Open access
Aug 2026
A JEPA-Inspired Span-Masked Framework for Language Representation Learning: Revisiting Cosine Similarity and VICReg Regularization
A lightweight span-masked JEPA-inspired framework that formulates language representation learning as latent semantic prediction from partially observed contextual inputs is proposed, offering an efficient experimental foundation for future self-supervised language models.
C. Jareanpon, Khanabhorn Kawattikul
· Applied Sciences · 0 citations