Publications

Model merging has recently emerged as a cost-efficient paradigm for multi-task learning. Among current approaches, task arithmetic …

When examined through the lens of their residual streams, a puzzling property emerges in transformer networks: residual contributions …

Deep neural networks often learn similar internal representations, both across different models and within their own layers. While …

Neural models learn data representations that lie on low-dimensional manifolds, yet modeling the relation between these …

In this paper, we present a novel data-free method for merging neural networks in weight space. Differently from most existing works, …

Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various …

We introduce ReMatching, a novel shape correspondence solution based on the functional maps framework. Our method, by exploiting a new …

In this article, we explore the potential of using latent diffusion models, a family of powerful generative models, for the task of …

The emergence of similar representations between independently trained neural models has sparked significant interest in the …

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

It has been observed that representations learned by distinct neural networks conceal structural similarities when the models are …

The convolution operator at the core of many modern neural architectures can effectively be seen as performing a dot product between an …

In this work, we present the local patch mesh representation for neural signed distance fields. This technique allows to discretize …

We present GSEdit, a pipeline for text-guided 3D object editing based on Gaussian Splatting models. Our method enables the editing of …

We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive learning method for musical audio representations …

Sound design involves creatively selecting, recording, and editing sound effects for various media like cinema, video games, and …

Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating …

While biological intelligence grows organically as new knowledge is gathered throughout life, Artificial Neural Networks forget …

Quantile regression (QR) is a statistical tool for distribution-free estimation of conditional quantiles of a target variable given …

In recent years Large Language Models (LLMs) have increased the state of the art on several natural language processing tasks. However, …

Plants are among the most complex objects to be modeled in computer graphics. While a large body of work is concerned with structural …

In recent studies, diffusion models have shown promise as priors for solving audio inverse problems, including source separation. These …

Recovering the latent factors of variation of high dimensional data has so far focused on simple synthetic settings. Mostly building on …

Different neural models often exhibit similar latent spaces when exposed to semantically similar data; however, this inherent …

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

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

Antibody-antigen interactions play a crucial role in identifying and neutralizing harmful foreign molecules. In this paper, we …

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

In this study, we introduce SAVAGE, a novel framework for sparse vicious adversarial link prediction attacks in graph neural networks …

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

Visual Reinforcement Learning is a popular and powerful framework that takes full advantage of the Deep Learning breakthrough. However, …

Singing voice detection (SVD) is an essential task in many music information retrieval (MIR) applications. Deep learning methods have …

Vector quantile regression (VQR) estimates the conditional vector quantile function (CVQF), a fundamental quantity which fully …

Datasets used to train deep learning models in industrial settings often exhibit skewed distributions with some samples repeated a …

Getting a good understanding of the user intent is vital for e-commerce applications to surface the right product to a given customer …

This paper presents Fauno, the first and largest open-source Italian conversational Large Language Model (LLM). Our goal with Fauno is …

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

Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network …

The rise in loosely-structured data available through text, images, and other modalities has called for new ways of querying them. …

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 …

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

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 …

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language …

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

3D human pose estimation is fundamental to understanding human behavior. Recently, promising results have been achieved by graph …

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

PromptSource is a system for creating, sharing, and using natural language prompts. Prompts are functions that map an example from a …

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

Many innovative applications require establishing correspondences among 3D geometric objects. However, the countless possible …

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

Computer-aided diagnosis (CAD) is becoming a prominent approach to assist clinicians spanning across multiple fields. These automated …

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

In this work we present a novel approach for computing correspondences between non-rigid objects, by exploiting a reduced …

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 …

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 …

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

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 …

Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., …

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 …

Machine learning models are known to be vulnerable to adversarial attacks, namely perturbations of the data that lead to wrong …

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

Federated Learning (FL) deals with learning a central model (i.e. the server) in privacy-constrained scenarios, where data are stored …

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 …

Action recognition in video sequences is an interesting field for many computer vision applications, including behavior analysis, event …

According to Aristotle, the whole is greater than the sum of its parts. This statement was adopted to explain human perception by the …

Syntactic parsers have dominated natural language understanding for decades. Yet, their syntactic interpretations are losing centrality …

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 …

Predicting interactions between proteins and other biomolecules purely based on structure is an unsolved problem in biology. The …

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 …

We consider the problem of localizing relevant subsets of non-rigid geometric shapes given only a partial 3D query as the input. Such …

We introduce the first completely unsupervised correspondence learning approach for deformable 3D shapes. Key to our model is the …

We introduce GFrames, a novel local reference frame (LRF) construction for 3D meshes and point clouds. GFrames are based on the …

The registration of non-rigidly deforming shapes is a fundamental problem in the area of Graphics and Computational Geometry. One of …

Objects Matching is a ubiquitous problem in computer science with particular relevance for many applications; property transfer between …

We consider the tasks of representing, analyzing and manipulating maps between shapes. We model maps as densities over the product …

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

This paper describes the UNITOR system that participated to the Irony Detection in Italian Tweets task (IronITA) within the context of …

The use of Laplacian eigenfunctions is ubiquitous in a wide range of computer graphics and geometry processing applications. In …

In this paper, we present SyntNN as a way to include traditional syntactic models in multilayer neural networks used in the task of …

In this paper, we consider the problem of information transfer across shapes and propose an extension to the widely used functional map …

The concept of using functional maps for representing dense correspondences between deformable shapes has proven to be extremely …

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

We present a method to match three dimensional shapes under non-isometric deformations, topology changes and partiality. We formulate …

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 …

Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a …

Deep learning has achieved a remarkable performance breakthrough in several fields, most notably in speech recognition, natural …

We propose an efficient procedure for calculating partial dense intrinsic correspondence between deformable shapes performed entirely …

Partial similarity problems arise in numerous applications that involve real data acquisition by 3D sensors, inevitably leading to …

In this paper, we propose a method for computing partial functional correspondence between non-rigid shapes. We use perturbation …

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

Notions of similarity and correspondence between geometric shapes and images are central to many tasks in geometry processing, computer …

Establishing correspondence between shapes is a fundamental problem in geometry processing, arising in a wide variety of applications. …

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 …

We propose Anisotropic Windowed Fourier Transform (AWFT), a framework for localized space-frequency analysis of deformable 3D shapes. …

Classical formulations of the shape matching problem involve the definition of a matching cost that directly depends on the action of …

Shape correspondence is a fundamental problem in computer graphics and vision, with applications in various problems including …

We propose the first algorithm for non-rigid 2D-to-3D shape matching, where the input is a 2D shape represented as a planar curve and a …

Spectral methods have recently gained popularity in many domains of computer graphics and geometry processing, especially shape …

A particularly challenging setting of the shape matching problem arises when the shapes being matched have topological artifacts due to …

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 …

The goal of these course notes is to describe the main mathematical ideas behind geometric deep learning and to provide implementation …

Notions of similarity and correspondence between geometric shapes and images are central to many tasks in geometry processing, computer …

Shape from shading with multiple light sources is an active research area and a diverse range of approaches have been proposed in the …

Since their introduction in the shape analysis community, functional maps have met with considerable success due to their ability to …

Surface registration is often performed as a two step process. A feature matching scheme is first adopted to find a coarse initial …

The surface of natural or human-made objects usually comprises a collection of distinct regions characterized by different features. …

Tridimensional shape recovery based on Photometric Stereo (PS) recently received a strong improvement due to new mathematical models …

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

In this paper, we propose an optimization method for estimating the parameters that typically appear in graph-theoretical formulations …

We propose novel point descriptors for 3D shapes with the potential to match two shapes of the same object under natural deformations. …

This paper introduces an anisotropic Laplace-Beltrami operator for shape analysis. While keeping useful properties of the standard …

We consider the problem of stable region detection and segmentation of deformable shapes. We pursue this goal by determining a …

We propose a shape matching method that produces dense correspondences tuned to a specific class of shapes and deformations. In a …

We consider a parametrized relaxation of the widely adopted quadratic assignment problem (QAP) formulation for minimum distortion …

We propose the adoption of a vector extrapolation technique to accelerate convergence of correspondence problems under the quadratic …

Traditional camera models are often the result of a compromise between the ability to account for non-linearities in the image …

Phase shift methods have proven to be very robust and accurate for photometric 3D reconstruction. One problem of these approaches is …

During the last years a wide range of algorithms and devices have been made available to easily acquire range images. The increasing …

We consider the problem of minimum distortion intrinsic correspondence between deformable shapes, many useful formulations of which …

Most Structure from Motion pipelines are based on the iterative refinement of an initial batch of feature correspondences. Typically …

Over the last decades fiducial markers have provided widely adopted tools to add reliable model-based features into an otherwise …

Surface registration is a fundamental step in the reconstruction of three-dimensional objects. While there are several fast and …

Surface registration is a fundamental step in the reconstruction of three-dimensional objects. This is typically a two-step process …

During the last few years a wide range of algorithms and devices have been made available to easily acquire range images. To this …

Many successful feature detectors and descriptors exist for 2D intensity images. However, obtaining the same effectiveness in the …

Accurate intrinsic camera calibration is essential to any computer vision task that involves image based measurements. Given its …

In this paper we introduce a robust matching technique that allows to operate a very accurate selection of corresponding feature points …

Feature-based image matching relies on the assumption that the features contained in the model are distinctive enough. When both model …

In this paper we introduce a robust matching technique that allows very accurate selection of corresponding feature points from …

Surface registration is a fundamental step in the reconstruction of three-dimensional objects. This is typically a two step process …

Bundle Adjustment is a widely adopted self-calibration technique that allows to estimate scene structure and camera parameters at once. …

Phase shift methods have proven to be very robust and accurate for photometric 3D reconstruction. One problem of these approaches is …