AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection

Yanran Zhang, Wenzhao Zheng, Yifei Li, Bingyao Yu, Yu Zheng, Lei Chen, Jiwen Lu, Jie Zhou

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 1 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 GDUF second-stage detector-guided optimization (ablation)UniGenDet · FakeClueaccuracy: 40.5 -> 98.0Improved
add GDUF second-stage optimization (ablation)UniGenDet · FakeClueF1: 34.1 -> 97.7Improved
add SMSA module (ablation)UniGenDet · FakeClueaccuracy: 95.0 -> 98.0Improved
add SMSA module (ablation)UniGenDet · FakeClueF1: 94.6 -> 97.7Improved
add SMSA module (ablation)UniGenDet · FakeClueROUGE-L: 50.9 -> 56.3Improved
add detector-guided generator alignment (stage 2) (ablation)BAGEL · FIDFID: 22.9 -> 17.5Improved
add SMSA and full two-stage training on top of BAGEL+GDUF (ablation)UniGenDet · FIDFID: 19.4 -> 17.5Improved
replace FakeVLM with UniGenDet under JPEG quality 90FakeVLM · FakeClue JPEG 90accuracy: 86.8 -> 95.1Improved
replace FakeVLM with UniGenDet under JPEG quality 50FakeVLM · FakeClue JPEG 50accuracy: 80.4 -> 91.3Improved
replace FakeVLM with UniGenDet, no perturbationFakeVLM · FakeClueaccuracy: 98.6 -> 98.0No clear effect
replace FakeVLM with UniGenDet on LlamaGenFakeVLM · ARForensics (LlamaGen)accuracy: 98.1 -> 89.4Hurt
replace FakeVLM with UniGenDet on meanFakeVLM · ARForensicsmean accuracy: 97.1 -> 98.1Improved

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