Stan van Wingerden — accepted AI-conference papers

2026

Towards Spectroscopy: Susceptibility Clusters in Language Models

Andrew Gordon, Daniel Murfet, William Snell, Garrett Baker, George Wang, Stan van Wingerden

ICML 2026poster

Spectroscopy infers the internal structure of physical systems by measuring their response to perturbations. We apply this principle to neural networks: perturbing the data distribution by upweighting a token $y$ in context $x$, we measure the model's response via susceptibilities $\chi_{xy}$, which…

Cited by 0 Source ↗Scholar ↗

2025

Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient

George Wang, Jesse Hoogland, Stan van Wingerden, Zach Furman, Daniel Murfet

ICLR 2025spotlight

We introduce refined variants of the Local Learning Coefficient (LLC), a measure of model complexity grounded in singular learning theory, to study the development of internal structure in transformer language models during training. By applying these refined LLCs (rLLCs) to individual components of…

Cited by 1 Source ↗PDF ↗Scholar ↗