Hao Yang

~Hao_Yang26

2

论文总数

2.0

年均投稿

4.6

平均评分

接收情况1/2

会议分布

ICLR

1

COLM

1

发表论文 (2 篇)

20252 篇

Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models

ICLR 2025withdrawn

Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models in Multi-turn Interactions

COLM 2025Poster

合作者 (3)

Ehsan Shareghi2 篇

Gholamreza Haffari2 篇