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
54.12/100
前 6.7%
全站排名 #4,343
发表论文8 篇
平均评分
年均产出2.7 篇/年
Qingming Li
研究方向
AI Security and Privacy · Federated Learning · Data Valuation · Preference Modeling · Personalized Ranking
23
STAR: Strategy-driven Automatic Jailbreak Red-teaming For Large Language Model
ICLR 2026Poster
二作26
From ``Sure" to ``Sorry": Detecting Jailbreak in Large Vision Language Model via JailNeurons
ICLR 2026Poster
二作24
Contextual and Seasonal LSTMs for Time Series Anomaly Detection
ICLR 2026Poster
二作12
HiddenGuard: Detecting and Interpreting NSFW Prompts in Text-to-Image Models through Uncovering Harmful Semantics
ICLR 2026Withdrawn
三作5
Trust the Process? Backdoor Attack against Vision–Language Models with Chain-of-Thought Reasoning
ICLR 2026Withdrawn