AI safety researcher

Kexin Pei

Google Scholar dblp

Last 12 months2 papers

AI safety papers from the last year

On this site: 7 papers

October 2026

Natural Code Transformation Confuses Agents in Vulnerability Analysis
Oct 9arXiv ↗

April 2026

SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair
Apr 19arXiv ↗

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