Browsing Faculté des arts et des sciences by Subject "normalizing flows"
Now showing items 1-2 of 2
-
AI alignment and generalization in deep learning
(2023-09-13)This thesis covers a number of works in deep learning aimed at understanding and improving generalization abilities of deep neural networks (DNNs). DNNs achieve unrivaled performance in a growing range of tasks and domains, yet their behavior during ... -
Conditional generative modeling for images, 3D animations, and video
(2023-11-01)Generative modeling for computer vision has shown immense progress in the last few years, revolutionizing the way we perceive, understand, and manipulate visual data. This rapidly evolving field has witnessed advancements in image generation, 3D ...