Want to use SOTA Self Supervised Learning (SSL) methods on noisy data? We provide a novel training curriculum that significantly improves test performance on clean and noisy samples! The approach is fully SSL and works on any method (DINOv2, MoCo, ...) arxiv.org/abs/2505.12191

Want better training and geometric insights for Sparse AutoEncoders (SAEs)? Search no more... We leverage spline theory to provide a new "EM-like" training algo (PAM-SGD) and to delve into SAE geometry with connections to PCA, k-means, and more... arxiv.org/abs/2505.11836

Learning by reconstruction captures uninformative details in your data. This “attention to details” biases the ViT’s attention. Our solution: a new token aggregator->improves (significantly) MAE linear probe perf. and (slightly) JEPAs like I-JEPA arxiv.org/abs/2412.03215

Understanding the evolution of historical maps is key to track the development of civilizations (urbanization, environmental changes, ...). We show how to use Self Supervised Learning to do that without supervision! arxiv.org/abs/2411.17425 (SSL workshop NeurIPS24)