影响力指数

9.65/100

超过 30.1%

全站排名 #44,984

发表论文2 篇

平均评分6.0

年均产出1.0 篇/年

Kai Yang

Researcher@LLM Department·中国·OpenReview

研究方向

LLM · Reinforcement Learning

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners

ICLR 2026Poster

Exploration and Anti-Exploration with Distributional Random Network Distillation

ICLR 2024Rejected

合作者 (9)

博士导师1 篇