ML Anthology

Henry, Nathan W.

2 publications

ICLR 2026 RepIt: Steering Language Models with Concept-Specific Refusal Vectors Vincent Siu, Nathan W. Henry, Nicholas Crispino, Yang Liu, Dawn Song, Chenguang Wang
ICLR 2025 Geometry of Lightning Self-Attention: Identifiability and Dimension Nathan W. Henry, Giovanni Luca Marchetti, Kathlén Kohn