Charles Dossal — accepted AI-conference papers

2026

FlowID: Enhancing Forensic Identification with Latent Flow-Matching Models

Jules Ripoll, David Bertoin, Charles Dossal, Alasdair Newson, Jose Pablo Baraybar

IJCAI 2026

Every day, many people die under violent circumstances, whether from crimes, war, migration, or climate disasters. Medico-legal and law enforcement institutions document many portraits of the deceased for evidence, but cannot immediately carry out identification on them. While traditional image edit

Cited by 0 Scholar ↗

2025

Gradient correlation is a key ingredient to accelerate SGD with momentum

Julien Hermant, Marien Renaud, Jean-François Aujol, Charles Dossal, Aude Rondepierre

ICLR 2025poster

Empirically, it has been observed that adding momentum to Stochastic Gradient Descent (SGD) accelerates the convergence of the algorithm. However, the literature has been rather pessimistic, even in the case of convex functions, about the possibility of theoretically proving this observation. We inv…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗