Phone (office): +39 049 827 7774
BIOGRAPHY
Leon Marx is a first year Ph.D. student in Information Engineering at the Department of Information Engineering, University of Padova. He received his Bachelor’s Degree in Physics from the University of Heidelberg in 2022 with a thesis on domain generalization using generative AI. In 2025, he received his Master’s degree in Physics from the same university with a thesis on continual learning for computer vision focusing on generative and weakly-supervised ML. The thesis was carried out at the Department of Information Engineering in Padova in a collaboration with the University of Heidelberg.
RESEARCH AREAS
Continual Learning
Learning tasks over a series of consecutive steps without forgetting previous knowledge, allowing for efficient adaptation and personalization.
Semantic Segmentation
Semantic segmentation refers to the pixel-level classification of image data, yielding a fine-grained understanding of the scene.
Generative Machine Learning
Generative models learn to mirror a given data distribution providing synthetic samples that closely resemble the real training data.
Weakly-Supervised Learning
Weakly-supervised learning aims to train models without the need for fully-annotated data, avoiding high labeling costs and increasing model autonomy.
PUBLICATIONS
0000
DR.WILSS: Diffusion-Based Replay for Weakly Supervised Class-Incremental Semantic Segmentation Unpublished
Submitted to the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 0000.