JEPAMatch augments FlexMatch with LeJEPA-derived latent regularization to produce better-structured representations, yielding higher accuracy and faster convergence on CIFAR-100, STL-10, and Tiny-ImageNet.
In: Proceedings of the 58th annual meeting of the association for computational linguistics
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
JEPAMatch: Geometric Representation Shaping for Semi-Supervised Learning
JEPAMatch augments FlexMatch with LeJEPA-derived latent regularization to produce better-structured representations, yielding higher accuracy and faster convergence on CIFAR-100, STL-10, and Tiny-ImageNet.
- Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning