Bartosz Cywiński

Bartosz Cywiński on Hugging Face Daily Papers: 5 papers, 0 in the top 3 of their day, 36 upvotes.

1. Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation 1 upvotes, #22 of 2026-03-09
2. Eliciting Secret Knowledge from Language Models 3 upvotes, #24 of 2025-10-02
3. Towards eliciting latent knowledge from LLMs with mechanistic interpretability 9 upvotes, #23 of 2025-05-21
4. Precise Parameter Localization for Textual Generation in Diffusion Models 11 upvotes, #10 of 2025-02-17
5. SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders 6 upvotes, #9 of 2025-02-03

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.