Ching-Chia Kao

~Ching-Chia_Kao1

2

论文总数

2.0

年均投稿

5.9

平均评分

接收情况1/2

会议分布

NeurIPS

1

ICLR

1

发表论文 (2 篇)

20252 篇

Safety Depth in Large Language Models: A Markov Chain Perspective

NeurIPS 2025Poster

Information-Theoretical Principled Trade-off between Jailbreakability and Stealthiness on Vision Language Models

ICLR 2025Rejected

合作者 (3)

Chia-Mu Yu2 篇

Chu-Song Chen2 篇

Chun-Shien Lu2 篇