Scholar
David Williams-King
Google Scholar ID: IRiBU0gAAAAJ
Research Scientist, Mila
cybersecurity
artificial intelligence
accessibility
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
678
H-index
9
i10-index
8
Publications
20
Co-authors
5
list available
Publications
15 items
Activation Flow: Manufacturing Activations for Steering
2026
Cited
0
GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis
2026
Cited
0
A Causal Model for Locating and Unlocking Sandbagging in Model Organisms
2026
Cited
0
Reference-Grafting Matches Fine-Tuning at Eliciting Sandbagged Capabilities
2026
Cited
0
Efficient Safety Alignment of Language Models via Latent Personality Traits
2026
Cited
0
"I've Seen How This Goes": Characterizing Diversity via Progressive Conditional Surprise
2026
Cited
0
Behavioural Analysis of Alignment Faking
2026
Cited
0
FragBench: Cross-Session Attacks Hidden in Benign-Looking Fragments
2026
Cited
0
Load more
Co-authors
4 total
Junfeng Yang
Professor of Computer Science, Columbia University
Vasileios P. Kemerlis
Associate Professor, Brown University
Kexin Pei
Assistant Professor, Computer Science, University of Chicago
Yoshua Bengio
Professor of computer science, University of Montreal, Mila, IVADO, CIFAR