Adapting diffusion models causes hidden damage to unrelated concepts detectable via sparse autoencoders and zero-shot classification, and DriftScope provides a prompt-level token-drift diagnostic.
Tomczak, Tomasz Trzcinski, Florian Shkurti, and Pi- otr Milos
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Modern Hopfield energy identifies high-energy samples as more prone to intrinsic forgetting in continual learning, with effective energy-based replay validated in diffusion models.
citing papers explorer
-
DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation
Adapting diffusion models causes hidden damage to unrelated concepts detectable via sparse autoencoders and zero-shot classification, and DriftScope provides a prompt-level token-drift diagnostic.
-
Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models
Modern Hopfield energy identifies high-energy samples as more prone to intrinsic forgetting in continual learning, with effective energy-based replay validated in diffusion models.
- CollaFuse: Collaborative Diffusion Models