Not All Steps Matter: Temporally Adaptive Spectral Control for Concept Removal in Diffusion Models
As text-to-image diffusion models see widespread deployment, removing unsafe or undesirable concepts without retraining has become a pressing need. Spectral methods are attractive because they are training-free and reversible, yet current variants apply the same output-value (OV) circuit…
By Chanaka Thushitha Bandara, Lakmali Nadeesha Kumari, Sen-Ching Samson CheungarXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Nov 17, 2026.
Comments
Sign in to join the discussion.