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
53.2/100
前 7%
全站排名 #4,534
发表论文8 篇
平均评分
年均产出4.0 篇/年
Sicheng Zhu
研究方向
machine learning; generalization; out-of-domain generalization; adversarial robustness; interpretability; invariance;
21
AutoDAN: Automatic and Interpretable Adversarial Attacks on Large Language Models
ICLR 2024Rejected
一作12
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models
COLM 2024Poster
一作15
Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds
ICLR 2024Poster
三作13
Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models
COLM 2024Poster
二作19
PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts
ICLR 2024Poster
二作26
On the Possibilities of AI-Generated Text Detection: A Sample Complexity Analysis
ICLR 2024Rejected
三作