Diffusion models have emerged as a powerful new family of deep generative models with
record-breaking performance in many applications, including image synthesis, video …

Training deep neural networks requires gradient estimation from data batches to update
parameters. Gradients per parameter are averaged over a set of data and this has been …

We present high quality image synthesis results using diffusion probabilistic models, a class
of latent variable models inspired by considerations from nonequilibrium thermodynamics …

To date, various 3D scene understanding tasks still lack practical and generalizable pre-
trained models, primarily due to the intricate nature of 3D scene understanding tasks and …

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 …

Energy based models (EBMs) are appealing due to their generality and simplicity in
likelihood modeling, but have been traditionally difficult to train. We present techniques to …

Vision transformer networks have shown superiority in many computer vision tasks. In this
paper, we take a step further by proposing a novel generative vision transformer with latent …

This paper studies a curious phenomenon in learning energy-based model (EBM) using
MCMC. In each learning iteration, we generate synthesized examples by running a non …

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 …

Text generation is ubiquitous in many NLP tasks, from summarization, to dialogue and
machine translation. The dominant parametric approach is based on locally normalized …