Cywiński, Bartosz

1. SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
   2025/01/29 by Bartosz Cywiński, Kamil Rafał Deja, Cywiński, Bartosz +1 · 14 citations
   Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #Natural Language Processing Techniques #Topic Modeling
2. Towards eliciting latent knowledge from LLMs with mechanistic interpretability
   2025/05/20 by Bartosz Cywiński, Emil Ryd, Cywiński, Bartosz +5 · 4 citations
   Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Semantic Web and Ontologies #Topic Modeling
3. GUIDE: Guidance-based Incremental Learning with Diffusion Models
   2024/03/06 by Cywiński, Bartosz, Deja, Kamil, Trzciński, Tomasz +2 · 1 citation
   #FOS: Computer and information sciences #Machine Learning (cs.LG)
4. Precise Parameter Localization for Textual Generation in Diffusion Models
   2025/02/14 by Staniszewski, Łukasz, Cywiński, Bartosz, Boenisch, Franziska +2 · 2 citations
   #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
5. Eliciting Secret Knowledge from Language Models
   2025/10/01 by Cywiński, Bartosz, Ryd, Emil, Wang, Rowan +4 · 3 citations
   #FOS: Computer and information sciences #Machine Learning (cs.LG)