2 papers
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
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…