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
67.49/100
前 3.1%
全站排名 #1,982
发表论文8 篇
平均评分
年均产出2.7 篇/年
Audrey Huang
研究方向
reinforcement learning · offline reinforcement learning · off-policy evaluation
20
Self-Improvement in Language Models: The Sharpening Mechanism
ICLR 2025Oral
一作5
Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
ICML 2025Poster
一作22
Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
ICLR 2025Spotlight
一作34
Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol
NeurIPS 2025Poster
13
Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol
ICML 2025Rejected