About me

I am a PhD student at the University of Passau advised by Professor Florian Lemmerich. My work currently focuses on studying similarity of neural networks.

Publications

Localizing Reasoning Training-Induced Changes in Large Language Models

Max Klabunde, Florian Lemmerich
Mechanistic Interpretability Workshop at Neural Information Processing Systems (NeurIPS), 2025
[Paper] [Code]

ReSi: A Comprehensive Benchmark for Representational Similarity Measures

Max Klabunde, Tobias Schumacher, Markus Strohmaier, Florian Lemmerich
International Conference on Learning Representations (ICLR), 2025
[Paper] [Code]

Revisiting the Relation Between Robustness and Universality

Max Klabunde, Tobias Schumacher, Markus Strohmaier, Florian Lemmerich
Second Workshop on Representational Alignment at International Conference on Learning Representations (ICLR), 2025
[Paper] [Code]

Similarity of Neural Network Models: A Survey of Functional and Representational Measures

Max Klabunde, Tobias Schumacher, Markus Strohmaier, Florian Lemmerich
ACM Computing Surveys, 2025
[Paper] [Code]

Towards Measuring Representational Similarity of Large Language Models

Max Klabunde, Mehdi Ben Amor, Michael Granitzer, Florian Lemmerich
UniReps Workshop at Neural Information Processing Systems (NeurIPS), 2023
[Paper] [Code]

On the Prediction Instability of Graph Neural Networks

Max Klabunde and Florian Lemmerich
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2022
[Paper] [Code]

The Effects of Randomness on the Stability of Node Embeddings

Tobias Schumacher, Hinrikus Wolf, Martin Ritzert, Florian Lemmerich, Jan Bachmann, Florian Frantzen, Max Klabunde, Martin Grohe, Markus Strohmaier
arXiv preprint, 2020
[Paper] [Code]