Action-conditioned JEPA models treat pathology as a transition vector on latent states to simulate cardiac dynamics, outperforming supervised learning by over 0.05 AUROC in low-resource regimes on MIMIC-IV-ECG.
Mimic-iv-ecg-ext-icd: Diagnostic labels for mimic-iv-ecg (version 1.0
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
LAMAE learns cross-lead interactions in ECGs via latent attention in a masked autoencoder, providing structural supervision that improves representation quality and outperforms baselines on ICD-10 code prediction.
citing papers explorer
-
Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAs
Action-conditioned JEPA models treat pathology as a transition vector on latent states to simulate cardiac dynamics, outperforming supervised learning by over 0.05 AUROC in low-resource regimes on MIMIC-IV-ECG.
-
Foundation Model for Cardiac Time Series via Masked Latent Attention
LAMAE learns cross-lead interactions in ECGs via latent attention in a masked autoencoder, providing structural supervision that improves representation quality and outperforms baselines on ICD-10 code prediction.