AI RESEARCH
ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clustering
arXiv CS.CV
•
ArXi:2508.06656v2 Announce Type: replace In-generation watermarking for latent diffusion models has recently shown high robustness in marking generated images for easier detection and attribution. However, its application to autoregressive (AR) image models is underexplored. Autoregressive models generate images by autoregressively predicting a sequence of visual tokens that are then decoded into pixels using a VQ-VAE decoder. Inspired by KGW watermarking for large language models, we examine token-level watermarking schemes that bias the next-token prediction based on prior tokens.