research
∙
05/20/2022
Swapping Semantic Contents for Mixing Images
Deep architecture have proven capable of solving many tasks provided a s...
share
research
∙
05/20/2022
Towards efficient feature sharing in MIMO architectures
Multi-input multi-output architectures propose to train multiple subnetw...
research
∙
03/10/2021
MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks
Recent strategies achieved ensembling "for free" by fitting concurrently...
research
∙
04/01/2020
A theory of independent mechanisms for extrapolation in generative models
Deep generative models reproduce complex empirical data but cannot extra...
research
∙
12/08/2018
Counterfactuals uncover the modular structure of deep generative models
Deep generative models such as Generative Adversarial Networks (GANs) an...
research
∙
04/11/2018