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

Research: My primary focus is on generative models for non-i.i.d. data, including diffusion models, flow matching, and Bayesian sample inference. I work on time series, graphs, hierarchical structures, molecular generation, and recommender systems. 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. I have worked as a Student Researcher at Google in Mountain View and as an Applied Scientist Intern at Amazon in Berlin.

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

Google
2026

TUM School of CIT
2023 - Present

Amazon
2022 - 2023

NUS School of Computing
2018 - 2019

TUM Department of Informatics
2016 - 2022

News

Jul 2026	Our preprint Interpolating Discrete Diffusion Models with Controllable Resampling is now available.
Apr 2026	I joined Google as a Student Researcher in Mountain View, working on generative recommendation.
Mar 2026	Discrete Bayesian Sample Inference for Graph Generation was accepted at ICLR 2026.
Nov 2025	TreeGen, a Bayesian generative model for hierarchies, was accepted at NeurIPS 2025.
May 2025	Efficient time series processing through token merging was accepted at ICML 2025.
May 2025	Point set diffusion for unlocking point processes was accepted at ICLR 2025.
Jan 2025	At ICLR 2025, we presented flow matching with Gaussian process priors for probabilistic time series forecasting.
Nov 2024	Score-based adversarial image generation was published in Transactions on Machine Learning Research.
Sep 2024	Expected Probabilistic Hierarchies was accepted at NeurIPS 2024.
Sep 2023	Unconditional diffusion models for time series forecasting were accepted at NeurIPS 2023.
Jun 2023	In June 2023, I started my PhD in Informatics at TUM’s Data Analytics and Machine Learning (DAML) group under the supervision of Prof. Dr. Stephan Günnemann, working on generative models for non-i.i.d. data.