collaborators

5 papers

cs.CV2026

LeVLJEPA: End-to-End Vision-Language Pretraining Without Negatives

Lukas Kuhn, Giuseppe Serra, Randall Balestriero +1

Vision-language pretraining remains dominated by contrastive objectives, whereas vision-only self-supervised learning has largely adopted non-contrastive methods. At the same time,…

cs.CV2026

Non-Contrastive Vision-Language Learning with Predictive Embedding Alignment

Lukas Kuhn, Giuseppe Serra, Florian Buettner

Vision-language models have transformed multimodal representation learning, yet dominant contrastive approaches like CLIP require large batch sizes, careful negative sampling, and…

cs.LG2025

Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond

Giuseppe Serra, Florian Buettner

Given the ability to model more realistic and dynamic problems, Federated Continual Learning (FCL) has been increasingly investigated recently. A well-known problem encountered in…

cs.LG2025

DATS: Distance-Aware Temperature Scaling for Calibrated Class-Incremental Learning

Giuseppe Serra, Florian Buettner

Continual Learning (CL) is recently gaining increasing attention for its ability to enable a single model to learn incrementally from a sequence of new classes. In this scenario, i…

cs.LG2025

How to Leverage Predictive Uncertainty Estimates for Reducing Catastrophic Forgetting in Online Continual Learning

Giuseppe Serra, Ben Werner, Florian Buettner

Many real-world applications require machine-learning models to be able to deal with non-stationary data distributions and thus learn autonomously over an extended period of time,…