416 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Fondazione Bruno KesslerIT16 papers
- Birkbeck, University of LondonGB13 papers
- Norwegian University of Science and TechnologyNO12 papers
- University of TrentoIT12 papers
- Fundación Ciencias Exactas y NaturalesAR10 papers
- Universidad de Buenos AiresAR10 papers
- Consejo Nacional de Investigaciones Científicas y TécnicasAR9 papers
- TU WienAT9 papers
- Sapienza University of RomeIT8 papers
- University of UdineIT8 papers
- Centre National de la Recherche ScientifiqueFR7 papers
- University of JyväskyläFI7 papers
22 papers · 1 filter
On the Koopman-Based Generalization Bounds for Multi-Task Deep Learning
Mahdi Mohammadigohari, Giuseppe Di Fatta, Giuseppe Nicosia +1
The paper establishes generalization bounds for multitask deep neural networks using operator-theoretic techniques. The authors propose a tighter bound than those derived from conv…
Operator-Based Generalization Bound for Deep Learning: Insights on Multi-Task Learning
Mahdi Mohammadigohari, Giuseppe Di Fatta, Giuseppe Nicosia +1
This paper presents novel generalization bounds for vector-valued neural networks and deep kernel methods, focusing on multi-task learning through an operator-theoretic framework.…
On the cybersecurity of LoRaWAN-based system: a Smart-Lighting case study
Florian Hofer, Barbara Russo
Cyber-physical systems and the Internet of Things (IoT) are key technologies in the Industry 4.0 vision. They incorporate sensors and actuators to interact with the physical enviro…
Network Inequality through Preferential Attachment, Triadic Closure, and Homophily
Jan Bachmann, Samuel Martin-Gutierrez, Lisette Espín-Noboa +2
Inequalities in social networks arise from linking mechanisms, such as preferential attachment (connecting to popular nodes), homophily (connecting to similar others), and triadic…
Cross-Domain Evaluation of Transformer-Based Vulnerability Detection on Open & Industry Data
Moritz Mock, Thomas Forrer, Barbara Russo
Deep learning solutions for vulnerability detection proposed in academic research are not always accessible to developers, and their applicability in industrial settings is rarely…
Generalized local charge conservation in many-body quantum mechanics
F. Minotti, G. Modanese
In the framework of the quantum theory of many-particle systems, we study the compatibility of approximated Non-Equilibrium Green Functions (NEGFs) and of approximated solutions of…
ProfVLM: A lightweight video-language model for multi-view proficiency estimation
Edoardo Bianchi, Jacopo Staiano, Antonio Liotta
Most existing approaches formulate action quality assessment and skill proficiency estimation as discriminative prediction tasks, typically producing discrete labels or scores with…
Do we need an alternative to local gauge coupling to electromagnetic fields?
F. Minotti, G. Modanese
The local gauge coupling through the recipe , that works so well with Dirac spinors in QED and in the gauge theories of the Standard Model, has…
Architectural practice process and artificial intelligence -- an evolving practice
Mustapha El Moussaoui
In an era of exponential technological advancement, artificial intelligence (AI) has emerged as a transformative force in architecture, reshaping traditional design and constructio…
Future Illiteracies -- Architectural Epistemology and Artificial Intelligence
Mustapha El Moussaoui
In the age of artificial intelligence, architectural practice faces a paradox of immense potential and creeping standardization. As humans are increasingly relying on AI-generated…
Point of Interest Recommendation: Pitfalls and Viable Solutions
Alejandro Bellogín, Linus W. Dietz, Francesco Ricci +1
Point of interest (POI) recommendation can play a pivotal role in enriching tourists' experiences by suggesting context-dependent and preference-matching locations and activities,…
Teaching Complex Systems based on Microservices
Renato Cordeiro Ferreira, Thatiane de Oliveira Rosa, Alfredo Goldman +1
Developing complex systems using microservices is a current challenge. In this paper, we present our experience with teaching this subject to more than 80 students at the Universit…
On exterior-algebraic quaternions with application to Maxwell equations
Ivano Colombaro
Within the framework of exterior algebra, the concept of time-like quaternions has been previously established. This paper advances beyond the existing structure by elucidating the…
Approximation of viscous transport and conservative equations with one sided Lipschitz velocity fields
Fabio Camilli, Adriano Festa, Luciano Marzufero
The aim of this work is to investigate semi-Lagrangian approximation schemes on unstructured grids for viscous transport and conservative equations with measurable coefficients tha…
From Sound Workflow Nets to LTLf Declarative Specifications by Casting Three Spells
Luca Barbaro, Giovanni Varricchione, Marco Montali +1
In process management, effective behavior modeling is essential for understanding execution dynamics and identifying potential issues. Two complementary paradigms have emerged in t…
A Lower Bound on Conservative Elementary Object Systems Coverability
Francesco Di Cosmo, Soumodev Mal, Tephilla Prince
Elementary Object Systems (EOS) are a form of Petri Net (PN) where tokens carry internal PN. This model has been recently proposed for analysis of robustness of Multi Agent Systems…
Generating Counterfactual Explanations Under Temporal Constraints
Andrei Buliga, Chiara Di Francescomarino, Chiara Ghidini +2
Counterfactual explanations are one of the prominent eXplainable Artificial Intelligence (XAI) techniques, and suggest changes to input data that could alter predictions, leading t…
Common Foundations for SHACL, ShEx, and PG-Schema
S. Ahmetaj, I. Boneva, J. Hidders +11
Graphs have emerged as an important foundation for a variety of applications, including capturing and reasoning over factual knowledge, semantic data integration, social networks,…
Modelling of the bonding process for a non-woven fabric: analysis and numerics
F. Bagagiolo, E. Bertolazzi, L. Marzufero +2
This paper presents research conducted at the University of Trento addressing an industrial challenge from Fater S.p.A. regarding the thermal bonding of non-woven fabrics for diape…
Excited states of coherent harmonic qubits with long-range photon coupling and dissipation
L. Gamberale, G. Modanese
It is known that ensembles of interacting oscillators or qubits can exhibit the phenomenon of quantum synchronization. In this work we consider a set of identical two-state sys…
Leveraging multi-task learning to improve the detection of SATD and vulnerability
Barbara Russo, Jorge Melegati, Moritz Mock
Multi-task learning is a paradigm that leverages information from related tasks to improve the performance of machine learning. Self-Admitted Technical Debt (SATD) are comments in…
Optimizing Deep Learning Models to Address Class Imbalance in Code Comment Classification
Moritz Mock, Thomas Borsani, Giuseppe Di Fatta +1
Developers rely on code comments to document their work, track issues, and understand the source code. As such, comments provide valuable insights into developers' understanding of…