AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Generative Modelling with Inverse Heat Dissipation

Severi Rissanen, Markus Heinonen, Arno Solin

ICLR 2023 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 11 citations (OpenAlex)

Read the paper

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 inverse heat dissipation instead of standard diffusionIHDM · CIFAR-10FID: 18.96 vs 3.17Hurt
Set forward-process noise σ to zero (ablation)IHDM · MNISTsample qualityHurt
Set sampling noise δ to zero (ablation)IHDM · Image generationimage detailHurt
Increase sampling noise δ above the training noise σ (ablation)IHDM · Image generationimage detail: 1.25 to 1.3Improved
Increase sampling noise δ too far (ablation)IHDM · Image generationsample qualityHurt
Train on only the first 20 MNIST digits (ablation)IHDM · MNISTgeneralization: 20Improved

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