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

As ChatGPT goes viral, generative AI (AIGC, aka AI-generated content) has made headlines
everywhere because of its ability to analyze and create text, images, and beyond. With such …

We argue that the theory and practice of diffusion-based generative models are currently
unnecessarily convoluted and seek to remedy the situation by presenting a design space …

Denoising diffusion models hold great promise for generating diverse and realistic human
motions. However, existing motion diffusion models largely disregard the laws of physics in …

Denoising diffusion models, a class of generative models, have garnered immense interest
lately in various deep-learning problems. A diffusion probabilistic model defines a forward …

Diffusion models have become competitive candidates for solving various inverse problems.
Models trained for specific inverse problems work well but are limited to their particular use …

OpenAI has recently released GPT-4 (aka ChatGPT plus), which is demonstrated to be one
small step for generative AI (GAI), but one giant leap for artificial general intelligence (AGI) …

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 …

Denoising diffusion models, a class of generative models, have garnered immense interest
lately in various deep-learning problems. A diffusion probabilistic model defines a forward …

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 …