We present WineSensed, a large multimodal wine dataset for studying the
...
Digital dentistry has made significant advancements in recent years, yet...
Bayesian neural networks often approximate the weight-posterior with a
G...
Masked pre-training removes random input dimensions and learns a model t...
Out of distribution (OOD) medical images are frequently encountered, e.g...
We propose the first Bayesian encoder for metric learning. Rather than
r...
Riemannian geometry provides powerful tools to explore the latent space ...
Pre-trained protein language models have demonstrated significant
applic...
Decoders built on Gaussian processes (GPs) are enticing due to the
margi...
Established methods for unsupervised representation learning such as
var...
This paper presents the computational challenge on differential geometry...
The encoder network of an autoencoder is an approximation of the nearest...
Deep generative models can automatically create content of diverse types...
Faithful visualizations of data residing on manifolds must take the
unde...
In recent decades, advancements in motion learning have enabled robots t...
We present simple methods for out-of-distribution detection using a trai...
Stochastic latent variable models (LVMs) achieve state-of-the-art perfor...
We present a method to fit exact Gaussian process models to large datase...
Place recognition and visual localization are particularly challenging i...
Probabilistic models often use neural networks to control their predicti...
Energy-based models (EBMs) provide an elegant framework for density
esti...
Latent space geometry has shown itself to provide a rich and rigorous
fr...
For robots to work alongside humans and perform in unstructured environm...
We present Multi-chart flows, a flow-based model for concurrently learni...
Deep generative models have shown themselves to be state-of-the-art dens...
Uncertainty quantification in image retrieval is crucial for downstream
...
Causal discovery estimates the underlying physical process that generate...
A common assumption in generative models is that the generator immerses ...
We propose a fully generative model where the latent variable respects b...
High-capacity models require vast amounts of data, and data augmentation...
Variational Autoencoders (VAEs) represent the given data in a low-dimens...
Manifold learning seeks a low dimensional representation that faithfully...
We propose a fast, simple and robust algorithm for computing shortest pa...
Deep generative models are tremendously successful in learning
low-dimen...
We investigate learning of the differential geometric structure of a dat...
Latent variable models learn a stochastic embedding from a low-dimension...
Deep generative models provide a systematic way to learn nonlinear data
...
Principal Component Analysis (PCA) is a fundamental method for estimatin...
The multivariate normal density is a monotonic function of the distance ...
Data augmentation is a key element in training high-dimensional models. ...
We investigate the geometrical structure of probabilistic generative
dim...
We consider kernel methods on general geodesic metric spaces and provide...
We study a probabilistic numerical method for the solution of both bound...