publications

Causal and Interpretable Structures in LLM Compositional Tasks

The Geometry of Ignorance: LLMs Know When to Temper Bayesian Priors

A Graph Signal Processing Perspective on Numerical Sequence Representations in LLM In-Context Learning

Jacobian Scopes: token-level causal attributions in LLMs

Twirled Perfect Tensor Networks: Computationally covariant holographic tensor networks

Geometric surprises in the Python’s lunch conjecture

Quasinormal Modes of Black Holes: Small Perturbations of Black Holes