AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

The Spacetime of Diffusion Models: An Information Geometry Perspective

Rafal Karczewski, Markus Heinonen, Alison Pouplin, Søren Hauberg, Vikas K Garg

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space · 3 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 spacetime geodesic paths instead of MCMC/Doob baselinestransition path sampling · Alanine dipeptideMaxEnergy: 42.54 -> 37.36 (vs MCMC-fixed-length)Improved
use spacetime geodesic instead of MCMC-fixed-lengthtransition path sampling · Alanine dipeptideenergy evaluations: 1.29B -> 16MImproved
add SNR penalty (low-variance) or KL region-avoidance penalty to geodesic (ablation)spacetime geodesic · Alanine dipeptidepath variance / region avoidanceImproved
compare geodesics with PF-ODE trajectoriesEDM2 · ImageNet-512perceptual difference of trajectoriesNo clear effect
compare DiffED with LPIPS and SSIMDiffED · ImageNet image pairscorrelation: LPIPS -7%, SSIM 53%Mixed

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