AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

One-shot Conditional Sampling: MMD meets Nearest Neighbors

Anirban Chatterjee, Sayantan Choudhury, Rohan Hore

ICML 2026 · Image generation › Fast diffusion sampling · approach: Distributional control of diffusion · 0 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 CGMMD instead of full diffusion model for conditional samplingMNIST denoising · MNIST denoising (sigma=0.9)time per image (s): 5.42 × 10−2 -> 5.6 × 10−4Improved
use CGMMD instead of full diffusion model for conditional samplingMNIST denoising · MNIST denoising (sigma=0.9)PSNR: 13.326 -> 8.922Hurt
use CGMMD instead of distilled diffusionMNIST denoising · MNIST denoising (sigma=0.9)SSIM: 0.508 -> 0.718Improved
use CGMMD instead of GCDS and WGAN at high noiseHelix conditional sampling · Helix benchmark, sigma 0.2 to 0.6qualitative sample fidelityImproved
add l1 regularisation to WGANWGAN baseline · Helix benchmarktraining stabilityImproved
increase ambient dimension d from 25 to 500 with fixed intrinsic dimension 5 (ablation)CGMMD · Synthetic intrinsic-dimension experimentMSE of conditional mean and SDNo clear effect
vary kernel among Gaussian, Laplace and IMQ (ablation)CGMMD · Synthetic intrinsic-dimension experimentMSE of conditional mean and SDNo clear effect

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