Published multiple papers, including 'SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance', which proposes integrating rich priors from VLM pre-training into semi-supervised semantic segmentation to learn better semantic decision boundaries.
Research Experience
Research Scientist at Google Zurich since Aug 2024; Student Researcher at Google Zurich, working on Vision-Language Models from Apr 2023 to Nov 2023; PreMaster Program at Bosch Center for Artificial Intelligence, focusing on Explainable Artificial Intelligence from Feb 2019 to Jul 2019; Research Internship at Bosch Center for Artificial Intelligence, working on Environment Representations for Deep Learning from Oct 2018 to Dec 2018.
Education
Ph.D. at the Computer Vision Lab, ETH Zurich, supervised by Prof. Luc Van Gool from Sep 2021 to Jun 2024; M.Sc. in Robotics, Systems and Control, ETH Zurich, awarded the ETH Medal for an outstanding Master’s thesis from Sep 2019 to Jun 2021; B.Sc. in Computer Systems in Engineering, Otto von Guericke University Magdeburg, Germany, Best Graduate at the Computer Science Department 2018/19 from Oct 2015 to Jan 2019.
Background
Research interests include domain-robust and label-efficient visual scene understanding, including domain-adaptive, domain-generalizable, semi-supervised, self-supervised, language-guided, and generative learning. During his Ph.D., he interned at Google to work on vision-language models for label-efficient semantic segmentation.