Publications

We analyze how large language models (LLMs) represent out-of-context words, investigating their reliance on the given context to …

The use of relative representations for latent embeddings has shown potential in enabling latent space communication and zero-shot …

In graph learning, maps between graphs and their subgraphs frequently arise. For instance, when coarsening or rewiring operations are …

In this work, we define a diffusion-based generative model capable of both music synthesis and source separation by learning the score …

Autoregressive models have achieved impressive results over a wide range of domains in terms of generation quality and downstream task …

Cross-lingual phenomena are quite common in informal contexts like social media, where users are likely to mix their native language …

Few-shot graph classification is a novel yet promising emerging research field that still lacks the soundness of well-established …

Gaussian Boson Sampling (GBS) is a non-universal model for quantum computing inspired by the original formulation of the Boson Sampling …

Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space into latent representations. …

Deep learning approaches have recently raised the bar in many fields, from Natural Language Processing to Computer Vision, by …

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their …

Generating shapes using natural language can enable new ways of imagining and creating the things around us. While significant recent …

Spectral geometric methods have brought revolutionary changes to the field of geometry processing. Of particular interest is the study …

Graph Neural Networks (GNNs) have proven to be successful in several predictive modeling tasks for graph-structured data. Amongst those …

Shape matching is a central problem in geometry processing applications, ranging from texture transfer to statistical shape analysis. …

AlphaGo Zero for Othello. With two ideas to speed up the learning, and tested in a live match against a former world champion.

An algorithm that exploits features of the bicomplex field to compute 4-dimensional Newton fractals for procedural texturing applications. The generated fractals are computed in a pixel shader only on the target surface to achieve real-time performance.

We introduce a novel approach to disentangle style from content in the 3D domain and perform unsupervised neural style transfer. Our …

A generalization of the algorithm for simulating the evolution of slime mold organisms to work on triangular meshes. The algorithm is implemented on GPU to achieve real-time performance.

Many natural shapes have most of their characterizing features concentrated over a few regions in space. For example, humans and …

A neural implicit representation which couples solving for a well-defined surface and real-time rendering capabilities.

The 3D cloth segmentation task is particularly challenging due to the extreme variation of shapes, even among the same category of …

The marine ecosystem is changing at an alarming rate, exhibiting biodiversity loss and the migration of tropical species to temperate …

When a ML system becomes an artificial scientist: mastering the game of Zendo with Transformers.

Olivaw is an AI Othello playing agent which autonomously learns how to improve its gameplay by playing against itself. Some top-notch …

Abstract In this paper, we introduce complex functional maps, which extend the functional map framework to conformal maps between …

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their …

CLIP proved that aligning visual and language spaces is key to solving many vision tasks without explicit training, but required to …

The Associazione Medici Diabetologi (AMD) collects and manages one of the largest worldwide available collections of diabetic patient …

Universal sound separation consists of separating mixes with arbitrary sounds of different types, and permutation invariant training …

The last two decades have seen an incessant growth in the use of Unmanned Aerial Vehicles (UAVs) equipped with HD cameras for …

The Average Mixing Kernel Signature is a novel spectral signature for points on non-rigid three-dimensional shapes. It is based on a …

We introduce a novel learning-based method to recover shapes from their Laplacian spectra, based on establishing and exploring …

We propose a novel approach to disentangle the generative factors of variation underlying a given set of observations. Our method …

In this paper, we propose a transformer-based procedure for the efficient registration of non-rigid 3D point clouds. The proposed …

In this paper, we provide a theoretical foundation for pointwise map recovery from functional maps and highlight its relation to a …

Abstract In this paper, we propose a new construction for the Mexican hat wavelets on shapes with applications to partial shape …

State of the art audio source separation models rely on supervised data-driven approaches, which can be expensive in terms of labeling …

In the 3D digital world, deformations and animations of shapes are fundamental topics for several applications. The entertainment …

The usual Laplacian eigenbasis is extended to consider also polynomials of the eigenfunctions. The new extended basis has in increased descriptive power in signal reconstruction and transfer tasks, coming at a very reduced cost.

Patient-specific Biomechanical Models (PBMs) can enhance computer assisted surgical procedures with critical information. Although …

An efficient algorithm for computing the multiplication of a matrix by its transpose, exploiting Strassen-like recursions. The algorithm is designed to be parallelized with multiple paradigms, from multi-threading to distributed computing.

Abstract We propose a novel discrete solver for optimizing functional map-based energies, including descriptor preservation and …

We introduce a novel computational framework for digital geometry processing, based upon the derivation of a nonlinear operator …

In this paper we propose an approach for computing multiple high-quality near-isometric dense correspondences between a pair of 3D …

We introduce the first learning-based method for recovering shapes from Laplacian spectra. Given an auto-encoder, our model takes the …

We introduce a new method for non-rigid registration of 3D human shapes. Our proposed pipeline builds upon a given parametric model of …

We introduce the Average Mixing Kernel Signature (AMKS), a novel signature for points on non-rigid three-dimensional shapes based on …

In this paper, we advocate the adoption of metric preservation as a powerful prior for learning latent representations of deformable 3D …

3D acquisition pipeline delivers 3D digital models accurately representing real-world objects, improving the geometric accuracy and …

Adversarial attacks have demonstrated remarkable efficacy in altering the output of a learning model by applying a minimal perturbation …

The intrinsic random nature of quantum physics offers novel tools for the generation of random numbers, a central challenge for a …

Predicting interactions between proteins and other biomolecules solely based on structure remains a challenge in biology. A high-level …

Abstract In this paper we develop an in-depth theoretical investigation of the discrete Hamiltonian eigenbasis, which remains quite …

We present a simple and efficient method for refining maps or correspondences by iterative upsampling in the spectral domain that can …

We propose a new approach for 3D shape matching of deformable human shapes. Our approach is based on the joint adoption of three …

The question whether one can recover the shape of a geometric object from its Laplacian spectrum (‘hear the shape of the …

Functional representation is a well-established approach to represent dense correspondences between deformable shapes. The approach …

We introduce a new framework for learning dense correspondence between deformable 3D shapes. Existing learning based approaches model …

The paper investigates if and how the topology of the peer-assessment network can affect the performance of the Bayesian model adopted …

The paper presents a study of the performance variations of the Bayesian model of peer-assessment implemented in OpenAnswer, in terms …

Recent efforts in the area of joint object matching approach the problem by taking as input a set of pairwise maps, which are then …

Artificial markers are successfully adopted to solve several vision tasks, ranging from tracking to calibration. While most designs …

Feature matching is a key step in most Computer Vision tasks involving several views of the same subject. In fact, it plays a crucial …

Matching deformable 3D shapes under partiality transformations is a challenging problem that has received limited focus in the computer …

We consider the problem of deformable object detection and dense correspondence in cluttered 3D scenes. Key ingredient to our method is …

Due to their recent availability as off-the-shelf commercial devices, light-field cameras has gathered increasing attention from both …