Fake-HR1: Rethinking Reasoning of Vision Language Model for Synthetic Image Detection

ArXi:2602.10042v3 Announce Type: replace-cross Recent studies have nstrated that incorporating Chain-of-Thought (CoT) reasoning into the detection process can enhance a model's ability to detect synthetic images. However, excessively lengthy reasoning incurs substantial resource overhead, including token consumption and latency, which is particularly redundant when handling obviously generated forgeries.