publications

2025

1. ICML

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

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

   Forty-second International Conference on Machine Learning, 2025

   To appear in ICML 2025

   PDF

2024

1. ICML

   

   Listening to the noise: Blind Denoising with Gibbs Diffusion

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

   In Forty-first International Conference on Machine Learning, 2024

   Bib PDF Code Poster

   @inproceedings{heurte2023listening,
     title = {Listening to the noise: Blind Denoising with Gibbs Diffusion},
     author = {Heurtel-Depeiges, David and Margossian, Charles and Ohana, Ruben and R{\'e}galdo-Saint Blancard, Bruno},
     booktitle = {Forty-first International Conference on Machine Learning},
     year = {2024},
     url = {https://openreview.net/forum?id=rmEgJ7bhuZ},
   }

2023

1. ML4PS NeurIPS

   Removing Dust from CMB Observations with Diffusion Models

   David Heurtel-Depeiges, Blakesley Burkhart, Ruben Ohana, and Bruno Régaldo-Saint Blancard

   ML for the Physical Sciences Workshop, NeurIPS, 2023

   Oral presentation

   PDF