影响力指数

1.39/100

超过 3.4%

全站排名 #62,202

发表论文2 篇

平均评分3.8

年均产出2.0 篇/年

Zhaoqian Dai

Researcher@Alibaba Group·中国·OpenReview

Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs

ICLR 2026Poster

HINT: Helping Ineffective Rollouts Navigate Towards Effectiveness

ICLR 2026Withdrawn

合作者 (9)