AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Score-Based Generative Models Detect Manifolds

Jakiw Pidstrigach

NeurIPS 2022 · Image generation › Fast diffusion sampling · approach: Distributional control of diffusion · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use pretrained DDPM++ drift instead of exact empirical driftreverse SDE · CIFAR-10distance to training examplesImproved
perturb empirical drift with constant vector (1,...,1)reverse SDE with empirical drift · CIFAR-10distance to closest training image: 0 -> 0.07Hurt
perturb the drift with a constant error vector (0,-1)reverse SDE · unit circle S1support of sample distributionNo clear effect
poor prior approximation N(m, I) instead of p1reverse SDE · unit circle S1uniformity of samplesHurt
use perturbed drift instead of DDPM++ driftreverse SDE · CIFAR-10martingale integral at t to 1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

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