3 papers
cs.LG2026
Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners
Daniel Herbst, Lea Karbevska, Divyanshu Kumar +3
While promising, graph reasoners based on Large Language Models (LLMs) lack built-in invariance to symmetries in graph representations. Operating on sequential graph serializations…
cs.LG2026
Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability
Vincent Bürgin, Vincent Bürgin, Daniel Herbst +2
Many striking phenomena in deep learning, such as linear mode connectivity and the structured behavior of training dynamics, are closely tied to parameter symmetries: transformatio…
cs.LG2025
Higher-Order Graphon Neural Networks: Approximation and Cut Distance
Daniel Herbst, Stefanie Jegelka
Graph limit models, like graphons for limits of dense graphs, have recently been used to study size transferability of graph neural networks (GNNs). While most literature focuses o…