Academia

Publications

Publication figure

Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations

A. Hill, N. McKee, J. Maeß, S. Bluecher, K.-R. Müller

NeurIPS, 2025

Publication figure

A Common Interface for Automatic Differentiation

G. Dalle, A. Hill

Preprint, 2025

Publication figure

Sparser, Better, Faster, Stronger: Sparsity Detection for Efficient Automatic Differentiation

A. Hill and G. Dalle

TMLR, 2025

Publication figure

An Illustrated Guide to Automatic Sparse Differentiation

A. Hill, G. Dalle, A. Montoison

ICLR blog post, 2025

Talks

Leveraging Sparsity to Accelerate Automatic Differentiation

A. Hill, G. Dalle

JuliaCon Local, Paris, 2025

Composable Sparse AD in Julia

WIAS Seminar, Berlin, 2025

Composable Sparse AD in Julia

27th EuroAD Workshop, Kaiserslautern, 2025

Sparse Automatic Differentiation

COSMO Group Seminar, EPFL, Lausanne, 2024

Gradients for everyone: a quick guide to autodiff in Julia

G. Dalle and A. Hill

JuliaCon, Eindhoven, 2024

What's new with Explainable AI in Julia?

JuliaCon, Eindhoven, 2024

ExplainableAI.jl: Interpreting neural networks in Julia

JuliaCon, Remote, 2022

Dithering in Julia with DitherPunk.jl

JuliaCon, Remote, 2022

Awards

Prix science ouverte du logiciel libre de recherche, G. Dalle, A. Hill, 2025:
Open source software award for DifferentiationInterface.jl, awarded by the French Ministry of Higher Education and Research

Teaching

2023–2026: Julia for Machine Learning
2023–2025: Deep Learning 2: Neural ODE lecture
2022–2023: Project Machine Learning

Code under MIT license, text CC BY-SA 4.0, Adrian Hill.
Built with ♥ using Franklin.jl and Julia.
Last modified on January 19, 2026.
Impressum.