Qing-Shan Jia

~Qing-Shan_Jia1

3

论文总数

1.5

年均投稿

6.2

平均评分

接收情况3/3

会议分布

ICLR

1

NeurIPS

1

ICML

1

发表论文 (3 篇)

20252 篇

STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning

NeurIPS 2025Poster

CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries

ICML 2025Poster

20241 篇

Query-Policy Misalignment in Preference-Based Reinforcement Learning

ICLR 2024Spotlight

合作者 (9)

Yiqin Yang2 篇

Jianxiong Li1 篇

Xianyuan Zhan1 篇

Ya-Qin Zhang1 篇