A diffusion model unlearning method that automatically chooses a closely related, non-synonym target concept for each erased concept, reducing side effects on other concepts while keeping erasure effective.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them
A diffusion model unlearning method that automatically chooses a closely related, non-synonym target concept for each erased concept, reducing side effects on other concepts while keeping erasure effective.