AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

PPM-CLIP: Probabilistic Prompt Modeling for Generalizable AI-Generated Image Detection

Xinyuan Wang, Yingxin Lai, Zhiming Luo, Zhihui Liu

CVPR 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 Prompt Flow Module (probabilistic prompts) (ablation)PPM-CLIP · GenImage meanmAcc: 92.1 -> 99.6Improved
add PWCL patch-wise contrastive learning (ablation)PPM-CLIP · GenImage meanmAcc: 80.0 -> 99.6Improved
use frequency-based patch selection instead of random (ablation)PWCL · GenImage meanmAcc: 95.0 -> 99.6Improved
add Prompt Repository (ablation)PPM-CLIP · GenImage meanmAcc: 88.9 -> 99.6Improved
increase Monte Carlo samples from 2 to 10 (ablation)PPM-CLIP · GenImage meanmAcc: 98.6 -> 100.0 (FPS 50.51 -> 18.76)Improved
increase Monte Carlo samples from 4 to 10 (ablation)PPM-CLIP · GenImage meanmAcc: 99.6 -> 100.0Improved
raise KL weight from 0.001 to 0.1 (ablation)PPM-CLIP · GenImage meanmAcc: 99.6 -> 97.1Hurt
lower KL weight from 0.001 to 0.0001 (ablation)PPM-CLIP · GenImage meanmAcc: 99.6 -> 92.3Hurt
use PPM-CLIP vs best baselinePPM-CLIP · DRCT averageaccuracy: 91.35 -> 95.72 (DRCT)Improved
use PPM-CLIP vs UnivFD on inpainting (DR variants)PPM-CLIP · DRCT DR variantsaccuracy: ~51% -> 87.80% (SDv1/v2-DR)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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