NewXResearch hub
ExploreLibraryProfile
Account
Sign In
Linh Le
Scholar

Linh Le

Google Scholar ID: zlYcKiAAAAAJ
University of Queensland, University of Technology Sydney, HPI, Mila Institute, university of Mcgill
Health InfomaticsAI Safety
Google Scholar↗
Citations & Impact
All-time
Citations
136
 
H-index
6
 
i10-index
3
 
Publications
20
 
Co-authors
0
 
Publications
13 items
Activation Flow: Manufacturing Activations for Steering
2026
Cited
0
GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis
2026
Cited
0
Reference-Grafting Matches Fine-Tuning at Eliciting Sandbagged Capabilities
2026
Cited
0
A Causal Model for Locating and Unlocking Sandbagging in Model Organisms
2026
Cited
0
Efficient Safety Alignment of Language Models via Latent Personality Traits
2026
Cited
0
FragBench: Cross-Session Attacks Hidden in Benign-Looking Fragments
2026
Cited
0
Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms
2026
Cited
0
MANTA: Multi-turn Assessment for Nonhuman Thinking&Alignment
2026
Cited
0