Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
When Are Concepts Erased From Diffusion Models?
Kevin Lu, Nicky Kriplani, Rohit Gandikota +4
In concept erasure, a model is modified to selectively prevent it from generating a target concept. Despite the rapid development of new methods, it remains unclear how thoroughly…
cs.LG2025
One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models
Viacheslav Surkov, Chris Wendler, Antonio Mari +5
For large language models (LLMs), sparse autoencoders (SAEs) have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of…