AI safety researcher

Pavel Izmailov

Google Scholar dblp

Last 12 months3 papers

Defenses 1Interpretability 1

AI safety papers from the last year

On this site: 5 papers

October 2026

LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification
Oct 12DefensesarXiv ↗

May 2026

How's it going? Reinforcement learning in language models recruits a functional welfare axis
May 28InterpretabilityarXiv ↗

February 2026

Reliable and Responsible Foundation Models: A Comprehensive Survey
Feb 4arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.