Marcel Kollovieh

PhD Student in the Data Analytics and Machine Learning (DAML) group at TUM .


Hi! I am Marcel, a PhD student at the Technical University of Munich (TUM) under the supervision of Prof. Dr. Stephan Günnemann.

Research: My primary focus is on generative models, including variational autoencoders, diffusion, and score-based generative models. I also work on time series, graphs, and hierarchical structures. For a comprehensive overview of my background and research projects, please refer to my CV and publications.

Previously: I received my bachelor’s and master’s degrees in computer science from TUM. Following my graduation, I completed an internship as an applied scientist at AWS AI Labs in Berlin.

Feel free to write me an email if you are interested in discussing with me.

TUM School of CIT
2023 - Present
2022 - 2023
NUS Logo
NUS School of Computing
2018 - 2019
TUM Department of Informatics
2016 - 2022


Oct 2023 Our preprint on score-based adversarial robustness is now available.
Sep 2023 Our paper on unconditional diffusion models for time series forecasting got accepted at NeurIPS 2023.
Jul 2023 Our preprint on unconditional diffusion models for time series forecasting is now available.
Jun 2023 Started my PhD at TUM in the DAML Lab.
Nov 2022 Started my internship at AWS AI Labs in Berlin.