Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Franzese, Giulio"'
Diffusion models for Text-to-Image (T2I) conditional generation have seen tremendous success recently. Despite their success, accurately capturing user intentions with these models still requires a laborious trial and error process. This challenge is
Externí odkaz:
http://arxiv.org/abs/2405.20759
Autor:
Christophorou, Christophoros, Ioannou, Iacovos, Vassiliou, Vasos, Christofi, Loizos, Vardakas, John S, Seder, Erin E, Chiasserini, Carla Fabiana, Iordache, Marius, Issaid, Chaouki Ben, Markopoulos, Ioannis, Franzese, Giulio, Järvet, Tanel, Verikoukis, Christos
In the upcoming 6G era, mobile networks must deal with more challenging applications (e.g., holographic telepresence and immersive communication) and meet far more stringent application requirements stemming along the edge-cloud continuum. These new
Externí odkaz:
http://arxiv.org/abs/2403.05277
The analysis of scientific data and complex multivariate systems requires information quantities that capture relationships among multiple random variables. Recently, new information-theoretic measures have been developed to overcome the shortcomings
Externí odkaz:
http://arxiv.org/abs/2402.05667
In this work we present a new method for the estimation of Mutual Information (MI) between random variables. Our approach is based on an original interpretation of the Girsanov theorem, which allows us to use score-based diffusion models to estimate
Externí odkaz:
http://arxiv.org/abs/2310.09031
Multi-modal data-sets are ubiquitous in modern applications, and multi-modal Variational Autoencoders are a popular family of models that aim to learn a joint representation of the different modalities. However, existing approaches suffer from a cohe
Externí odkaz:
http://arxiv.org/abs/2306.04445
Generative Models (GMs) have attracted considerable attention due to their tremendous success in various domains, such as computer vision where they are capable to generate impressive realistic-looking images. Likelihood-based GMs are attractive due
Externí odkaz:
http://arxiv.org/abs/2305.18900
Autor:
Franzese, Giulio, Corallo, Giulio, Rossi, Simone, Heinonen, Markus, Filippone, Maurizio, Michiardi, Pietro
We introduce Functional Diffusion Processes (FDPs), which generalize score-based diffusion models to infinite-dimensional function spaces. FDPs require a new mathematical framework to describe the forward and backward dynamics, and several extensions
Externí odkaz:
http://arxiv.org/abs/2303.00800
Autor:
Franzese, Giulio, Rossi, Simone, Yang, Lixuan, Finamore, Alessandro, Rossi, Dario, Filippone, Maurizio, Michiardi, Pietro
Score-based diffusion models are a class of generative models whose dynamics is described by stochastic differential equations that map noise into data. While recent works have started to lay down a theoretical foundation for these models, an analyti
Externí odkaz:
http://arxiv.org/abs/2206.05173
Autor:
Bounoua, Mustapha1,2 (AUTHOR) giulio.franzese@eurecom.fr, Franzese, Giulio2 (AUTHOR) pietro.michiardi@eurecom.fr, Michiardi, Pietro2 (AUTHOR)
Publikováno v:
Entropy. Apr2024, Vol. 26 Issue 4, p320. 38p.
We revisit the theoretical properties of Hamiltonian stochastic differential equations (SDES) for Bayesian posterior sampling, and we study the two types of errors that arise from numerical SDE simulation: the discretization error and the error due t
Externí odkaz:
http://arxiv.org/abs/2106.16200