AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clustering

Denis Lukovnikov, Andreas Müller, Erwin Quiring, Asja Fischer

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Next-scale and token autoregressive images · 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
cluster green/red sets (k=64) instead of per-token sets (ablation)KGW-style AR watermark (LlamaGen GPT-B) · Gaussian noise std .2TPR@FPR=1%: 0.075 -> 0.369Improved
cluster green/red sets (k=64) instead of per-token sets (ablation)KGW-style AR watermark (RAR-XL) · Gaussian blur R3TPR@FPR=1%: 0.045 -> 0.100Improved
cluster green/red sets (k=64) (ablation)KGW-style AR watermark (LlamaGen GPT-L) · Regeneration attackTPR@FPR=1%: 0.812 -> 0.997Improved
add cluster classifier to clustered watermark (ablation)Ours (Clustering, k=64), LlamaGen GPT-L · Salt & Pepper .1TPR@FPR=1%: 0.543 -> 1.000Improved
add token classifier to clustered watermark (ablation)Ours (Clustering, k=64), RAR-XL · Gaussian blur R3TPR@FPR=1%: 0.100 -> 0.837Improved
add token classifier without clustering (ablation)Ours (No Clustering), LlamaGen GPT-B · Gaussian blur R3TPR@FPR=1%: 0.068 -> 0.366Improved
add clustering (ablation)Ours, LlamaGen GPT-L · ImageNet FIDFID: 4.36 -> 4.85Hurt
add clustering (ablation)Ours, RAR-XL · ImageNet FIDFID: 3.14 -> 3.96Hurt
lower number of clusters (below 64) (ablation)Training-free clustered watermark · TPR and FID (Fig. 3, 4)TPR@FPR=1%, FID: k=8 to 128Mixed
higher penalty delta (2 -> 5) (ablation)Clustered watermark · TPR under perturbationsTPR@FPR=1%Improved
lower green fraction (0.5 -> 0.25) (ablation)Clustered watermark · TPR / FIDTPR@FPR=1%, FIDMixed
choose best hash prefix (kappa=5 vs kappa=1) (ablation)Clustered watermark k=8, LlamaGen GPT-B · green token ratio of unwatermarked imagesseparabilityImproved

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