Ye Leng
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Vision×1AI×1Crypto×1
Frequent co-authors
Research Timeline
2026
When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm
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.
Highlighted terms show continued research focus across papers
Papers
cs.CVcs.AIcs.CRRecentMar 25, 2026
When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm
Ye Leng, Junjie Chu, Mingjie Li, Chenhao Lin +4 more
The paper analyzes that while multimodal large language models (MLLMs) offer superior semantic understanding for image generation, this enhanced capability significantly increases safety risks, partic…
View →