28 citations · 39 across the 9 of their papers we have counts for
6 papers · 1 filter
Towards More General Control of Diffusion Models Using Jeffrey Guidance
Raphaël Razafindralambo, Rémy Sun, Frédéric Precioso +2
A key strength of diffusion models lies in their flexibility, since their outputs can be controlled at sampling time through guidance. However, beyond simple cases such as conditio…
When Are Two Scores Better Than One? Investigating Ensembles of Diffusion Models
Raphaël Razafindralambo, Rémy Sun, Frédéric Precioso +2
Diffusion models now generate high-quality, diverse samples, with an increasing focus on more powerful models. Although ensembling is a well-known way to improve supervised models,…
Towards efficient feature sharing in MIMO architectures
Rémy Sun, Alexandre Ramé, Clément Masson +2
Multi-input multi-output architectures propose to train multiple subnetworks within one base network and then average the subnetwork predictions to benefit from ensembling for free…
MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks
Alexandre Rame, Remy Sun, Matthieu Cord
Recent strategies achieved ensembling "for free" by fitting concurrently diverse subnetworks inside a single base network. The main idea during training is that each subnetwork lea…
A theory of independent mechanisms for extrapolation in generative models
Michel Besserve, Rémy Sun, Dominik Janzing +1
Generative models can be trained to emulate complex empirical data, but are they useful to make predictions in the context of previously unobserved environments? An intuitive idea…
Counterfactuals uncover the modular structure of deep generative models
Michel Besserve, Arash Mehrjou, Rémy Sun +1
Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data. However, manipulating such representation to…