collaborators

9 papers

cs.LG2025

Forward Only Learning for Orthogonal Neural Networks of any Depth

Paul Caillon, Alex Colagrande, Erwan Fagnou +2

Backpropagation is still the de facto algorithm used today to train neural networks. With the exponential growth of recent architectures, the computational cost of this algorithm a…

cs.LG2025

On the MIA Vulnerability Gap Between Private GANs and Diffusion Models

Ilana Sebag, Jean-Yves Franceschi, Alain Rakotomamonjy +2

Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis. While both can be trained under differential privac…

cs.CL2025

Improving Diversity in Language Models: When Temperature Fails, Change the Loss

Alexandre Verine, Florian Le Bronnec, Kunhao Zheng +3

Increasing diversity in language models is a challenging yet essential objective. A common approach is to raise the decoding temperature. In this work, we investigate this approach…

cs.CV2025

Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics

Alex Colagrande, Paul Caillon, Eva Feillet +1

Transformers have become the de facto standard for a wide range of tasks, from image classification to physics simulations. Despite their impressive performance, the quadratic comp…

cs.LG2025

Bridging the Theoretical Gap in Randomized Smoothing

Blaise Delattre, Paul Caillon, Quentin Barthélemy +2

Randomized smoothing has become a leading approach for certifying adversarial robustness in machine learning models. However, a persistent gap remains between theoretical certified…

cs.LG2025

Fast Training of Recurrent Neural Networks with Stationary State Feedbacks

Paul Caillon, Erwan Fagnou, Alexandre Allauzen

Recurrent neural networks (RNNs) have recently demonstrated strong performance and faster inference than Transformers at comparable parameter budgets. However, the recursive gradie…