AI safety researcher

Yi Zeng

Chinese Academy of Sciences

dblp ORCID Homepage

Last 12 months11 papers

Evaluation and benchmarks 3Defenses 1

AI safety papers from the last year

On this site: 28 papers

August 2026

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety
Aug 13DefensesarXiv ↗
When Truth Is Distributed: Misinformation Derails Collective Fact Recovery in LLM-Based Multi-Agent Systems
Aug 4Evaluation and benchmarksarXiv ↗

June 2026

ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models
Jun 25Evaluation and benchmarksarXiv ↗
SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety
Jun 17Evaluation and benchmarksarXiv ↗
CogManip: Benchmarking Manipulative Behavior in Multi-Turn Interactions with Large Language Model
Jun 4arXiv ↗

February 2026

December 2025

Towards Reliable Evaluation of Adversarial Robustness for Spiking Neural Networks
Dec 27arXiv ↗

November 2025

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