All Competitors

EEG foundation model that makes each electrode its own token stream, pretrained by causal next-signal prediction over 138 electrode positions.

Self-supervised 12-lead ECG encoder that predicts masked patches in latent space, using a cross-lead attention mask shaped by clinical reading.

Masked-autoencoder foundation model pretrained on digital-stethoscope heart sounds and single-lead ECG for cardiovascular disease detection.

Convolutional ECG foundation model trained on expert annotations spanning 150 diagnostic categories, with 12-lead and single-lead wearable variants.

ECG foundation model pretrained on 12-lead waveforms paired with clinical reports, enabling label-efficient and zero-shot cardiac diagnosis.

Joint-embedding predictive foundation model pretrained on over a million unlabeled ECGs, learning transferable 12-lead representations for diagnosis.

Brain-dynamics foundation model for resting-state fMRI, adapting the Joint-Embedding Predictive Architecture with brain gradient positioning.

Multimodal contrastive model aligning clinical EEG with free-text reports, enabling zero-shot EEG classification from natural-language prompts.

EEG-to-language foundation model that pairs a Q-Conformer encoder with a frozen LLM to decode coherent sentences from non-invasive brain recordings.

Multi-task EEG foundation model that treats brain signals as a foreign language, pairing a text-aligned neural tokenizer with a GPT-2 backbone.

Nanopore basecaller for fully 5-hydroxymethylcytosine-substituted DNA, reading raw ion current from strands that standard basecallers cannot resolve.

Multimodal ECG-language model aligning 12-lead waveforms with clinical report text for conversational cardiac diagnosis and report generation.

Neural spike decoding model whose Hebbian self-attention yields interpretable low-dimensional embeddings of electrophysiology and calcium imaging.

Foundation model for photoplethysmography (PPG) that learns quality-robust waveform representations for heart rate, blood pressure, and AF detection.

Open transformer foundation model for 12-lead electrocardiograms, pretrained on 1.5 million unlabeled ECGs with a wav2vec 2.0 self-supervised recipe.

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

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

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

EEG foundation model that learns transferable brain-signal representations with a vector-quantized tokenizer and masked transformer pretraining.

Multi-modal foundation model for sleep analysis, learning joint representations across brain, cardiac, and respiratory polysomnography signals.

ECG foundation model that learns 12-lead waveform representations by contrastively aligning each recording with machine-generated cardiological text.

Transformer encoder self-supervised on 100,000 hours of dual-accelerometer data, used as a frozen feature extractor for human activity recognition.

Self-supervised CNN pretrained on 700,000 person-days of UK Biobank accelerometer data for human activity recognition across devices and cohorts.