Daniel Murfet

According to our database, Daniel Murfet authored at least 27 papers between 2014 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Patterning: The Dual of Interpretability.

George Wang, Daniel Murfet

CoRR, January, 2026

Towards Spectroscopy: Susceptibility Clusters in Language Models.

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

CoRR, January, 2026

Stagewise Reinforcement Learning and the Geometry of the Regret Landscape.

Chris Elliott, Einar Urdshals, David Quarel, Matthew Farrugia-Roberts, Daniel Murfet

CoRR, January, 2026

Gentzen-Mints-Zucker duality.

Daniel Murfet, William Troiani

Math. Struct. Comput. Sci., 2026

Linear logic and the Hilbert scheme.

Daniel Murfet, William Troiani

Math. Struct. Comput. Sci., 2026

2025

Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory.

Einar Urdshals, Edmund Lau, Jesse Hoogland, Stan van Wingerden, Daniel Murfet

CoRR, October, 2025

Embryology of a Language Model.

George Wang, Garrett Baker, Andrew Gordon, Daniel Murfet

CoRR, August, 2025

Studying Small Language Models with Susceptibilities.

Garrett Baker, George Wang, Jesse Hoogland, Daniel Murfet

CoRR, April, 2025

Modes of Sequence Models and Learning Coefficients.

Zhongtian Chen, Daniel Murfet

CoRR, April, 2025

Programs as Singularities.

Daniel Murfet, William Troiani

CoRR, April, 2025

You Are What You Eat - AI Alignment Requires Understanding How Data Shapes Structure and Generalisation.

Simon Pepin Lehalleur, Jesse Hoogland, Matthew Farrugia-Roberts, Susan Wei, Alexander Gietelink Oldenziel, George Wang, Liam Carroll, Daniel Murfet

CoRR, February, 2025

Dynamics of Transient Structure in In-Context Linear Regression Transformers.

Liam Carroll, Jesse Hoogland, Matthew Farrugia-Roberts, Daniel Murfet

CoRR, January, 2025

Open Problems in Mechanistic Interpretability.

Lee Sharkey, Bilal Chughtai, Joshua Batson, Jack Lindsey, Jeffrey Wu, Lucius Bushnaq, Nicholas Goldowsky-Dill, Stefan Heimersheim, Alejandro Ortega, Joseph Isaac Bloom, Stella Biderman, Adrià Garriga-Alonso, Arthur Conmy, Neel Nanda, Jessica Rumbelow, Martin Wattenberg, Nandi Schoots, Joseph Miller, William Saunders, Eric J. Michaud, Stephen Casper, Max Tegmark, David Bau, Eric Todd, Atticus Geiger, Mor Geva, Jesse Hoogland, Daniel Murfet, Tom McGrath

Trans. Mach. Learn. Res., 2025

Loss Landscape Degeneracy and Stagewise Development in Transformers.

Jesse Hoogland, George Wang, Matthew Farrugia-Roberts, Liam Carroll, Susan Wei, Daniel Murfet

Trans. Mach. Learn. Res., 2025

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

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

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

The Local Learning Coefficient: A Singularity-Aware Complexity Measure.

Edmund Lau, Zach Furman, George Wang, Daniel Murfet, Susan Wei

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

The Developmental Landscape of In-Context Learning.

Jesse Hoogland, George Wang, Matthew Farrugia-Roberts, Liam Carroll, Susan Wei, Daniel Murfet

CoRR, 2024

2023

Deep Learning Is Singular, and That's Good.

Susan Wei, Daniel Murfet, Mingming Gong, Hui Li, Jesse Gell-Redman, Thomas Quella

IEEE Trans. Neural Networks Learn. Syst., December, 2023

Dynamical versus Bayesian Phase Transitions in a Toy Model of Superposition.

Zhongtian Chen, Edmund Lau, Jake Mendel, Susan Wei, Daniel Murfet

CoRR, 2023

Quantifying degeneracy in singular models via the learning coefficient.

Edmund Lau, Daniel Murfet, Susan Wei

CoRR, 2023

2022

Elimination and cut-elimination in multiplicative linear logic.

Daniel Murfet, William Troiani

CoRR, 2022

2021

Geometry of Program Synthesis.

James Clift, Daniel Murfet, James Wallbridge

CoRR, 2021

2020

Cofree coalgebras and differential linear logic.

James Clift, Daniel Murfet

Math. Struct. Comput. Sci., 2020

Encodings of Turing machines in linear logic.

James Clift, Daniel Murfet

Math. Struct. Comput. Sci., 2020

Deep Learning is Singular, and That's Good.

Daniel Murfet, Susan Wei, Mingming Gong, Hui Li, Jesse Gell-Redman, Thomas Quella

CoRR, 2020

Logic and the 2-Simplicial Transformer.

James Clift, Dmitry Doryn, Daniel Murfet, James Wallbridge

Proceedings of the 8th International Conference on Learning Representations, 2020

2014

Logic and linear algebra: an introduction.

Daniel Murfet

CoRR, 2014