Publications

2025

1. GCLR @AAAI 2026

   Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners

   Daniel Herbst^*, Lea Karbevska^*, Divyanshu Kumar^*, Akanksha Ahuja^*, Fatemeh Gholamzadeh^*, and Fabrizio Frasca

   Workshop on Graphs and more Complex Structures For Learning and Reasoning at AAAI 2026, Nov 2025

   PDF
2. ICLR 2025

   Spotlight

   Higher-Order Graphon Neural Networks: Approximation and Cut Distance

   Daniel Herbst, and Stefanie Jegelka

   International Conference on Learning Representations, Feb 2025

   PDF

   Spotlight

2024

1. NeurIPS 2024

   Spatio-Spectral Graph Neural Networks

   Simon Geisler^*, Arthur Kosmala^*, Daniel Herbst, and Stephan Günnemann

   Advances in Neural Information Processing Systems, Sep 2024

   PDF Code