Publications

From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication
It has been observed that representations learned by distinct neural networks conceal structural similarities when the models are …
Irene Cannistraci, Luca Moschella, Marco Fumero, Valentino Maiorca, Emanuele Rodolà
PDF Cite arXiv
From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication
Latent Space Translation via Semantic Alignment
Different neural models often exhibit similar latent spaces when exposed to semantically similar data; however, this inherent …
Valentino Maiorca, Luca Moschella, Antonio Norelli, Marco Fumero, Francesco Locatello, Emanuele Rodolà
Cite NeurIPS 2023
Latent Space Translation via Semantic Alignment
ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training
CLIP proved that aligning visual and language spaces is key to solving many vision tasks without explicit training, but required to …
Antonio Norelli, Marco Fumero, Valentino Maiorca, Luca Moschella, Emanuele Rodolà, Francesco Locatello
Cite NeurIPS 2023
ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training
Zero-shot stitching in Reinforcement Learning using Relative Representations
In this paper we investigate the use of a recent method called “relative represen- tations” to enable zero-shot model …
Antonio Ricciardi, Valentino Maiorca, Luca Moschella, Emanuele Rodolà
PDF Cite EWRL16
Zero-shot stitching in Reinforcement Learning using Relative Representations
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their …
442 authors including, Andrea Santilli, Antonio Norelli, Emanuele Rodolà, Giambattista Parascandolo, Giorgio Mariani, Luca Moschella, Simone Melzi
PDF Cite TMLR
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Bootstrapping Parallel Anchors for Relative Representations
The use of relative representations for latent embeddings has shown potential in enabling latent space communication and zero-shot …
Irene Cannistraci, Luca Moschella, Valentino Maiorca, Marco Fumero, Antonio Norelli, Emanuele Rodolà
PDF Cite arXiv
Bootstrapping Parallel Anchors for Relative Representations
Relative representations enable zero-shot latent space communication
Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space into latent representations. …
Luca Moschella, Valentino Maiorca, Marco Fumero, Antonio Norelli, Francesco Locatello, Emanuele Rodolà
PDF Cite ICLR 2023 notable top 5%
Relative representations enable zero-shot latent space communication
CaSpeR: Latent Spectral Regularization for Continual Learning
While biological intelligence grows organically as new knowledge is gathered throughout life, Artificial Neural Networks forget …
Emanuele Frascaroli, Riccardo Benaglia, Matteo Boschini, Luca Moschella, Cosimo Fiorini, Emanuele Rodolà, Simone Calderara
PDF Cite arXiv
CaSpeR: Latent Spectral Regularization for Continual Learning
Metric Based Few-Shot Graph Classification
Few-shot graph classification is a novel yet promising emerging research field that still lacks the soundness of well-established …
Donato Crisostomi, Simone Antonelli, Valentino Maiorca, Luca Moschella, Riccardo Marin, Emanuele Rodolà
PDF Cite LoG 2022
Metric Based Few-Shot Graph Classification
Learning Spectral Unions of Partial Deformable 3D Shapes
Spectral geometric methods have brought revolutionary changes to the field of geometry processing. Of particular interest is the study …
Luca Moschella, Simone Melzi, Luca Cosmo, Filippo Maggioli, Or Litany, Maks Ovsjanikov, Leonidas Guibas, Emanuele Rodolà
PDF Cite Computer Graphics Forum
Learning Spectral Unions of Partial Deformable 3D Shapes
Explanatory Learning: Beyond Empiricism in Neural Networks
We introduce Explanatory Learning (EL), a framework to let machines use existing knowledge buried in symbolic sequences – e.g. …
Antonio Norelli, Giorgio Mariani, Luca Moschella, Andrea Santilli, Giambattista Parascandolo, Simone Melzi, Emanuele Rodolà
PDF Cite arXiv
Explanatory Learning: Beyond Empiricism in Neural Networks
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 NeurIPS 2021
Shape registration in the time of transformers
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 EC-TEL 2017
Effects of Network Topology on the OpenAnswer’s Bayesian Model of Peer Assessment
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 ITHET 2017
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