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
36.37/100
前 17.4%
全站排名 #11,222
发表论文7 篇
平均评分
年均产出3.5 篇/年
Yanai Elazar
研究方向
NLP · Explainability · Interpretation · Commonsense Reasoning · Analysis · Causal Inference · Interpretability · Data Attribution
22
On Linear Representations and Pretraining Data Frequency in Language Models
ICLR 2025Poster
通讯27
GRADE: Quantifying Sample Diversity in Text-to-Image Models
ICLR 2025Rejected
20
How Many Van Goghs Does It Take to Van Gogh? Finding the Imitation Threshold
ICLR 2025Rejected
通讯22
Generalization v.s. Memorization: Tracing Language Models’ Capabilities Back to Pretraining Data
ICLR 2025Poster
三作10
Leveraging Set Assumption for Membership Inference in Language Models
ICLR 2025Rejected
12
Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback
ICLR 2025Rejected
三作