arxiv
PublishedOctober 3, 2026 at 4:00 AM
—neutral
The Null Is the Hard Part: Exact Tests for Memorization in Generative Models
Publisher summary· verbatim
arXiv:2610.00251v1 Announce Type: new Abstract: Memorization audits of generative models read similarity scores against thresholds, with no null distribution, and the conclusions they support can be wrong. By MemBench's rule, the benchmark's mitigations roughly halve Stable Diffusion's memorization;
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
arxivSequential Capacity of Quantum Processes with Finite Memory1darxivGraph Representation via Elements of Discrete Morse and Cobordism Theories1darxivAF-Muon: An AdamW-Free Muon Optimizer for Tied-Embedding Models1darxivDo Your Own Research: Learning to Forecast by Learning to Search1dThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗