AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

General and Efficient Steering of Unconditional Diffusion Models

Qingsong Wang, Mikhail Belkin, Yusu Wang

ICML 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration

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
add high-noise noise alignment to RFM-only steering (ablation)NA-RFM · CIFAR-10 label guidanceaccuracy: 94.8% -> 96.6%Improved
add high-noise noise alignment to RFM-only steering (ablation)NA-RFM · CIFAR-10 label guidanceFID: 40.3 -> 41.4Hurt
add RFM activation steering to noise alignment (ablation)NA-RFM on SiT-XL/2 · ImageNet (SiT-XL/2)accuracy: 12.9% -> 61.3%Improved
add RFM activation steering to noise alignment (ablation)NA-RFM on SiT-XL/2 · ImageNet (SiT-XL/2)FID: 220.9 -> 151.8Improved
increase noise alignment strength lambda from 3 to 8 (ablation)noise alignment only · CIFAR-10 label guidanceaccuracy: 62% -> 80%Improved
increase noise alignment strength lambda from 3 to 8 (ablation)noise alignment only · CIFAR-10 label guidanceFID: 99 -> 120Hurt
train RFM direction at high noise sigma=5.0 instead of sigma in [0.6, 2.0] (ablation)NA-RFM · CIFAR-10generation accuracyHurt
replace TFG-4 with NA-RFMCIFAR-10 label guidance · CIFAR-10 label guidanceaccuracy: 77.1% -> 96.6%Improved
replace classifier guidance with NA-RFMCIFAR-10 label guidance · CIFAR-10 label guidanceaccuracy: 86.0% -> 96.6%Improved
replace TFG-4 with NA-RFMImageNet 256 · ImageNet 256accuracy: 59.8% -> 75.8%Improved
replace TFG-4 with NA-RFMBirds-525 · Birds-525 fine-grainedaccuracy: 2.2% -> 14.1%Improved
replace TFG with NA-RFMCelebA-HQ Gender+Hair · CelebA-HQ Gender+Hairaccuracy: 75.4% -> 83.3%Improved

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