3 papers
cs.CV2026
PatchHead: Learning Spatial Patch Evidence for Generalizable AI-Generated Image Detection
Shengbo Qi, Hongyi Fang, Benjia Zhou +1
AI-generated image detectors generalize poorly when their training and test images originate from different generators or datasets. Despite the rich spatial representations produce…
cs.CV2026
Model the Edit, Not the Image: Visual Autoregressive Editing from a Source-Centric Perspective
Hongyi Fang, Chuwen Xie, Benjia Zhou +6
Next-scale visual autoregressive models (VARs) have emerged as a powerful generative paradigm, producing high-quality images through efficient coarse-to-fine prediction. However, t…
cs.CV2026
Detail Continuation over a Trustworthy Coarse Scale for Autoregressive Super-Resolution
Hongyi Fang, Jiahui Wu, Yichen Yue +2
Hallucination remains a persistent challenge in generative super-resolution (GSR), where reconstructed results may contain visually plausible yet weakly supported content, structur…