影响力指数

34.02/100

前 20%

全站排名 #12,862

发表论文4 篇

平均评分5.6

年均产出1.3 篇/年

Weidi Luo

PhD student@University of Georgia·美国·OpenReview

研究方向

AI Safety · Trustworthy AI

Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models

ICLR 2026Poster

Computer-Use Agent Frameworks Can Expose Realistic Risks Through Tactics, Techniques, and Procedures

ICLR 2026Rejected

Prompt Injection Benchmark for Foundation Model Integrated Systems

ICLR 2025Rejected

合作者 (20)

博士导师4 篇

博士导师2 篇