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.
2023 - Present
2022 - 2023
2018 - 2019
2016 - 2022
News
| May 2025 | Our paper on token merging for time series got accepted at ICML 2025. |
|---|---|
| Feb 2025 | Our preprint Bayesian Sample Inference is now available. |
| Jan 2025 | Our paper on flow matching for time series forecasting got accepted at ICLR 2025. |
| Nov 2024 | Our paper on score-based adversarial robustness has been accepted at TMLR. |
| Sep 2024 | Our paper on probabilistic hierarchical clustering has been accepted at NeurIPS 2024. |
| Oct 2023 | Our preprint on score-based adversarial robustness is now available. |
| Sep 2023 | Our paper on unconditional diffusion models for time series forecasting has been 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. |