In this work, we improve the generative replay in a continual learning
s...
Currently, over half of the computing power at CERN GRID is used to run ...
Diffusion models have achieved remarkable success in generating high-qua...
We introduce a joint diffusion model that simultaneously learns meaningf...
This work focuses on modelling a speaker's accent that does not have a
d...
Generative Adversarial Networks (GANs) are powerful models able to synth...
Diffusion-based Deep Generative Models (DDGMs) offer state-of-the-art
pe...
We introduce a neural network architecture that logarithmically reduces ...
Catastrophic forgetting of previously learned knowledge while learning n...
We propose a new method for unsupervised continual knowledge consolidati...
In this work, we propose a novel end-to-end sinkhorn autoencoder with no...