3 papers
cs.LG2026
LpWM: A Case for Sparse Representations in World Models
Yilun Kuang, Yash Dagade, Quentin Le Lidec +3
Joint-embedding predictive architectures (JEPAs) learn latent dynamics for planning and avoid representation collapse by matching features to maximum-entropy distributions such as…
cs.LG2026
Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations
Yilun Kuang, Yash Dagade, Tim G. J. Rudner +2
Joint-Embedding Predictive Architectures (JEPA) learn view-invariant representations and admit projection-based distribution matching for collapse prevention. Existing approaches r…
cs.LG2026
Radial-VCReg: More Informative Representation Learning Through Radial Gaussianization
Yilun Kuang, Yash Dagade, Deep Chakraborty +4
Self-supervised learning aims to learn maximally informative representations, but explicit information maximization is hindered by the curse of dimensionality. Existing methods lik…