Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Unbiased Open World Regularization for Fair Self-Supervised Learning
L{é}o Nicollier, Marc Pic, Pablo Mus{é} +2
Despite recent advances, self-supervised learning (SSL) models and Joint-Embedding Predictive Architectures (JEPAs) remain susceptible to learning spurious biases in the dataset. T…
cs.LG2026
Expanding SPHERE-JEPA: A Family of Statistical Regularizers for the Hypersphere
Léo Nicollier, Enric Meinhardt-Llopis, Max Dunitz +3
In Self-Supervised Learning (SSL), preventing representation collapse by explicitly enforcing a uniform distribution on the unit hypersphere has proven to be effective. However, cu…
cs.LG2026
SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings
Léo Nicollier, Max Dunitz, Marc Pic +3
A fundamental open question in self-supervised learning (SSL) is the explicit characterization of the optimal geometry of the learned representations. Recently, LeJEPA identified i…