School of Informatics, University of Edinburgh
I am a PhD student at the School of Informatics, University of Edinburgh and part of the APRIL Lab. I am primarily supervised by Antonio Vergari, who leads the lab, with Michael U. Gutmann as my secondary advisor.
I mainly work on probabilistic machine learning. Currently, I am interesting in making probabilistic predictions obey rules, so guaranteeing that the probability mass of the prediction only covers the space that is allowed by the rules. In practice, this means that I think a lot about how to calculate integrals over non-standard domains efficiently and exactly. But in general, i am open minded and curios!
This line of work led to A Probabilistic Neuro-Symbolic Layer For Algebraic Constraint Satisfaction, which received the runner-up best student paper award at UAI 2025.
My code is on GitHub. Please do not hesitate to reach out to me via email if you have any questions or want to collaborate!
Education
-
University of EdinburghPhD in Informatics2024 - 2027
-
Eberhard Karls University of TuebingenMS in Informatics2019 - 2023
-
Karlsruhe Institute of TechnologyUndergraduate studies in Informatics2015 - 2019
Selected Publications (view all )
Making Generative Models Know What They Don't Know via Hypothesis Testing
Leander Kurscheidt, Antonio Vergari
ICML 2026 Workshop on Testing Poster
Hypothesis-testing-based uncertainty estimation for generative models, aimed at making model confidence better aligned with what the model truly knows.
Making Generative Models Know What They Don't Know via Hypothesis Testing
Leander Kurscheidt, Antonio Vergari
ICML 2026 Workshop on Testing Poster
Hypothesis-testing-based uncertainty estimation for generative models, aimed at making model confidence better aligned with what the model truly knows.
The Theory and Practice of MAP Inference over Non-Convex Constraints
Leander Kurscheidt, Gabriele Masina, Roberto Sebastiani, Antonio Vergari
ICML 2026 Poster
A study of MAP inference in the presence of non-convex constraints, spanning theoretical and practical aspects of structured probabilistic inference.
The Theory and Practice of MAP Inference over Non-Convex Constraints
Leander Kurscheidt, Gabriele Masina, Roberto Sebastiani, Antonio Vergari
ICML 2026 Poster
A study of MAP inference in the presence of non-convex constraints, spanning theoretical and practical aspects of structured probabilistic inference.
A Probabilistic Neuro-symbolic Layer for Algebraic Constraint Satisfaction
Leander Kurscheidt, Paolo Morettin, Roberto Sebastiani, Andrea Passerini, Antonio Vergari
UAI 2025 Oral Runner-up Best Student Paper
A probabilistic neuro-symbolic approach for algebraic constraint satisfaction, connecting learned representations with structured reasoning.
A Probabilistic Neuro-symbolic Layer for Algebraic Constraint Satisfaction
Leander Kurscheidt, Paolo Morettin, Roberto Sebastiani, Andrea Passerini, Antonio Vergari
UAI 2025 Oral Runner-up Best Student Paper
A probabilistic neuro-symbolic approach for algebraic constraint satisfaction, connecting learned representations with structured reasoning.