AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

OmniAID: Decoupling Semantic and Artifacts for Universal AI-Generated Image Detection in the Wild

Yuncheng Guo, Junyan Ye, Chenjue Zhang, Hengrui Kang, Haohuan Fu, Conghui He, Weijia Li

ICML 2026 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection

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 Universal Artifact Expert to the semantic experts (ablation)OmniAID · Chameleon (trained on GenImage SD v1.4)accuracy (%): 66.07 -> 77.35Improved
add Object/Scene semantic expert e1 (ablation)OmniAID · Chameleon (trained on GenImage SD v1.4)accuracy (%): 68.11 -> 77.35Improved
add Human/Animal semantic expert e0 (ablation)OmniAID · Chameleon (trained on GenImage SD v1.4)accuracy (%): 70.80 -> 77.35Improved
combine both semantic experts with the artifact expert instead of a single expert (ablation)OmniAID · GenImage (trained on SD v1.4)accuracy (%): 84.38 -> 95.94Improved
train on Mirage-Train instead of GenImage-SD v1.4OmniAID · Mirage-Testaccuracy (%): 51.10 -> 88.39Improved
train on Mirage-Train instead of GenImage-SD v1.4OmniAID · Chameleonaccuracy (%): 77.35 -> 91.42Improved
train on Mirage-Train instead of GenImage-SD v1.4Effort · GenImageaccuracy (%): 91.10 -> 85.00Hurt
train on Mirage-Train instead of GenImage-SD v1.4AIDE · Mirage-Testaccuracy (%): 31.25 -> 76.78Improved
train on Mirage-Train instead of GenImage-SD v1.4OmniAID · GenImageaccuracy (%): 95.94 -> 97.24Improved
use SVD initialization instead of standard LoRA initialization (ablation)OmniAID experts · OOD benchmarksaccuracy (%)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