AI Paper Atlas

Research map / Probabilistic and scientific modeling

Variational and generative sampling: research map

2,370 papers on Variational and generative sampling in Probabilistic and scientific modeling, from ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR (2016–2026), grouped into 6 clusters and 24 approaches. The busiest year so far is 2026.

What it is

Many problems need samples from, or estimates of, a complicated probability distribution. This topic covers the main tools: variational inference (fitting a simple distribution), Monte Carlo sampling, normalizing flows, VAEs and diffusion-based samplers.

Terms you will see on this page:

Variational inference
approximating a hard distribution with the closest member of a simpler family.
MCMC
Markov chain Monte Carlo, generating samples by a random walk that settles on the target distribution.
Normalizing flow
an invertible network that turns simple noise into data and gives exact likelihoods.

Start reading with the most cited papers here:

Within Probabilistic and scientific modeling, its share shrank from 20.4% in 2023–24 to 16.4% in 2025–26 (414 → 499 papers at ICML, NeurIPS, ICLR, CVPR and AAAI, the venues with data for all four years).

2016: 128162017: 140172018: 166182019: 229192020: 258202021: 214212022: 208222023: 240232024: 232242025: 237252026: 31826

Explore Variational and generative sampling in the interactive map

Working on something in this topic? Describe your idea in scime atlas to see which approach it falls under, the closest papers by meaning and how crowded the spot has become.

What changed recently

Approaches whose share of the topic moved most between 2023–24 and 2025–26 (ICML, NeurIPS, ICLR, CVPR and AAAI):

Papers from 2025–2026 that are already cited most:

Approaches and key papers

Probabilistic estimation · 636 papers
Keywords: estimation, probabilistic, variables

Approaches in this cluster:

Most cited and most cited since 2024:

Diffusion and score-based sampling · 445 papers
Keywords: diffusion, score, matching

Approaches in this cluster:

Most cited and most cited since 2024:

Variational autoencoders · 435 papers
Keywords: vae, autoencoders, latent

Approaches in this cluster:

Most cited and most cited since 2024:

Monte Carlo methods · 344 papers
Keywords: monte, carlo, mcmc

Approaches in this cluster:

Most cited and most cited since 2024:

Variational inference · 308 papers
Keywords: variational inference, vi, lower

Approaches in this cluster:

Most cited and most cited since 2024:

Normalizing flows · 202 papers
Keywords: flows, normalizing, invertible

Approaches in this cluster:

Most cited and most cited since 2024:

Related topics in Probabilistic and scientific modeling

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy