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 …

Normalizing flows provide a general mechanism for defining expressive probability
distributions, only requiring the specification of a (usually simple) base distribution and a …

Diffusion models have significantly advanced the fields of image, audio, and video
generation, but they depend on an iterative sampling process that causes slow generation …

The conjoining of dynamical systems and deep learning has become a topic of great
interest. In particular, neural differential equations (NDEs) demonstrate that neural networks …

Creating noise from data is easy; creating data from noise is generative modeling. We
present a stochastic differential equation (SDE) that smoothly transforms a complex data …

Consistency models are a nascent family of generative models that can sample high quality
data in one step without the need for adversarial training. Current consistency models …

Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier
of p (class| pixel feature). Though straightforward, this de facto paradigm neglects the …

Normalizing flows, autoregressive models, variational autoencoders (VAEs), and deep
energy-based models are among competing likelihood-based frameworks for deep …

Diffusion models have revolutionized text-to-image generation with its exceptional quality
and creativity. However, its multi-step sampling process is known to be slow, often requiring …

Score-based generative models (SGMs) have demonstrated remarkable synthesis quality.
SGMs rely on a diffusion process that gradually perturbs the data towards a tractable …