Concept Acupuncturist: An Efficient and Precise Concept Erasure Method for Diffusion Models via Sparse Autoencoders
arXiv:2610.32059v1 Announce Type: new Abstract: Diffusion-based image generation models produce high-quality images but may generate harmful or policy-violating content, motivating machine unlearning (MU) to selectively remove target concepts while preserving general capabilities. However, existing…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-26 04:00 · arXiv cs.CV
Concept Acupuncturist: An Efficient and Precise Concept Erasure Method for Diffusion Models via Sparse Autoencoders