D
Diederik P. Kingma
Researcher at Google
Publications - 45
Citations - 173232
Diederik P. Kingma is an academic researcher from Google. The author has contributed to research in topics: Inference & Artificial neural network. The author has an hindex of 27, co-authored 42 publications receiving 130871 citations. Previous affiliations of Diederik P. Kingma include OpenAI & University of Amsterdam.
Papers
More filters
Journal ArticleDOI
Imagen Video: High Definition Video Generation with Diffusion Models
Jonathan Ho,V. K. Chan,Chitwan Saharia,Jay Whang,Ruiqi Gao,Alexey A. Gritsenko,Diederik P. Kingma,Ben Poole,Mahmood Norouzi,David J. Fleet,Tim Salimans +10 more
TL;DR: Imagen Video is presented, a text-conditional video generation system based on a cascade of video diffusion models not only capable of generating videos of high quality, but also having a high degree of controllability and world knowledge, including the ability to generate diverse videos and text animations in various artistic styles and with 3D object understanding.
Posted Content
Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
TL;DR: In this article, a new synthesis of variational inference and Monte Carlo methods is proposed, where one or more steps of MCMC are incorporated into the variational approximation of the objective function.
Posted Content
Glow: Generative Flow with Invertible 1x1 Convolutions
TL;DR: Glow as discussed by the authors is a simple type of generative flow using an invertible 1x1 convolution, which is able to achieve a significant improvement in log-likelihood on standard benchmarks.
Proceedings ArticleDOI
Flow Contrastive Estimation of Energy-Based Models
TL;DR: In this paper, the authors proposed a joint training method to jointly estimate an energy-based model and a flow-based one, in which the two models are iteratively updated based on a shared adversarial value function.
Proceedings Article
Score-Based Generative Modeling through Stochastic Differential Equations
TL;DR: In this article, a score-based generative model is proposed to generate images from a complex data distribution by slowly injecting noise, and a corresponding reverse-time SDE that transforms the prior distribution back into the data distribution using slowly removing the noise.