2013 · Generative models
Auto-Encoding Variational Bayes
Variational autoencoders provide a tractable approach to learning probabilistic latent representations and generating data.
Paper & contextDiederik P. Kingma
Generative models
Learning latent-variable models with efficient gradient estimators.
Kingma’s work connects probabilistic generative models with practical optimization. This selection includes variational autoencoders, the Adam optimizer, and diffusion models, tracing methods that make latent-variable learning and neural-network training easier to carry out.
Selected work
10 papers
2014 · Optimization
Adam: A Method for Stochastic Optimization
Adam combines adaptive learning rates with moving averages of gradients, becoming a widely used optimizer for neural networks.
Paper & context2020 · Generative models
Score-Based Generative Modeling through Stochastic Differential Equations
This paper unifies score-based generative methods through a continuous process that adds noise and a learned process that reverses it.
Paper & context2017 · Generative models
PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications
Selected research in generative models, computer vision. Read the full paper, including the methods, experiments, and reported results.
Paper & context2021 · Generative models
Variational Diffusion Models
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2024 · Generative models
DeMo: Decoupled Momentum Optimization
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2024 · Generative models
Adam-mini: Use Fewer Learning Rates To Gain More
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2024 · Generative models
EM Distillation for One-step Diffusion Models
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2023 · Generative models
Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2022 · Generative models
On Distillation of Guided Diffusion Models
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & contextAn independent editorial profile. Inclusion does not imply Council membership or endorsement. Research is collaborative; coauthorship does not imply sole credit.
Selection & sources