AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Generating Risky Samples with Conformity Constraints via Diffusion Models

Han Yu, Hao Zou, Xingxuan Zhang, Zhengyi Wang, Yue He, Kehan Li, Peng Cui

AAAI 2026 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space · 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
add embedding screening and gradient guidance together (ablation)Stable-unCLIP base · NICO++ (ResNet-50)error rate of generated samplesImproved
increase gradient scale s from 0.1 to 50 (ablation)RiskyDiff · NICO++ (ResNet-50)error rate of generated samples: 6.9 -> 73.8Improved
increase gradient scale s beyond 20 (ablation)RiskyDiff · NICO++ (ResNet-50)conformity to category: 58.8 -> 73.8Hurt
increase gradient scale s from 5 to 10 (ablation)RiskyDiff · NICO++ (ResNet-50)FID: 17.7 -> 17.5Improved
raise conformity coefficient from 0 to 0.1 (ablation)RiskyDiff · NICO++ (ResNet-50)error rate of generated samples: 41.3 -> 15.9Hurt
raise conformity coefficient from 0 to 0.0001 (ablation)RiskyDiff · NICO++ (ResNet-50)FID: 19.7 -> 17.5Improved
reduce validation data from full to 0.1 of its size (ablation)RiskyDiff · NICO++ (ResNet-50)error rate of generated samples: 41.2 -> 39.4No clear effect
retrain with AdvDiff-generated data instead of originalResNet-50 · NICO++ ID accuracyaccuracy: 82.9 -> 80.1Hurt
retrain with RiskyDiff-generated dataResNet-50 · PACS OOD accuracyaccuracy: 77.7 -> 81.4Improved
retrain with Mixup instead of originalResNet-50 · PACS OOD accuracyaccuracy: 77.7 -> 72.4Hurt
retrain with RiskyDiff-generated dataResNet-50 · CIFAR-100 testaccuracy: 78.4 -> 79.7Improved
retrain with RiskyDiff-generated dataResNet-50 · NICO++ OOD accuracyaccuracy: 69.6 -> 71.5Improved

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