影响力指数

17.02/100

前 48.9%

全站排名 #31,500

发表论文3 篇

平均评分4.7

年均产出1.5 篇/年

Yulan Hu

Researcher@Alibaba Group·中国·OpenReview

研究方向

NLP · LLM RLHF · LLM Reasoning · Graph Learning

Learn More with Less: Uncertainty Consistency Guided Query Selection for RLVR

ICLR 2026Poster

Learning to Reward: A Contextual Bandit Framework for Distributional Reward Policy Optimization

ICLR 2026Rejected

Recipes for Unbiased Reward Modeling Learning: An Empirically Study

ICLR 2025Withdrawn

合作者 (11)

博士导师3 篇