"activation engineering" Papers
2 papers found
Conference
Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering
JIANFENG CAI, Jiale Hong, Zongmeng Zhang et al.
NEURIPS 2025oralarXiv:2505.12826
3
citations
The Blessing and Curse of Dimensionality in Safety Alignment
Rachel S.Y. Teo, Laziz Abdullaev, Tan Minh Nguyen
COLM 2025paperarXiv:2507.20333
6
citations