Research. My research focuses on deep models for tractable probabilistic inference. They can help humans in modeling complex phenomena by dealing with uncertainty. My objective is to enable these models to efficiently provide insights on big collections of (unstructured) data, perform accurate and trustworthy predictions, and generate new valuable data.

Bio. I'm a Ph.D. student in Machine Learning at the Computer Science Department of TU Darmstadt University, Germany. Currently, I'm part of the project KompAKI. Previously, I’ve been part of AIPHES (TU Darmstadt, HITS, Heidelberg University), a Research Training Group mainly focused on Natural Language Processing on large-scale text sources.

Advised Theses
2024. Quantifying and Explaining Latent Uncertainty: Probabilistic Circuits for Robust Deep Learning. M.Sc. thesis, P.R. Emunds (in collaboration w/ Continental AG).
2022. Deep Reinforcement Learning for Portfolio Management in Finance. B.Sc. thesis, D. Jonatan.
2021. Oriented Object Detection using a One-Stage Anchor-Free Deep Model. M.Sc. thesis, S. Lang.
2020. Development of a Load Forecasting Model of the ETA-Factory as a System of Systems based on Machine Learning. M.Sc. thesis, M.A. Zahid (co-advised with Jessica Walther, PTU - TU Darmstadt).
2020. Fake News Detection on Social Media Using Geometric Deep Learning. M.Sc. thesis, S. Stenger.
2019. Predicting the Rise and Fall of Machine Learning Topics. M.Sc. thesis, J.H. Abel.

Publications