2 papers
cs.LG2025
Self-Supervised Siamese Autoencoders
Friederike Baier, Sebastian Mair, Samuel G. Fadel
In contrast to fully-supervised models, self-supervised representation learning only needs a fraction of data to be labeled and often achieves the same or even higher downstream pe…
stat.ML2025
Principled Interpolation in Normalizing Flows
Samuel G. Fadel, Sebastian Mair, Ricardo da S. Torres +1
Generative models based on normalizing flows are very successful in modeling complex data distributions using simpler ones. However, straightforward linear interpolations show unex…