3 papers
eess.IV2026
Discovering shared interpretable operations in image compression autoencoders
Caroline Mazini Rodrigues, Nicolas Keriven, Thomas Maugey
With the increasing adoption of deep learning for applications such as image compression, improvements in the rate-distortion trade-off have been achieved at the cost of increasing…
stat.ML2026
Notes on generative modeling: flow matching, diffusion, optimal transport and Schr{ö}dinger bridge
Titouan Vayer
These notes recapitulate the high level mathematical principles behind different techniques for generative modeling. I show the connections between optimal transport and standard t…
cs.CV2026
A Projection-Based Surrogate Gradient Interpretation for Neural Codec Wrappers
Esteban Pesnel, Julien Le Tanou, Michael Ropert +2
Neural wrappers are learned pre-and postprocessing networks designed to enhance the performance of conventional video codecs. Although these approaches can significantly improve co…