AI RESEARCH

PROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Models

arXiv CS.CV

ArXi:2603.21547v1 Announce Type: new 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 target concept is absent from generated frames, treating output-level suppression as evidence of representational removal. We