|
Yakup Emre Şahin
I’m a PhD researcher in Deep Learning at the University of Liège under the supervision of
Prof. Gilles Louppe, working on scientific foundation models at the intersection
of machine learning and physics.
I did my Master’s on Physics and AI at LMU Munich with DAAD scholarship and wrote my thesis at Helmholtz AI
in the group of Prof. Niki Kilbertus on symbolic regression for dynamical systems.
Before that, I did my double Bachelor’s in Electrical & Electronics Engineering and Physics at Boğaziçi University,
Istanbul and had research internships at different places including CERN and Koç University Gravity group.
Email /
CV /
Bio /
Scholar /
Twitter /
Github
|
|
Research
I am interested in deep learning applications in the physical sciences and in developing
learning techniques. My research focuses on using machine learning to model and understand
complex physical systems, as well as advancing methods that improve efficiency, generalization,
and interpretability.
|
Selected Publications
Predicting symbolic ODEs from multiple trajectories
Yakup Emre Şahin, Niki Kilbertus, Sören Becker
NeurIPS 2025 ML4PS Workshop
We introduce MIO, a transformer-based model for inferring symbolic ordinary differential equations (ODEs) from multiple observed trajectories of a dynamical system.
Subtleties in constraining gravity theories with mass-radius data
Ekrem S. Demirboğa, Yakup Emre Şahin, Fethi M. Ramazanoğlu
Physical Review D
Mass–radius measurements of neutron stars can constrain certain alternative gravity theories like DEF and scalar–Gauss–Bonnet models, though their effectiveness depends on the specific model and mechanism.
DC and pulsed electron beam test facility at CERN
Adriana Rossi, Hao Zhang, Antti Kolehmainen, Wilfried Devauchelle, Sergey Sadovich, Diego Perini,
Yakup Emre Şahin, Jean Cenede, Oliver Stringer, Maxime Toscan du Plantier, Fredrik Wenander,
Ashley Churchman, Franck Guillot-Vignot, Thibaut Coiffet, Muhammed Sameed, Ondrej Sedlacek,
Manfred Wendt
JACoW IPAC 2023
A CERN test stand was built for the Hi-Lumi and ARIES projects to evaluate electron lens and space charge compensation components, featuring versatile diagnostics and instrumentation, with first results confirming the HEL gun design.
|
