Author

Leitao Yuan

Observed name: Yuan, Leitao

Institutions: Shanghai Artificial Intelligence Laboratory, Zhejiang University

Observed institutions: Shanghai Artificial Intelligence Laboratory, Zhejiang University

OpenAlex ID: A5123962030

Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs

2026 · Yuan, Leitao, Mao, Qinghua, et al. · arXiv (Cornell University) · 1

SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment

2026 · Mao, Qinghua, Qu, Wanying, et al. · arXiv (Cornell University)

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents

2026 · Qu, Wanying, Mao, Qinghua, et al. · arXiv (Cornell University)

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

2026 · Zhou, Tianyi, Liu, Dongrui, et al. · arXiv (Cornell University)

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

2026 · Liu, Dongrui, Li, Yu, et al. · arXiv (Cornell University)

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

2026 · Liu, Dongrui, Ren, Qihan, et al. · arXiv (Cornell University)

Works count: 6

Citation count: 1

H-index: 1

I10-index: