-
A Prior of a Googol Gaussians: a Tensor Ring Induced Prior for Generative Models
Generative models produce realistic objects in many domains, including text, image, video, and audio synthesis. Most popular models—Generative Adversarial Networks (GANs) and... -
LatentGAN Autoencoder: Learning Disentangled Latent Distribution
LatentGAN Autoencoder: Learning Disentangled Latent Distribution -
CIFAR10 dataset
The dataset used in this paper is the CIFAR10 dataset, which contains 60,000 32x32 color images in 10 classes, with 6,000 images per class. -
Dualsmoke: Sketch-based smoke illustration design with two-stage generative m...
The Sketch-based smoke illustration design with two-stage generative model -
Importance weighted autoencoders
Importance weighted autoencoders -
SGVAE: Sequential Graph Variational Autoencoder
Generative models of graphs are well-known, but many existing models are limited in scalability and expressivity. We present a novel sequential graphical variational autoencoder... -
SPI-GAN: DENOISING DIFFUSION GANS WITH STRAIGHT-PATH INTERPOLATIONS
Score-based generative models (SGMs) show the state-of-the-art sampling quality and diversity. However, their training/sampling complexity is notoriously high due to the highly... -
Adversarial Feature Learning
Adversarial Feature Learning -
VELC: A New Variational AutoEncoder Based Model for Time Series Anomaly Detec...
Time series anomaly detection method based on VAE with re-Encoder and latent constraint network -
Urban Sound Propagation
The Urban Sound Propagation benchmark is based on the physically complex and practically relevant, yet intuitively easy to grasp task of modeling the 2d propagation of waves... -
Generative Adversarial Networks
Generative Adversarial Networks (GANs) consist of two networks: a generator G(z) and a discriminator D(x). The discriminator is trying to distinguish real objects from objects... -
IMAGE DATA
The MNIST, Fashion-MNIST, CIFAR-10, and CelebA datasets are used for image data. -
2D TOY DATA
The Swiss roll and 9 Gaussian mixture grid are the true distributions, and our energy function Eθ : R2 → R is a simple neural network with several fully connected layers. -
Synthetic example
The dataset is not explicitly described in the paper, but it is mentioned that the authors used a synthetic example to demonstrate the issue with the envelop theorem. -
Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models
The dataset used in the paper for Bespoke Non-Stationary (BNS) solvers for fast sampling of diffusion and flow models. -
Synthetic dataset for hyperbolic GAN
The dataset used in the paper is a synthetic dataset generated using the proposed hyperbolic generative adversarial network (GAN) model. -
Generative Manufacturing Systems
Generative Manufacturing Systems (GMS) dataset, using diffusion models and ChatGPT for implicit learning from envisioned futures.
