David Heurtel-Depeiges — accepted AI-conference papers

2025

Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data

David Heurtel-Depeiges, Anian Ruoss, Joel Veness, Tim Genewein

ICML 2025poster

Foundation models are strong data compressors, but when accounting for their parameter size, their compression ratios are inferior to standard compression algorithms. Naively reducing the parameter count does not necessarily help as it deteriorates predictions and, accordingly, compression. We condu…

Cited by 2 Source ↗PDF ↗Scholar ↗

2024

Listening to the noise: Blind Denoising with Gibbs Diffusion

David Heurtel-Depeiges, Charles Margossian, Ruben Ohana, Bruno Régaldo-Saint Blancard

ICML 2024poster

In recent years, denoising problems have become intertwined with the development of deep generative models. In particular, diffusion models are trained like denoisers, and the distribution they model coincide with denoising priors in the Bayesian picture. However, denoising through diffusion-based p…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗