← Search

Bartosz Cywiński

2 accepted papers

2025

Precise Parameter Localization for Textual Generation in Diffusion Models

ICLR 2025poster

Novel diffusion models can synthesize photo-realistic images with integrated high-quality text. Surprisingly, we demonstrate through attention activation patching that only less than $1$\% of diffusion models' parameters, all contained in attention layers, influence the generation of textual conten…

2025

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders

ICML 2025poster

Diffusion models, while powerful, can inadvertently generate harmful or undesirable content, raising significant ethical and safety concerns. Recent machine unlearning approaches offer potential solutions but often lack transparency, making it difficult to understand the changes they introduce to th…