AI safety researcher

Kaidi Xu

Google Scholar dblp

Last 12 months5 papers

Evaluation and benchmarks 1

AI safety papers from the last year

On this site: 52 papers

August 2026

SCP-NL2TL: Selective Conformal Prediction with Semantic Verification for Natural Language to Temporal Logic Specifications
Aug 5arXiv ↗

June 2026

SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents
Jun 1Evaluation and benchmarksarXiv ↗

February 2026

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

December 2025

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