Ye Leng
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper analyzes that while multimodal large language models (MLLMs) offer superior semantic understanding for image generation, this enhanced capability significantly increases safety risks, particularly in generating unsafe content and creating harder-to-detect fake images compared to traditional diffusion models.
This paper introduces GEOFlagBench, a benchmark for detecting Generative Engine Optimization (GEO) pages, and proposes Intervention-Paired Training (IPT) to improve detection accuracy.
Papers
GEO-Flag: Detecting and Measuring GEO-Optimized Web Content
Junjie Chu, Ye Leng, Mingjie Li, Yun Shen +2 more
This paper introduces GEOFlagBench, a benchmark for detecting Generative Engine Optimization (GEO) pages, and proposes Intervention-Paired Training (IPT) to improve detection accuracy.