papers

Publications (24)

cs.LG2025

Generating Graphs via Spectral Diffusion

Giorgia Minello, Alessandro Bicciato, Luca Rossi +2

In this paper, we present GGSD, a novel graph generative model based on 1) the spectral decomposition of the graph Laplacian matrix and 2) a diffusion process. Specifically, we pro…

cs.CG2019

Isospectralization, or how to hear shape, style, and correspondence

Luca Cosmo, Mikhail Panine, Arianna Rampini +3

The question whether one can recover the shape of a geometric object from its Laplacian spectrum ('hear the shape of the drum') is a classical problem in spectral geometry with a b…

cs.SD2024

Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models

Emilian Postolache, Giorgio Mariani, Luca Cosmo +2

Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating accompaniments, and performing source separati…

cs.CV2015

Partial Functional Correspondence

Emanuele RodolÃ, Luca Cosmo, Michael M. Bronstein +2

In this paper, we propose a method for computing partial functional correspondence between non-rigid shapes. We use perturbation analysis to show how removal of shape parts changes…

cs.LG2023

Latent Autoregressive Source Separation

Emilian Postolache, Giorgio Mariani, Michele Mancusi +3

Autoregressive models have achieved impressive results over a wide range of domains in terms of generation quality and downstream task performance. In the continuous domain, a key…

cs.LG2022

Unsupervised Source Separation via Bayesian Inference in the Latent Domain

Michele Mancusi, Emilian Postolache, Giorgio Mariani +4

State of the art audio source separation models rely on supervised data-driven approaches, which can be expensive in terms of labeling resources. On the other hand, approaches for…

cs.LG2022

Latent-Graph Learning for Disease Prediction

Luca Cosmo, Anees Kazi, Seyed-Ahmad Ahmadi +2

Recently, Graph Convolutional Networks (GCNs) have proven to be a powerful machine learning tool for Computer-Aided Diagnosis (CADx) and disease prediction. A key component in thes…

cs.CV2024

SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapes

Mohammad Zohaib, Luca Cosmo, Alessio Del Bue

Unsupervised 3D keypoints estimation from Point Cloud Data (PCD) is a complex task, even more challenging when an object shape is deforming. As keypoints should be semantically and…

cs.LG2023

Spectral Maps for Learning on Subgraphs

Marco Pegoraro, Riccardo Marin, Arianna Rampini +3

In graph learning, maps between graphs and their subgraphs frequently arise. For instance, when coarsening or rewiring operations are present along the pipeline, one needs to keep…

cs.SD2025

Naturalistic Music Decoding from EEG Data via Latent Diffusion Models

Emilian Postolache, Natalia Polouliakh, Hiroaki Kitano +4

In this article, we explore the potential of using latent diffusion models, a family of powerful generative models, for the task of reconstructing naturalistic music from electroen…

cs.SD2025

FolAI: Synchronized Foley Sound Generation with Semantic and Temporal Alignment

Riccardo Fosco Gramaccioni, Christian Marinoni, Emilian Postolache +4

Traditional sound design workflows rely on manual alignment of audio events to visual cues, as in Foley sound design, where everyday actions like footsteps or object interactions a…

cs.LG2022

Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications

Kamilia Mullakaeva, Luca Cosmo, Anees Kazi +3

Graphs are a powerful tool for representing and analyzing unstructured, non-Euclidean data ubiquitous in the healthcare domain. Two prominent examples are molecule property predict…

cs.LG2021

Learning disentangled representations via product manifold projection

Marco Fumero, Luca Cosmo, Simone Melzi +1

We propose a novel approach to disentangle the generative factors of variation underlying a given set of observations. Our method builds upon the idea that the (unknown) low-dimens…

cs.LG2024

GNN-LoFI: a Novel Graph Neural Network through Localized Feature-based Histogram Intersection

Alessandro Bicciato, Luca Cosmo, Giorgia Minello +2

Graph neural networks are increasingly becoming the framework of choice for graph-based machine learning. In this paper, we propose a new graph neural network architecture that sub…

cs.SD2025

COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations

Ruben Ciranni, Giorgio Mariani, Michele Mancusi +4

We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive learning method for musical audio representations that captures the harmonic and rhythmic coher…

cs.SD2025

STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioning

Giorgio Strano, Chiara Ballanti, Donato Crisostomi +3

Recent advances in generative models have made it possible to create high-quality, coherent music, with some systems delivering production-level output. Yet, most existing models f…

cs.LG2022

Differentiable Graph Module (DGM) for Graph Convolutional Networks

Anees Kazi, Luca Cosmo, Seyed-Ahmad Ahmadi +2

Graph deep learning has recently emerged as a powerful ML concept allowing to generalize successful deep neural architectures to non-Euclidean structured data. Such methods have sh…

cs.CV2022

Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transport

Mahdi Saleh, Shun-Cheng Wu, Luca Cosmo +3

Shape matching has been a long-studied problem for the computer graphics and vision community. The objective is to predict a dense correspondence between meshes that have a certain…

cs.CV2021

Shape registration in the time of transformers

Giovanni Trappolini, Luca Cosmo, Luca Moschella +3

In this paper, we propose a transformer-based procedure for the efficient registration of non-rigid 3D point clouds. The proposed approach is data-driven and adopts for the first t…

cs.LG2025

Graph Kernel Neural Networks

Luca Cosmo, Giorgia Minello, Alessandro Bicciato +4

The convolution operator at the core of many modern neural architectures can effectively be seen as performing a dot product between an input matrix and a filter. While this is rea…

cs.LG2021

Universal Spectral Adversarial Attacks for Deformable Shapes

Arianna Rampini, Franco Pestarini, Luca Cosmo +2

Machine learning models are known to be vulnerable to adversarial attacks, namely perturbations of the data that lead to wrong predictions despite being imperceptible. However, the…

cs.SD2024

Multi-Source Diffusion Models for Simultaneous Music Generation and Separation

Giorgio Mariani, Irene Tallini, Emilian Postolache +3

In this work, we define a diffusion-based generative model capable of both music synthesis and source separation by learning the score of the joint probability density of sources s…

cs.LG2020

LIMP: Learning Latent Shape Representations with Metric Preservation Priors

Luca Cosmo, Antonio Norelli, Oshri Halimi +2

In this paper, we advocate the adoption of metric preservation as a powerful prior for learning latent representations of deformable 3D shapes. Key to our construction is the intro…

cs.GR2022

Learning Spectral Unions of Partial Deformable 3D Shapes

Luca Moschella, Simone Melzi, Luca Cosmo +5

Spectral geometric methods have brought revolutionary changes to the field of geometry processing. Of particular interest is the study of the Laplacian spectrum as a compact, isome…