Stefano Fiorini — accepted AI-conference papers

2026

Directional Sheaf Hypergraph Networks: Unifying Learning on Directed and Undirected Hypergraphs

Emanuele Mule, Stefano Fiorini, Antonio Purificato, Federico Siciliano, Stefano Coniglio, Fabrizio Silvestri

ICLR 2026poster

Hypergraphs provide a natural way to represent higher-order interactions among multiple entities. While undirected hypergraphs have been extensively studied, the case of directed hypergraphs, which can model oriented group interactions, remains largely under-explored despite its relevance for many a…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Sheaves Reloaded: A Direction Awakening

Stefano Fiorini, Hakan Aktas, Iulia Duta, Pietro Morerio, Alessio Del Bue, Pietro Lio +1

ICLR 2026poster

Sheaf Neural Networks (SNNs) are a powerful algebraic-topology generalization of Graph Neural Networks (GNNs), and have been shown to significantly improve our ability to model complex relational data. While the GNN literature proved that incorporating directionality can substantially boost performa…

Cited by 0 Source ↗code ↗Scholar ↗

2025

ReassembleNet: Learnable Keypoints and Diffusion for 2D Fresco Reconstruction

Adeela Islam, Stefano Fiorini, Stuart James, Pietro Morerio, Alessio Del Bue

ICCV 2025poster

The task of reassembly is a significant challenge across multiple domains, including archaeology, genomics, and molecular docking, requiring the precise placement and orientation of elements to reconstruct an original structure. In this work, we address key limitations in state-of-the-art Deep Learn…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly

Gianluca Scarpellini, Stefano Fiorini, Francesco Giuliari, Pietro Moreiro, Alessio Del Bue

CVPR 2024poster

Reassembly tasks play a fundamental role in many fields and multiple approaches exist to solve specific reassembly problems. In this context we posit that a general unified model can effectively address them all irrespective of the input data type (image 3D etc.). We introduce DiffAssemble a Graph N…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗

2024

Graph Learning in 4D: A Quaternion-Valued Laplacian to Enhance Spectral GCNs

Stefano Fiorini, Stefano Coniglio, Michele Ciavotta, Enza Messina

AAAI 2024technical

We introduce QuaterGCN, a spectral Graph Convolutional Network (GCN) with quaternion-valued weights at whose core lies the Quaternionic Laplacian, a quaternion-valued Laplacian matrix by whose proposal we generalize two widely-used Laplacian matrices: the classical Laplacian (defined for undirected…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2024

Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving

Theodore Tsesmelis, Luca Palmieri, Marina Khoroshiltseva, Adeela Islam, Gur Elkin, Ofir Itzhak Shahar +17

NeurIPS 2024poster

This paper proposes the RePAIR dataset that represents a challenging benchmark to test modern computational and data driven methods for puzzle-solving and reassembly tasks. Our dataset has unique properties that are uncommon to current benchmarks for 2D and 3D puzzle solving. The fragments and fract…

Cited by 3 Source ↗PDF ↗Scholar ↗

2023

SigMaNet: One Laplacian to Rule Them All

Stefano Fiorini, Stefano Coniglio, Michele Ciavotta, Enza Messina

AAAI 2023technical

This paper introduces SigMaNet, a generalized Graph Convolutional Network (GCN) capable of handling both undirected and directed graphs with weights not restricted in sign nor magnitude. The cornerstone of SigMaNet is the Sign-Magnetic Laplacian (LSM), a new Laplacian matrix that we introduce ex nov…

Cited by 30 Source ↗PDF ↗code ↗Scholar ↗