Academia
Publications & preprints
Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations
A. Hill, N. McKee, J. Maeß, S. Bluecher, K.-R. Müller
NeurIPS paper, 2025A Common Interface for Automatic Differentiation
G. Dalle, A. Hill
Preprint, 2025Sparser, Better, Faster, Stronger: Sparsity Detection for Efficient Automatic Differentiation
A. Hill and G. Dalle
TMLR paper, 2025An Illustrated Guide to Automatic Sparse Differentiation
A. Hill, G. Dalle, A. Montoison
ICLR blog post, 2025
Conference talks
Leveraging Sparsity to Accelerate Automatic Differentiation
A. Hill, G. Dalle
JuliaCon Local, Paris, 2025Composable Sparse AD in Julia
27th EuroAD Workshop, Kaiserslautern, 2025Gradients for everyone: a quick guide to autodiff in Julia
G. Dalle and A. Hill
JuliaCon, Eindhoven, 2024What's new with Explainable AI in Julia?
JuliaCon, Eindhoven, 2024ExplainableAI.jl: Interpreting neural networks in Julia
JuliaCon, Remote, 2022Dithering in Julia with DitherPunk.jl
JuliaCon, Remote, 2022
Teaching
2024–2026: Julia for Machine Learning (course)
2023–2024: Julia for Machine Learning (seminar)
2023–2025: Deep Learning 2 – Neural ODE lecture
2022–2023: Project Machine Learning