AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Data Provenance for Image Auto-Regressive Generation

Bihe Zhao, Louis Kerner, Michel Meintz, Tameem Bakr, Franziska Boenisch, Adam Dziedzic

ICLR 2026 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 0 citations (OpenAlex)

Read the paper

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 calibration to the encoder reconstruction loss (ablation)EncLoss on VAR · ImageNet non-belongingTPR@1%FPR (%): 17.0 -> 100.0Improved
add calibration to the encoder reconstruction loss (ablation)EncLoss on RAR · ImageNet non-belongingTPR@1%FPR (%): 22.6 -> 98.2Improved
add calibration to the encoder reconstruction loss (ablation)EncLoss on Infinity · ImageNet non-belongingTPR@1%FPR (%): 0.3 -> 0.0Hurt
finetune inverse decoder instead of original encoder (ablation)combined loss on RAR · ImageNet non-belongingTPR@1%FPR (%): 6.2 -> 100.0Improved
finetune inverse decoder instead of original encoder (ablation)combined loss on VQDiff · LAION non-belongingTPR@1%FPR (%): 33.2 -> 99.4Improved
add optimized token search to quantization loss (ablation)Quantization loss on VAR · ImageNet non-belongingTPR@1%FPR (%): 0.4 -> 95.0Improved
combine quantization loss with encoder loss (ablation)Quantization loss on VAR · ImageNet non-belongingTPR@1%FPR (%): 0.4 -> 100.0Improved
combine quantization and encoder losses (ablation)Quantization loss on Infinity · ImageNet non-belongingTPR@1%FPR (%): 99.4 -> 0.0Hurt
finetune inverse decoder with augmentations (ablation)Quantization loss on RAR · Noise (0.05) attackTPR@1%FPR (%): 60.4 -> 87.8Improved
finetune inverse decoder with augmentations (ablation)Quantization loss on RAR · Contrast (2.0) attackTPR@1%FPR (%): 45.7 -> 91.1Improved
increase optimization iterations from 100 to 1200 (ablation)Optimized token search on VAR · ImageNet non-belongingTPR@1%FPR (%): 87.5 -> 95.0Improved
increase optimization iterations from 1200 to 1600 (ablation)Optimized token search on VAR · ImageNet non-belongingTPR@1%FPR (%): 95.0 -> 92.2Hurt

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