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

From Charts to Atlas: Merging Latent Spaces into One

Models trained on semantically related datasets and tasks exhibit comparable inter-sample relations within their latent spaces. We …

Donato Crisostomi, Irene Cannistraci, Luca Moschella, Pietro Barbiero, Marco Ciccone, Pietro Lio, Emanuele Rodolà

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

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

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

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

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

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

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

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

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

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

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

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

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

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