3

Leveraging Free Energy in Pretraining Model Selection for Improved Fine-Tuning

Temperature Optimization for Bayesian Deep Learning

The Local Learning Coefficient: A Singularity-Aware Complexity Measure

The Developmental Landscape of In-Context Learning

Received a best papers award at ICML 2024 Workshop on High-dimensional Learning Dynamics (HiLD): The Emergence of Structure and Reasoning

Dynamical versus Bayesian Phase Transitions in a Toy Model of Superposition

Variational Bayesian Neural Networks via Resolution of Singularities

Automating the assessment of biofouling in images using expert agreement as a gold standard