A new arXiv preprint (2607.28868v1) introduces a physics-aligned augmentation procedure for self-supervised learning in scientific imaging, tested on electron microscopy and 4D-STEM diffraction across…
Researchers show that the frozen predictor from Joint-Embedding Predictive Architectures (JEPAs) can be transferred across encoder families to improve occluded feature completion. In experiments, pair…
Researchers present COJEPA, a self-supervised framework for volumetric brain MRI that combines joint-embedding predictive architecture with contrastive loss, achieving the best monozygotic twin recall…
Elon Litman published a technical walkthrough of Joint Embedding Predictive Architectures (JEPA), Yann LeCun's self-supervised learning method that trains models to predict representations of masked i…
Researchers Chen Huang, Xianhang Li, Vimal Thilak, Etai Littwin, and Josh Susskind have developed Text-Conditional JEPA (TC-JEPA), a visual self-supervised learning model that uses image captions to r…