of protein language models identifying compute-optimal training for causal and masked objectives on 939 million protein sequences.

Medical image segmentation foundation model for 3D CT and MRI, covering 127 anatomical classes automatically plus interactive point-prompt refinement.

Histopathology foundation models pretrained with DINOv2 on over 1 million whole-slide images, released as Hibou-B and Hibou-L under Apache 2.0.

Single-cell foundation model with 800M parameters trained on ~100 million human cells, for annotation, perturbation prediction, and gene analysis.

Single-cell transcriptomics foundation model with 100 million parameters, pretrained on over 50 million human scRNA-seq profiles for cell embeddings.

Microsoft Research multimodal LLM for grounded chest X-ray report generation, localizing each described finding with bounding boxes on the image.

Structure-based molecular design that samples a quantum electron cloud in the protein pocket, then decodes it into ligands with a Llama-style model.

Multi-task protein framework recasting function, binding site, and structure prediction as autoregressive next-token prediction over ESM2 embeddings.

Virtual staining models that translate label-free light microscopy into fluorescent-equivalent predictions of nuclei and plasma membranes.

Discrete diffusion model that generates RNA secondary structure contact maps as pixel-wise segmentation, conditioned on RNA-FM and UFold features.

Full-atom peptide binder design against a target pocket, generating backbone frames, side-chain torsions and residue types in one joint flow.

Protein function prediction model that conditions a T5 encoder-decoder on retrieved homologs to assign EC numbers, GO terms and Pfam families.

Neural ab initio reconstruction for cryo-EM and cryo-ET that jointly infers particle poses and a continuous landscape of conformational states.