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
33.91/100
前 20.1%
全站排名 #12,938
发表论文5 篇
平均评分
年均产出1.7 篇/年
Vaidehi Patil
PhD student@Department of Computer Science, University of North Carolina at Chapel Hill·美国·OpenReview
研究方向
AI safety · security · privacy
27
The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
ICLR 2026Rejected
一作21
UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning
ICLR 2026Rejected
一作15
Self-Knowledge Without a Self? Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns
ICLR 2026Rejected
二作