arxiv
PublishedJuly 10, 2026 at 4:00 AM
AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate
Publisher summary· verbatim
arXiv:2607.08337v1 Announce Type: new Abstract: Diffusion unlearning is essential for mitigating the generation of harmful or copyrighted content in text-to-image models. Current diffusion unlearning techniques determine the model update direction by either using alternatives of the target concept a
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivSvarna: An Open Corpus Workbench for Modern Greek19harxivWhen LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals19harxivPLURAL: A Global Dataset for Value Alignment19harxivBiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression19hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗