3 papers
cs.CV2026
When Scene Text Hijacks the Scene: Uncovering, Exploiting, and Mitigating Rendered-Text Semantic Leakage in Image Generation Models
Feifei Li, Runjie Wang, Xiaohan Zhang +3
The reliability and accountability of image generative models (IGMs) are essential for building responsible and trustworthy AI systems. Recent IGMs, such as Nano Banana and GPT-Ima…
cs.CV2026
Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows
Xiang Yang, Feifei Li, Mi Zhang +4
Diffusion transformers (DiTs) equipped with multimodal attention (MM-Attn) have become a dominant paradigm for image generation. However, preventing the generation of harmful conte…
cs.CL2025
ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments
Yuquan Wang, Mi Zhang, Yining Wang +4
Large Reasoning Models (LRMs) have demonstrated impressive performance in reasoning-intensive tasks, but they remain vulnerable to harmful content generation, particularly in the m…