Publications
Research advancing our understanding of how neural networks develop.
Influence Dynamics and Stagewise Data Attribution
October 14, 2025 | Lee et al.
Current training data attribution (TDA) methods treat the influence one sample has on another as sta...
Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
October 14, 2025 | Urdshals et al.
We study neural network compressibility by using singular learning theory to extend the minimum desc...
Embryology of a Language Model
August 1, 2025 | Wang et al.
Understanding how language models develop their internal computational structure is a central proble...
Structural Inference: Interpreting Small Language Models with Susceptibilities
April 25, 2025 | Baker et al.
We develop a linear response framework for interpretability that treats a neural network as a Bayesi...
Programs as Singularities
April 10, 2025 | Murfet and Troiani
We develop a correspondence between the structure of Turing machines and the structure of singularit...
You Are What You Eat – AI Alignment Requires Understanding How Data Shapes Structure and Generalisation
February 8, 2025 | Lehalleur et al.
In this position paper, we argue that understanding the relation between structure in the data distr...
Dynamics of Transient Structure in In-Context Linear Regression Transformers
January 29, 2025 | Carroll et al.
Modern deep neural networks display striking examples of rich internal computational structure.
Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient
October 4, 2024 | Wang et al. | ICLR | Spotlight
We introduce refined variants of the Local Learning Coefficient (LLC), a measure of model complexity...
Loss landscape geometry reveals stagewise development of transformers
June 16, 2024 | Wang et al. | ICML HiLD Workshop | Best Paper
The development of the internal structure of neural networks throughout training occurs in tandem wi...
Loss Landscape Degeneracy and Stagewise Development of Transformers
February 4, 2024 | Hoogland et al. | TMLR | Best Paper at 2024 ICML HiLD Workshop
We show that in-context learning emerges in transformers in discrete developmental stages, when they...
Dynamical versus Bayesian Phase Transitions in a Toy Model of Superposition
October 10, 2023 | Chen et al.
We investigate phase transitions in a Toy Model of Superposition (TMS) using Singular Learning Theor...
The Local Learning Coefficient: A Singularity-Aware Complexity Measure
August 23, 2023 | Lau et al. | AISTATS 2025
Deep neural networks (DNN) are singular statistical models which exhibit complex degeneracies.
October 2025
Influence Dynamics and Stagewise Data Attribution
October 14, 2025 | Lee et al.
Current training data attribution (TDA) methods treat the influence one sample has on another as sta...
Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
October 14, 2025 | Urdshals et al.
We study neural network compressibility by using singular learning theory to extend the minimum desc...
September 2025
August 2025
Embryology of a Language Model
August 1, 2025 | Wang et al.
Understanding how language models develop their internal computational structure is a central proble...
July 2025
April 2025
Structural Inference: Interpreting Small Language Models with Susceptibilities
April 25, 2025 | Baker et al.
We develop a linear response framework for interpretability that treats a neural network as a Bayesi...
Programs as Singularities
April 10, 2025 | Murfet and Troiani
We develop a correspondence between the structure of Turing machines and the structure of singularit...
February 2025
You Are What You Eat – AI Alignment Requires Understanding How Data Shapes Structure and Generalisation
February 8, 2025 | Lehalleur et al.
In this position paper, we argue that understanding the relation between structure in the data distr...
January 2025
Dynamics of Transient Structure in In-Context Linear Regression Transformers
January 29, 2025 | Carroll et al.
Modern deep neural networks display striking examples of rich internal computational structure.
October 2024
Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient
October 4, 2024 | Wang et al. | ICLR | Spotlight
We introduce refined variants of the Local Learning Coefficient (LLC), a measure of model complexity...
June 2024
Loss landscape geometry reveals stagewise development of transformers
June 16, 2024 | Wang et al. | ICML HiLD Workshop | Best Paper
The development of the internal structure of neural networks throughout training occurs in tandem wi...
February 2024
Loss Landscape Degeneracy and Stagewise Development of Transformers
February 4, 2024 | Hoogland et al. | TMLR | Best Paper at 2024 ICML HiLD Workshop
We show that in-context learning emerges in transformers in discrete developmental stages, when they...
October 2023
Dynamical versus Bayesian Phase Transitions in a Toy Model of Superposition
October 10, 2023 | Chen et al.
We investigate phase transitions in a Toy Model of Superposition (TMS) using Singular Learning Theor...
August 2023
The Local Learning Coefficient: A Singularity-Aware Complexity Measure
August 23, 2023 | Lau et al. | AISTATS 2025
Deep neural networks (DNN) are singular statistical models which exhibit complex degeneracies.