LeJEPA
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures
arXiv:2606.01443v1 Announce Type: new Abstract: A central difficulty in training Joint-Embedding Predictive Architectures (JEPAs) is preventing representation collapse. LeJEPA addresses this by enforcing an isotropic Gaussian target on the embeddings via Sketched Isotropic Gaussian Regularization (SIGReg). This target is in tension with the manifold hypothesis, which expects embeddings to concentrate on a low-dimensional subset of the ambient space.
LuMamba: Latent Unified Mamba for Electrode Topology-Invariant and Efficient EEG Modeling
arXiv:2603.19100v2 Announce Type: replace Abstract: Electroencephalography (EEG) enables non-invasive monitoring of brain activity across clinical and neurotechnology applications, yet building foundation models for EEG remains challenging due to differing electrode topologies and computational scalability, as Transformer architectures incur quadratic sequence complexity. As a joint solution, we propose LuMamba (Latent Unified Mamba), a self-supervised framework combining topology-invariant...
Self-Soupervision: Cooking Model Soups without Labels
Announce Type: replace Abstract: Model soups are strange and strangely effective combinations of parameters. They take a model (the stock), fine-tune it into multiple models (the ingredients), and then mix their parameters back into one model (the soup) to improve predictions. While all known soups require supervised learning, and optimize the same loss on labeled data, our recipes for Self-Soupervision generalize soups to self-supervised learning (SSL).
CR-JEPA: Cross-Modal Joint-Embedding Predictive Learning for Remote Sensing Image Retrieval
arXiv:2606.00706v2 Announce Type: replace Abstract: Cross-modal remote sensing image retrieval aims to retrieve semantically related scenes across heterogeneous sensing modalities. This remains challenging because paired observations may differ substantially in imaging physics, spatial resolution, spectral configuration, and visual appearance. Moreover, a single retrieval projection trained with one objective may be insufficient to jointly support cross-modal semantic alignment and...