3 papers
cs.CV2025
Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence
Alessandro Riva, Alessandro Raganato, Simone Melzi
Current data-driven methodologies for point cloud matching demand extensive training time and computational resources, presenting significant challenges for model deployment and ap…
cs.LG2025
Disentangled Latent Spaces Facilitate Data-Driven Auxiliary Learning
Geri Skenderi, Luigi Capogrosso, Andrea Toaiari +3
Auxiliary tasks facilitate learning in situations where data is scarce or the principal task of interest is extremely complex. This idea is primarily inspired by the improved gener…
cs.CV2025
Blending Concepts with Text-to-Image Diffusion Models
Lorenzo Olearo, Giorgio Longari, Alessandro Raganato +2
Diffusion models have dramatically advanced text-to-image generation in recent years, translating abstract concepts into high-fidelity images with remarkable ease. In this work, we…