3 papers
cs.CR2026
When Safe Concepts Become Unsafe: Multi-Concept Compositional Vulnerabilities in Text-to-Image Models
Chaoshuo Zhang, Yibo Liang, Mengke Tian +7
Text-to-image (T2I) models are increasingly optimized for following user instructions faithfully. However, we find that this capability introduces a safety vulnerability we call Mu…
cs.CV2025
Concept Unlearning by Modeling Key Steps of Diffusion Process
Chaoshuo Zhang, Chenhao Lin, Zhengyu Zhao +3
Text-to-image diffusion models remain susceptible to generating undesirable or harmful content. Although concept unlearning mitigates this risk, existing methods struggle with a cr…
cs.CV2025
LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision
Chunyu Li, Chao Zhang, Weikai Xu +6
End-to-end audio-conditioned latent diffusion models (LDMs) have been widely adopted for audio-driven portrait animation, demonstrating their effectiveness in generating lifelike a…