Fedzechkina, Masha

2 publications

TMLR 2026 ExpertLens: Activation Steering Features Are Highly Interpretable Masha Fedzechkina, Eleonora Gualdoni, Sinead Williamson, Katherine Metcalf, Skyler Seto, Barry-John Theobald
AAAI 2024 Can You Rely on Synthetic Labellers in Preference-Based Reinforcement Learning? It's Complicated Katherine Metcalf, Miguel Sarabia, Masha Fedzechkina, Barry-John Theobald