α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Fabien Roger
Fabien Roger
2
papers
115
total citations
papers (2)
AI Control: Improving Safety Despite Intentional Subversion
ICML 2024
arXiv
110
citations
Why Do Some Language Models Fake Alignment While Others Don't?
NEURIPS 2025
arXiv
5
citations