83 citations · 343 across the 46 of their papers we have counts for
3 papers · 1 filter
One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models
Ba-Hien Tran, Giulio Franzese, Pietro Michiardi +1
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 impress…
Continuous-Time Functional Diffusion Processes
Giulio Franzese, Giulio Corallo, Simone Rossi +3
We introduce Functional Diffusion Processes (FDPs), which generalize score-based diffusion models to infinite-dimensional function spaces. FDPs require a new mathematical framework…
"It's a Match!" -- A Benchmark of Task Affinity Scores for Joint Learning
Raphael Azorin, Massimo Gallo, Alessandro Finamore +2
While the promises of Multi-Task Learning (MTL) are attractive, characterizing the conditions of its success is still an open problem in Deep Learning. Some tasks may benefit from…