AI safety researcher

Yi Zeng

Virginia Tech

Evaluation and benchmarks 2

Latest AI safety papers

On this site: 29 papers

September 2025

SpecEval: Evaluating Model Adherence to Behavior Specifications
Sep 2arXiv ↗

March 2025

AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
Mar 20arXiv ↗
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
Mar 19Evaluation and benchmarksarXiv ↗

November 2024

RedCode: Risky Code Execution and Generation Benchmark for Code Agents
Nov 12Evaluation and benchmarksarXiv ↗

July 2024

AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies
Jul 11arXiv ↗

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