All Competitors

An fMRI foundation model that trains Vision Transformers on cortical flat-map videos via masked autoencoding, exhibiting power-law scaling on brain activity reconstruction.

A CLIP-based visual-language foundation model for multi-modal ophthalmic imaging, enabling zero-shot disease detection across 11 modalities including fundus, OCT, and slit-lamp.

A masked-autoencoder foundation model that pre-trains a 3D Residual Encoder U-Net on ~39k brain MRIs to improve volumetric medical image segmentation.

Masked-autoencoder foundation models pretrained on millions of unlabeled digital-stethoscope PCG and ECG recordings, fine-tuned for cardiovascular disease detection.

A self-supervised foundation model for 12-lead ECG that combines masked autoencoder pretraining with contrastive regularization for robust diagnostics across clinical domains.

A multimodal generalist foundation model for ophthalmic imaging, self-supervised on 2.78M images across 11 modalities for diagnosis, prognosis, and visual question answering.

A masked-autoencoder EEG pretraining framework that maps any electrode layout to a unified topology for topology-agnostic, cross-dataset representations.

A self-supervised foundation model for retinal images, pretrained on 1.6M fundus and OCT scans to detect ocular and systemic disease.

A foundation model for fMRI brain activity recordings, pretrained with masked autoencoding on ~6,700 hours of data for clinical prediction and zero-shot network discovery.