SOTAVerified

Density Estimation

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

Papers

Showing 110 of 1394 papers

TitleStatusHype
Missing value imputation with adversarial random forests -- MissARF0
3C-FBI: A Combinatorial method using Convolutions for Circle Fitting in Blurry Images0
Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis0
Binned semiparametric Bayesian networksCode0
Distilling Normalizing Flows0
EBC-ZIP: Improving Blockwise Crowd Counting with Zero-Inflated Poisson RegressionCode1
Unsupervised Skill Discovery through Skill Regions Differentiation0
Scaling-Up the Pretraining of the Earth Observation Foundation Model PhilEO to the MajorTOM DatasetCode0
SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning0
Measuring multi-calibration0
Show:102550
← PrevPage 1 of 140Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MAFLog-likelihood (nats)3,049Unverified
2DDPMNLL (bits/dim)3.69Unverified
3MRCNFNLL (bits/dim)3.54Unverified
4FFJORDNLL (bits/dim)3.4Unverified
5RNODENLL (bits/dim)3.38Unverified
6Pixel CNNNLL (bits/dim)3.03Unverified
7score SDENLL (bits/dim)2.99Unverified
8Flow matchingNLL (bits/dim)2.99Unverified
9Pixel CNN ++NLL (bits/dim)2.92Unverified
10Image TransformerNLL (bits/dim)2.9Unverified