Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Fernández, Daniel Gallo"'
Autor:
Fernández, Daniel Gallo, van der Klis, Robert, Matişan, Rǎzvan-Andrei, Partyka, Janusz, Gavves, Efstratios, Papa, Samuele, Lippe, Phillip
While vision transformers are able to solve a wide variety of computer vision tasks, no pre-training method has yet demonstrated the same scaling laws as observed in language models. Autoregressive models show promising results, but are commonly trai
Externí odkaz:
http://arxiv.org/abs/2410.10012
Autor:
Fernández, Daniel Gallo, Matişan, Rǎzvan-Andrei, Muñoz, Alejandro Monroy, Vasilcoiu, Ana-Maria, Partyka, Janusz, Veljković, Tin Hadži, Jazbec, Metod
Diffusion models have achieved unprecedented performance in image generation, yet they suffer from slow inference due to their iterative sampling process. To address this, early-exiting has recently been proposed, where the depth of the denoising net
Externí odkaz:
http://arxiv.org/abs/2410.09633
Text-to-image generative models often present issues regarding fairness with respect to certain sensitive attributes, such as gender or skin tone. This study aims to reproduce the results presented in "ITI-GEN: Inclusive Text-to-Image Generation" by
Externí odkaz:
http://arxiv.org/abs/2407.19996