Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization Paper • 2510.25616 • Published Oct 29 • 96
The Rogue Scalpel: Activation Steering Compromises LLM Safety Paper • 2509.22067 • Published Sep 26 • 27
When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA Paper • 2510.04849 • Published Oct 6 • 114
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features Paper • 2509.22033 • Published Sep 26 • 18