Kai Yuanqing Xiao

~Kai_Yuanqing_Xiao1

2

论文总数

2.0

年均投稿

4.8

平均评分

接收情况0/2

会议分布

ICLR

2

发表论文 (2 篇)

20252 篇

Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning

ICLR 2025Rejected

The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

ICLR 2025Rejected

合作者 (5)

Alex Beutel2 篇

Johannes Heidecke2 篇

Lilian Weng2 篇

Eric Wallace1 篇

Reimar Heinrich Leike1 篇