影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
43.45/100
前 12%
全站排名 #7,719
发表论文7 篇
平均评分
年均产出3.5 篇/年
Minzhou Pan
研究方向
AI safety · Machine learning · Backdoor Attack
46
ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks
ICLR 2026Poster
24
Guarding a Needle in the Haystack: A Real-Time Policy-Following Streaming Video Guardrail
ICLR 2026Desk Rejected
6
SAFEVISION: Efficient Image Guardrail with Robust Policy Adherence and Explainability
ICLR 2026Rejected
二作15
AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories
ICLR 2025Spotlight
11
How to Evaluate and Mitigate IP Infringement in Visual Generative AI?
ICML 2025Poster
34
SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations
ICLR 2025Poster
三作20
SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability
ICLR 2025Rejected
二作