Author

David Millard

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

One-Step Voice Conversion by Learning kNN Transport in WavLM Space

Voice conversion (VC) systems fall into two families: non-parametric embedding-space methods, which need no trained model but degrade on short target utterances, and spectrogram-based neural architectures, which achieve strong quality via multi-module pipelines with tens of millions of parameters. We propose kNN-FM-VC,...

A. Selitskiy, David Millard · 0 citations

#machine learning Jan 2026

Learning to Advect: A Neural Semi-Lagrangian Architecture for Weather Forecasting

A physics-inspired neural architecture that decomposes latent-state evolution into dedicated advection, diffusion, and reaction operators and achieves competitive deterministic forecast skill, with particularly strong performance at short to medium lead times, while preserving improved spectral fidelity and forecast ac...

Carlos A. Pereira, St'ephane Gaudreault, V. Dallerit et al. · arXiv.org · 5 citations

#machine learning May 2026

Stability of the Monge Map in Semi-Dual Optimal Transport

This paper shows that the semi-dual formulation of the optimal transport problem has a degenerate saddle-point structure, and that its numerical solution is equivalent to solving a constrained optimization problem. We derive necessary and sufficient conditions for the convergence of Monge maps without requiring optimal...

A. Selitskiy, David Millard · arXiv.org · 0 citations