Jonas Jürß (Juerss, /jʏʀs/)

Hi, I’m Jonas. I’m currently pursuing a PhD in Machine Learning at the University of Cambridge in the CaRAML group under the supervision of Pietro Liò.

My research interests are broadly in the fields of (Mechanistic) Interpretability and Graph Neural Networks. I am also a member of the WISDOM consortium, developing predictive models for complex diseases (in particular multiple sclerosis). However, the underlying motivation of understanding the inner workings of neural networks stretches pretty much across all fields, so feel free to about anything that interests you.

Prior to this, I worked as a Machine Learning Engineer at Cambridge Consultants and received an MPhil in Advanced Computer Science from Cambridge as well as a BSc in Informatics from the Technical University of Munich (TUM).

Publications

Archival

Recursive Algorithmic Reasoning
Jonas Jürß, Dulhan Jayalath, and Petar Veličković
Oral: In Proceedings of the Second Learning on Graphs Conference (LoG), PMLR 231, 2023
Recursive Reasoning with Neural Networks
Jonas Jürß and Dulhan Jayalath
In The First Tiny Papers Track at ICLR, 2023
No matching items

Non-Archival

Rethinking Test Generalisation In Neural Algorithmic Reasoning
Manasvi Aggarwal, Dulhan Jayalath, and Jonas Jürß
In The Fourth Learning on Graphs Conference (LoG, Extended Abstracts Track), 2025
Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts
Jonas Jürß, Lucie Charlotte Magister, Pietro Barbiero, Pietro Liò, and Nikola Simidjievski
In NeurIPS Workshop: New Frontiers in Graph Learning, 2023
No matching items