Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Tanielian, Ugo"'
The recent advances in text and image synthesis show a great promise for the future of generative models in creative fields. However, a less explored area is the one of 3D model generation, with a lot of potential applications to game design, video p
Externí odkaz:
http://arxiv.org/abs/2312.08094
In digital advertising, the selection of the optimal item (recommendation) and its best creative presentation (creative optimization) have traditionally been considered separate disciplines. However, both contribute significantly to user satisfaction
Externí odkaz:
http://arxiv.org/abs/2309.11507
Many deep generative models are defined as a push-forward of a Gaussian measure by a continuous generator, such as Generative Adversarial Networks (GANs) or Variational Auto-Encoders (VAEs). This work explores the latent space of such deep generative
Externí odkaz:
http://arxiv.org/abs/2207.10541
Autor:
Diemert, Eustache, Fabre, Romain, Gilotte, Alexandre, Jia, Fei, Leparmentier, Basile, Mary, Jérémie, Qu, Zhonghua, Tanielian, Ugo, Yang, Hui
Designing data sharing mechanisms providing performance and strong privacy guarantees is a hot topic for the Online Advertising industry. Namely, a prominent proposal discussed under the Improving Web Advertising Business Group at W3C only allows sha
Externí odkaz:
http://arxiv.org/abs/2201.13123
The mathematical forces at work behind Generative Adversarial Networks raise challenging theoretical issues. Motivated by the important question of characterizing the geometrical properties of the generated distributions, we provide a thorough analys
Externí odkaz:
http://arxiv.org/abs/2201.02824
Advances in computer vision are pushing the limits of im-age manipulation, with generative models sampling detailed images on various tasks. However, a specialized model is often developed and trained for each specific task, even though many image ed
Externí odkaz:
http://arxiv.org/abs/2111.15264
Standard formulations of GANs, where a continuous function deforms a connected latent space, have been shown to be misspecified when fitting different classes of images. In particular, the generator will necessarily sample some low-quality images in
Externí odkaz:
http://arxiv.org/abs/2110.09803
Current recommendation approaches help online merchants predict, for each visiting user, which subset of their existing products is the most relevant. However, besides being interested in matching users with existing products, merchants are also inte
Externí odkaz:
http://arxiv.org/abs/2109.01093
Determinantal point processes (DPPs) have received significant attention as an elegant probabilistic model for discrete subset selection. Most prior work on DPP learning focuses on maximum likelihood estimation (MLE). While efficient and scalable, ML
Externí odkaz:
http://arxiv.org/abs/2011.09712
Recent advances in adversarial attacks and Wasserstein GANs have advocated for use of neural networks with restricted Lipschitz constants. Motivated by these observations, we study the recently introduced GroupSort neural networks, with constraints o
Externí odkaz:
http://arxiv.org/abs/2006.05254