Scholar
Phillip Guo
Google Scholar ID: htCMHnUAAAAJ
University of Maryland
Transformers
Interpretability
Optimization
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
886
H-index
6
i10-index
6
Publications
8
Co-authors
0
Contact
No contact links provided.
Publications
3 items
Predicting LLM Safety Before Release by Simulating Deployment
2026
Cited
0
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
2024
Cited
72
Representation Engineering: A Top-Down Approach to AI Transparency
arXiv.org · 2023
Cited
298
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
