Diffusion models: A comprehensive survey of methods and applications
Diffusion models have emerged as a powerful new family of deep generative models with
record-breaking performance in many applications, including image synthesis, video …
record-breaking performance in many applications, including image synthesis, video …
Deep generative modelling: A comparative review of vaes, gans, normalizing flows, energy-based and autoregressive models
Deep generative models are a class of techniques that train deep neural networks to model
the distribution of training samples. Research has fragmented into various interconnected …
the distribution of training samples. Research has fragmented into various interconnected …
Denoising diffusion probabilistic models
We present high quality image synthesis results using diffusion probabilistic models, a class
of latent variable models inspired by considerations from nonequilibrium thermodynamics …
of latent variable models inspired by considerations from nonequilibrium thermodynamics …
How to train your energy-based models
Energy-Based Models (EBMs), also known as non-normalized probabilistic models, specify
probability density or mass functions up to an unknown normalizing constant. Unlike most …
probability density or mass functions up to an unknown normalizing constant. Unlike most …
[HTML][HTML] Deep generative modeling for protein design
A Strokach, PM Kim - Current opinion in structural biology, 2022 - Elsevier
Deep learning approaches have produced substantial breakthroughs in fields such as
image classification and natural language processing and are making rapid inroads in the …
image classification and natural language processing and are making rapid inroads in the …
Unsupervised learning of compositional energy concepts
Humans are able to rapidly understand scenes by utilizing concepts extracted from prior
experience. Such concepts are diverse, and include global scene descriptors, such as the …
experience. Such concepts are diverse, and include global scene descriptors, such as the …
Improved contrastive divergence training of energy based models
Contrastive divergence is a popular method of training energy-based models, but is known
to have difficulties with training stability. We propose an adaptation to improve contrastive …
to have difficulties with training stability. We propose an adaptation to improve contrastive …
Learning to compose visual relations
The visual world around us can be described as a structured set of objects and their
associated relations. An image of a room may be conjured given only the description of the …
associated relations. An image of a room may be conjured given only the description of the …
Vaebm: A symbiosis between variational autoencoders and energy-based models
Energy-based models (EBMs) have recently been successful in representing complex
distributions of small images. However, sampling from them requires expensive Markov …
distributions of small images. However, sampling from them requires expensive Markov …
Learning latent space energy-based prior model
We propose an energy-based model (EBM) in the latent space of a generator model, so that
the EBM serves as a prior model that stands on the top-down network of the generator …
the EBM serves as a prior model that stands on the top-down network of the generator …