Bartosz Cywinski

According to our database, Bartosz Cywinski authored at least 8 papers between 2025 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation.

Helena Casademunt, Bartosz Cywinski, Khoi Tran, Arya Jakkli, Samuel Marks, Neel Nanda

CoRR, March, 2026

Simple LLM Baselines are Competitive for Model Diffing.

Elias Kempf, Simon Schrodi, Bartosz Cywinski, Thomas Brox, Neel Nanda, Arthur Conmy

CoRR, February, 2026

2025

Eliciting Secret Knowledge from Language Models.

Bartosz Cywinski, Emil Ryd, Rowan Wang, Senthooran Rajamanoharan, Neel Nanda, Arthur Conmy, Samuel Marks

CoRR, October, 2025

Towards eliciting latent knowledge from LLMs with mechanistic interpretability.

Bartosz Cywinski, Emil Ryd, Senthooran Rajamanoharan, Neel Nanda

CoRR, May, 2025

Adapt & Align: Continual Learning with Generative Models' Latent Space Alignment.

Kamil Deja, Bartosz Cywinski, Jan Rybarczyk, Tomasz Trzcinski

Neurocomputing, 2025

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders.

Bartosz Cywinski, Kamil Deja

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Precise Parameter Localization for Textual Generation in Diffusion Models.

Lukasz Staniszewski, Bartosz Cywinski, Franziska Boenisch, Kamil Deja, Adam Dziedzic

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

GUIDE: Guidance-Based Incremental Learning with Diffusion Models.

Bartosz Cywinski, Kamil Deja, Tomasz Trzcinski, Bartlomiej Twardowski, Lukasz Kucinski

Proceedings of the ECAI 2025 - 28th European Conference on Artificial Intelligence, 25-30 October 2025, Bologna, Italy, 2025