← Search

Chenfeng Zhang

2 accepted papers

2026

Fake-HR1: Rethinking Reasoning of vision language model for Synthetic Image Detection

ICASSP 2026poster

Recent studies have demonstrated 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 par…

Cited by 0SourcePDFScholar
2026

TexEditor: Structure-Preserving Text-Driven texture Editing

ICML 2026poster

Text-guided texture editing aims to modify object appearance while preserving the underlying geometric structure. However, our empirical analysis reveals that even SOTA editing models frequently struggle to maintain structural consistency during texture editing, despite the intended changes being pu…

Cited by 0SourceScholar