SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders

Cywiński and Deja. "SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders." ICLR 2025 Workshops: XAI4Science, 2025.

[Cywiński and Deja. "SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders." ICLR 2025 Workshops: XAI4Science, 2025.](https://mlanthology.org/iclrw/2025/cywinski2025iclrw-saeuron/)

@inproceedings{cywinski2025iclrw-saeuron,
  title     = {{SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders}},
  author    = {Cywiński, Bartosz and Deja, Kamil},
  booktitle = {ICLR 2025 Workshops: XAI4Science},
  year      = {2025},
  url       = {https://mlanthology.org/iclrw/2025/cywinski2025iclrw-saeuron/}
}