by Bruce W, Lee Papers
2 papers found
Conference
Distillation Robustifies Unlearning
Bruce W, Lee, Addie Foote, Alex Infanger et al.
NEURIPS 2025spotlightarXiv:2506.06278
6
citations
Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
Mantas Mazeika, Xuwang Yin, Rishub Tamirisa et al.
NEURIPS 2025spotlightarXiv:2502.08640
36
citations