Dr Sebastian Cygert
Research interests: trustworthy AI, robustness, continual learning
Dr. Eng. Sebastian Cygert conducts research on reliable and trustworthy machine learning models capable of functioning correctly and adapting to the surrounding world. His research has been published at leading AI conferences such as NeurIPS, ICLR, ECCV, WACV, BMVC, or Interspeech.
He also has extensive commercial experience—he previously worked as a Applied Scientist at Amazon, where he contributed to projects such as the visual perception system for the autonomous robot and speech synthesis for Alexa.
He is a member of the Ellis Society.
Selected Publications
Articles
Daniel Marczak, Simone Magistri, Sebastian Cygert, Bartłomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer, "No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces", Proceedings of the 42nd International Conference on Machine Learning, PMLR 267, 2025, 43177-43199.