3 papers
cs.CV2026
Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models
Yiwei Xie, Ping Liu, Zheng Zhang
Text-to-video diffusion transformers encode semantic information unevenly across model depth, which constrains effective concept erasure. We identify a representational bottleneck,…
cs.CV2026
PROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Models
Yiwei Xie, Zheng Zhang, Ping Liu
Concept erasure techniques for text-to-video (T2V) diffusion models report substantial suppression of sensitive content, yet current evaluation is limited to checking whether the t…
cs.CV2025
Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression
Yiwei Xie, Ping Liu, Zheng Zhang
Text-to-Image (T2I) models have demonstrated impressive capabilities in generating high-quality and diverse visual content from natural language prompts. However, uncontrolled repr…