MR-JEPA: A General Purpose Video Foundation Model for Cardiac MRI
iScienceLuvr · x · 2026-09-01
MR-JEPA is a self-supervised video foundation model for Cardiac MRI that extends LeJEPA to 3D spatiotemporal inputs via tubelet tokenization, spatiotemporal masking augmentation, and initialization from a 2D Cardiac MRI foundation model.
It outperforms both a natural-video foundation model (V-JEPA2) and a prior CMR-specific foundation model on all regression tasks while remaining competitive for disease classification, despite using 5x fewer pretraining videos and a smaller architecture.
More from Research
- ExploitGym system prompts reveal little of interest — voooooogel · 2026-09-01
- LightFuse SOTA Relightable 3D Gaussian Reconstruction Beats Baseline by 9.74dB — janusch_patas · 2026-09-01
- Doubt cast on SWA effective receptive field math — giffmana · 2026-09-01
- Call for Papers: Synthetic Populations Research at Frontiers in AI — frederickaplan · 2026-09-01
- Multimodal AI Reveals Mechanism of Shape-Memory Alloy Degradation — bravo_abad · 2026-09-01
- ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation — janusch_patas · 2026-09-01