Luca Moschella

Luca Moschella

Research Intern at NNAISENSE - Ph.D. student in Computer Science

Gladia research group, Sapienza University of Rome

About me

I am a Ph.D. student at the Sapienza University of Rome in the Gladia research group led by Professor Emanuele Rodolà.

I’m excited by many Computer Science fields and, in particular, by Artificial Intelligence. I am passionate about frontier research, crossing the boundaries of AI and other applied disciplines. Currently, my research focuses on geometric deep learning, representation learning, and reasoning.

I’m a strong believer of reproducibility in science, and make an effort to write clean, well organized and documented code. I strive to keep up to pace with the latest technological advancements and I like to think of myself as an early adopter.

I am a long time Linux user and open source enthusiast. When I can, I try to give back to the open-source community.

Interests
  • Artificial Intelligence
  • Geometric Deep Learning
  • Representation Learning
  • Reasoning
Education

Experience

 
 
 
 
 
NNAISENSE
Research Intern
NNAISENSE
Jul 2021 – Present Lugano, Switzerland
  • Improving the AI software infrastructure with a main focus on hyperparameter tuning and its application to client projects.
 
 
 
 
 
Deep Learning & Applied AI @Sapienza
Teaching Assistant
Deep Learning & Applied AI @Sapienza
Jan 2020 – Present Rome, Italy

  • Designed the course lab sessions to explain and show to the students fundamentals and cutting-edge techniques in many areas of deep learning.

  • Latest course material with interactive notebooks available here.

Projects

Open Source

NN Template
Popular template to bootstrap the scaffolding for your PyTorch project with PyTorch Lightning, Hydra, DVC, Weights and Biases, and Streamlit.
nn-template
NN Template
Ultrawide Windows

Expose useful shortcuts to move windows, an easy-to-use middle ground between the default behavior and the tiling approach.

Currently, the 5th most popular Kwin script.

Install
Ultrawide Windows

Accomplish­ments

Coursera
Reinforcement Learning Specialization
Coursera Mar 2021
The Reinforcement Learning Specialization consists of 4 courses exploring the power of adaptive learning systems and artificial intelligence (AI).
See certificate
Student Volunteer
Symposium on Geometry Processing Jul 2019 – Jul 2019
Selected volunteer student to help in the organization of the conference.

Attended

ICLR
May 3, 2021 — May 17, 2021 Virtual
Memory Networks at AIDA
Apr 30, 2021 Virtual
Mediterranean Machine Learning summer school
Jan 11, 2021 — Jan 16, 2021 Virtual — Admission upon selection
NeurIPS
Dec 6, 2020 — Dec 12, 2020 Virtual
AAAI Conceptual Abastraction and Analogy in Natural and Artificial Intelligence
Nov 13, 2020 — Nov 14, 2020 Virtual — Admission upon selection
ACDL: 3rd Advanced Course on Data Science & Machine Learning
Jul 13, 2020 — Jul 17, 2020 Certosa di Pontignano, Siena — Admission upon selection
See all

Posters

Spectral Unions of Partial Deformable 3D Shapes
Mediterranean Machine Learning summer school
Jan 14, 2021 Virtual
Luca Moschella, Filippo Maggioli, Or Litany, Simone Melzi, Maks Ovsjanikov, Leonidas Guibas, Emanuele Rodolà
Video
Spectral Unions of Partial Deformable 3D Shapes
Learning Set Operations for Deformable Shapes
ELLIS Workshop on Geometric and Relational Deep Learning
Apr 24, 2020 Amsterdam (virtual)
Luca Moschella, Filippo Maggioli, Or Litany, Simone Melzi, Maks Ovsjanikov, Leonidas Guibas, Emanuele Rodolà
Video
Learning Set Operations for Deformable Shapes

Publications

Shape registration in the time of transformers
In this paper, we propose a transformer-based procedure for the efficient registration of non-rigid 3D point clouds. The proposed …
Giovanni Trappolini, Luca Cosmo, Luca Moschella, Riccardo Marin, Simone Melzi, Emanuele Rodolà
PDF Cite
Shape registration in the time of transformers
Spectral Unions of Partial Deformable 3D Shapes
Spectral geometric methods have brought revolutionary changes to the field of geometry processing – however, when the data to be …
Luca Moschella, Simone Melzi, Luca Cosmo, Filippo Maggioli, Or Litany, Maks Ovsjanikov, Leonidas Guibas, Emanuele Rodolà
PDF Cite
Spectral Unions of Partial Deformable 3D Shapes
Performance Variations of the Bayesian Model of Peer-Assessment Implemented in OpenAnswer Response to Modifications of the Number of Peers Assessed and of the Quality of the Class
The paper presents a study of the performance variations of the Bayesian model of peer-assessment implemented in OpenAnswer, in terms …
Maria De Marsico, Luca Moschella, Andrea Sterbini, Marco Temperini
PDF Cite DOI
Performance Variations of the Bayesian Model of Peer-Assessment Implemented in OpenAnswer Response to Modifications of the Number of Peers Assessed and of the Quality of the Class
Effects of Network Topology on the OpenAnswer’s Bayesian Model of Peer Assessment
The paper investigates if and how the topology of the peer-assessment network can affect the performance of the Bayesian model adopted …
Maria De Marsico, Luca Moschella, Andrea Sterbini, Marco Temperini
PDF Cite DOI
Effects of Network Topology on the OpenAnswer’s Bayesian Model of Peer Assessment

Contact