Daniel Gedon

Daniel Gedon

Postdoctoral Researcher
Tübingen AI Center · University of Tübingen

About

I am a postdoctoral researcher at the Tübingen AI Center at the University of Tübingen, working with Jakob Macke. I develop probabilistic machine learning methods for scientific discovery, with a focus on simulation-based inference and foundation models for science.

Research Interests

Scientific model discovery Simulation-based inference Foundation models for science LLMs for science Dynamical systems ECG deep learning

Selected Papers

A Probabilistic Framework for LLM-Based Model Discovery
Stefan Wahl, Raphaela Schenk, Ali Farnoud, Jakob H. Macke, Daniel Gedon  ·  arXiv 2026
arXiv Code
Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Models
Julius Vetter, Manuel Gloeckler, Daniel Gedon*, Jakob H. Macke*  ·  NeurIPS 2025
arXiv OpenReview Code
A Deep Learning ECG Model for Localization of Occlusion Myocardial Infarction
Stefan Gustafsson, Antônio H. Ribeiro, Daniel Gedon, Petrus E.O.G.B. Abreu, Nicolas Pielawski, Gabriela M.M. Paixão, Antonio Luiz P. Ribeiro, Daniel Lindholm, Thomas B. Schön, Johan Sundström  ·  medRxiv 2025
medRxiv
Deep Networks for System Identification: A Survey
Gianluigi Pillonetto, Aleksandr Aravkin, Daniel Gedon, Lennart Ljung, Antônio H. Ribeiro, Thomas B. Schön  ·  Automatica 2025
DOI arXiv
No Double Descent in Principal Component Regression: A High-Dimensional Analysis
Daniel Gedon, Antônio H. Ribeiro, Thomas B. Schön  ·  ICML 2024
OpenReview Code