Diffusion models have achieved remarkable success in generating high-qua...
Hierarchical Variational Autoencoders (VAEs) are among the most popular
...
We introduce a joint diffusion model that simultaneously learns meaningf...
Performant Convolutional Neural Network (CNN) architectures must be tail...
We study the problem of combining neural networks with symbolic reasonin...
The use of Convolutional Neural Networks (CNNs) is widespread in Deep
Le...
Diffusion-based Deep Generative Models (DDGMs) offer state-of-the-art
pe...
Variational autoencoders (VAEs) are deep generative models used in vario...
When designing Convolutional Neural Networks (CNNs), one must select the...
Spiking neural networks are a promising approach towards next-generation...
When controllers (brains) and morphologies (bodies) of robots simultaneo...
Modelers use automatic differentiation of computation graphs to implemen...
In this work, we explore adversarial attacks on the Variational Autoenco...
We introduce Invertible Dense Networks (i-DenseNets), a more parameter
e...
Conventional neural architectures for sequential data present important
...
In this paper, we present a new class of invertible transformations. We
...
Many real-life problems are represented as a black-box, i.e., the intern...
The challenge of robotic reproduction – making of new robots by recombin...
We introduce Invertible Dense Networks (i-DenseNets), a more parameter
e...
Density estimation, compression and data generation are crucial tasks in...
Models in systems biology are mathematical descriptions of biological
pr...
Inducing symmetry equivariance in deep neural architectures has resolved...
The framework of variational autoencoders (VAEs) provides a principled m...
This paper introduces a new method to build linear flows, by taking the
...
Machine learning models trained with purely observational data and the
p...
Not all generate-and-test search algorithms are created equal. Bayesian
...
Differential evolution (DE) is a well-known type of evolutionary algorit...
Although group convolutional networks are able to learn powerful
represe...
Media is generally stored digitally and is therefore discrete. Many
succ...
We generalize the well-studied problem of gait learning in modular robot...
Learning suitable latent representations for observed, high-dimensional ...
In this paper we present a a deep generative model for lossy video
compr...
We consider the problem of domain generalization, namely, how to learn
r...
Optimizing the execution time of tensor program, e.g., a convolution,
in...
This paper focuses on Bayesian Optimization - typically considered with
...
Decision making is a process that is extremely prone to different biases...
The Variational Auto-Encoder (VAE) is one of the most used unsupervised
...
Variational inference relies on flexible approximate posterior distribut...
Multiple instance learning (MIL) is a variation of supervised learning w...
The computer-aided analysis of medical scans is a longstanding goal in t...
In this paper, we propose a new volume-preserving flow and show that it
...
Many different methods to train deep generative models have been introdu...
We introduce a deep learning architecture for structure-based virtual
sc...