In recent years Large Language Models (LLMs) have increased the state of...
Quantile regression (QR) is a statistical tool for distribution-free
est...
This paper presents Fauno, the first and largest open-source Italian
con...
Autoregressive decoding limits the efficiency of transformers for Machin...
Triangular meshes are still today the data structure at the main foundat...
The rise in loosely-structured data available through text, images, and ...
Recovering the latent factors of variation of high dimensional data has ...
Representing 3D surfaces as level sets of continuous functions over
ℝ^3 ...
The use of relative representations for latent embeddings has shown pote...
In this work, we define a diffusion-based generative model capable of bo...
Autoregressive models have achieved impressive results over a wide range...
While biological intelligence grows organically as new knowledge is gath...
In this work we present a novel approach for computing correspondences
b...
Aligning the visual and language spaces requires to train deep neural
ne...
Neural networks embed the geometric structure of a data manifold lying i...
Graph Neural Networks (GNNs) have proven to be successful in several
pre...
The latest trends in inverse rendering techniques for reconstruction use...
Many modern deep-learning techniques do not work without enormous datase...
3D human pose estimation is fundamental to understanding human behavior....
We introduce Explanatory Learning (EL), a framework to let machines use
...
The marine ecosystem is changing at an alarming rate, exhibiting biodive...
The convolution operator at the core of many modern neural architectures...
Efficient and practical representation of geometric data is a ubiquitous...
The multiplication of a matrix by its transpose, A^T A, appears as an
in...
State of the art audio source separation models rely on supervised
data-...
In this work, we present a new learning-based pipeline for the generatio...
In this paper, we propose a transformer-based procedure for the efficien...
Machine learning models are known to be vulnerable to adversarial attack...
Spectral geometric methods have brought revolutionary changes to the fie...
We propose a novel approach to disentangle the generative factors of
var...
Shape correspondence is a fundamental problem in computer graphics and
v...
We propose a new approach for 3D shape matching of deformable human shap...
We introduce a novel computational framework for digital geometry proces...
Computer-aided diagnosis (CAD) is becoming a prominent approach to assis...
In this paper, we advocate the adoption of metric preservation as a powe...
We introduce the first learning-based method for recovering shapes from
...
According to Aristotle, a philosopher in Ancient Greece, "the whole is
g...
We consider the problem of localizing relevant subsets of non-rigid geom...
We present a simple and efficient method for refining maps or correspond...
We introduce the first completely unsupervised correspondence learning
a...
The question whether one can recover the shape of a geometric object fro...
We consider the tasks of representing, analyzing and manipulating maps
b...
We introduce a new method for non-rigid registration of 3D human shapes....
We present a method to match three dimensional shapes under non-isometri...
The use of Laplacian eigenfunctions is ubiquitous in a wide range of com...
Many algorithms for the computation of correspondences between deformabl...
Deep learning has achieved a remarkable performance breakthrough in seve...
Many algorithms for the computation of correspondences between deformabl...
Establishing correspondence between shapes is a fundamental problem in
g...
We propose the first algorithm for non-rigid 2D-to-3D shape matching, wh...