Scholar
Usman Anwar
Google Scholar ID: UBAfLyQAAAAJ
University of Cambridge
Reinforcement Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,325
H-index
8
i10-index
8
Publications
16
Co-authors
0
Contact
Email
https://mailhide.io/e/Mpto2XvD
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
6 items
A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
2026
Cited
0
Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory
2026
Cited
1
Mitigating Goal Misgeneralization with Minimax Regret
2025
Cited
0
Interpreting Emergent Planning in Model-Free Reinforcement Learning
2025
Cited
0
The Reality of AI and Biorisk
2024
Cited
0
Adversarial Robustness of In-Context Learning in Transformers for Linear Regression
arXiv.org · 2024
Cited
10
Resume (English only)
Research Experience
Extensive research experience in AI safety, alignment, and reinforcement learning.
Education
PhD, University of Cambridge, supervised by David Krueger. Funded by Open Phil AI Fellowship and Vitalik Buterin Fellowship on AI Safety.
Background
PhD student in Computational and Biological Learning lab at Cambridge University, UK. Broadly interested in AI Safety and Alignment.
Miscellany
Contact: Email / GitHub / Google Scholar / LinkedIn / CV
Co-authors
0 total
Co-authors: 0 (list not available)
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up