Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

methodology-7

Density Estimation

3260 papers • 126 benchmarks • 313 datasets

The goal of Density Estimation is to give an accurate description of the underlying probabilistic density distribution of an observable data set with unknown density. Source: Contrastive Predictive Coding Based Feature for Automatic Speaker Verification

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in density-estimation-7

Trend

Dataset

Best Model

Actions

CIFAR-10

CIFAR-10

UCI POWER

UCI POWER

UCI GAS

UCI GAS

Libraries

i

Use these libraries to find density-estimation-7 models and implementations

clementchadebec/benchmark_VAE

3 papers 1,668

Datasets

CIFAR-10

MNIST

CelebA-HQ

BSD

Caltech-101

UCI Machine Learning Repository

Subtasks

Arbitrary Conditional Density Estimation

Most implemented papers

Denoising Diffusion Probabilistic Models

P. Abbeel, Jonathan Ho, Ajay Jain•Thu Jun 18 2020

High quality image synthesis results are presented using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics, which naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding.

26731

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

UCI HEPMASS

UCI HEPMASS

UCI MINIBOONE

UCI MINIBOONE

BSDS300

BSDS300

MNIST

MNIST

ImageNet 32x32

ImageNet 32x32

Freyfaces

Freyfaces

OMNIGLOT

OMNIGLOT

Caltech-101

Caltech-101

CIFAR-10 (Conditional)

CIFAR-10 (Conditional)

ImageNet 64x64

ImageNet 64x64

CelebA-HQ 256x256

CelebA-HQ 256x256

lucidrains/imagen-pytorch

2 papers 7,749

yang-song/score_sde_pytorch

2 papers 1,480

yang-song/score_sde

2 papers 1,286

2 papers 40

2 papers 16

UCI Machine Learning Repository

JHU-CROWD++

UCF-CC-50

Silhouettes

0

Glow: Generative Flow with Invertible 1x1 Convolutions

Diederik P. Kingma, Prafulla Dhariwal•Sun Jul 08 2018

Glow, a simple type of generative flow using an invertible 1x1 convolution, is proposed, demonstrating that a generative model optimized towards the plain log-likelihood objective is capable of efficient realistic-looking synthesis and manipulation of large images.

3444 0

Density estimation using Real NVP

Samy Bengio, Jascha Narain Sohl-Dickstein, Laurent Dinh•Thu May 26 2016

This work extends the space of probabilistic models using real-valued non-volume preserving (real NVP) transformations, a set of powerful invertible and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact sampling, exact inference of latent variables, and an interpretable latent space.

4173 0

Importance Weighted Autoencoders

R. Salakhutdinov, Yuri Burda, R. Grosse•Mon Aug 31 2015

The importance weighted autoencoder (IWAE), a generative model with the same architecture as the VAE, but which uses a strictly tighter log-likelihood lower bound derived from importance weighting, shows empirically that IWAEs learn richer latent space representations than VAEs, leading to improved test log- likelihood on density estimation benchmarks.

1311 0

Masked Autoregressive Flow for Density Estimation

G. Papamakarios, Iain Murray, Theo Pavlakou•Thu May 18 2017

This work describes an approach for increasing the flexibility of an autoregressive model, based on modelling the random numbers that the model uses internally when generating data, which is called Masked Autoregressive Flow.

1506 0

MADE: Masked Autoencoder for Distribution Estimation

H. Larochelle, Karol Gregor, Iain Murray, M. Germain•Tue Feb 10 2015

This work introduces a simple modification for autoencoder neural networks that yields powerful generative models and proves that this approach is competitive with state-of-the-art tractable distribution estimators.

925 0

Conditional Image Generation with PixelCNN Decoders

O. Vinyals, Nal Kalchbrenner, K. Kavukcuoglu, Alex Graves, L. Espeholt, Aäron van den Oord•Wed Jun 15 2016

The gated convolutional layers in the proposed model improve the log-likelihood of PixelCNN to match the state-of-the-art performance of PixelRNN on ImageNet, with greatly reduced computational cost.

2691 0

Score-Based Generative Modeling through Stochastic Differential Equations

Stefano Ermon, Jascha Narain Sohl-Dickstein, Diederik P. Kingma, Ben Poole, Yang Song, Abhishek Kumar•Wed Nov 25 2020

This work presents a stochastic differential equation (SDE) that smoothly transforms a complex data distribution to a known prior distribution by slowly injecting noise, and a corresponding reverse-time SDE that transforms the prior distribution back into the data distribution by Slowly removing the noise.

9177 0

Adding a benchmark result helps the community track progress.

Density Estimation | State-of-the-Art