影响力指数

-/100

发表论文1 篇

平均评分4.0

年均产出1.0 篇/年

Baohua Zhang

Postdoc@Beijing Institute of Technology·中国·OpenReview

研究方向

large language models · psychology models · NLP · multi-lingual · deep learning

RLPIR: Reinforcement Learning with Prefix and Intrinsic Reward

ICLR 2026Rejected

合作者 (9)