Alexander Panfilov

~Alexander_Panfilov1

3

论文总数

1.5

年均投稿

5.7

平均评分

接收情况2/3

会议分布

ICLR

2

ICML

1

发表论文 (3 篇)

20252 篇

A Realistic Threat Model for Large Language Model Jailbreaks

ICLR 2025Rejected

An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks

ICML 2025Poster

20241 篇

Provable Compositional Generalization for Object-Centric Learning

合作者 (9)

Jonas Geiping2 篇

Matthias Hein2 篇

Vaclav Voracek2 篇

Valentyn Boreiko2 篇

Attila Juhos1 篇

Jack Brady1 篇

Matthias Bethge1 篇

Thaddäus Wiedemer1 篇