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
34.19/100
前 19.8%
全站排名 #12,740
发表论文4 篇
平均评分
年均产出4.0 篇/年
Chhavi Yadav
研究方向
Interpretability · Deep Learning · Auditing · Zero knowledge proofs (ZKPs) for Machine Learning · AI Safety & Security · Trustworthy ML
18
Can We Infer Confidential Properties of Training Data from LLMs?
NeurIPS 2025Spotlight
二作15
Evaluating Deep Unlearning in Large Language Models
ICLR 2025Rejected
二作15
ExpProof : Operationalizing Explanations for Confidential Models with ZKPs
ICML 2025Poster
一作28
Influence-based Attributions can be Manipulated
ICLR 2025Rejected
一作