Stefan Heimersheim

~Stefan_Heimersheim1

2

论文总数

2.0

年均投稿

6.0

平均评分

接收情况1/2

会议分布

ICML

1

ICLR

1

发表论文 (2 篇)

20252 篇

Detecting Strategic Deception with Linear Probes

ICML 2025Poster

Evaluating Synthetic Activations composed of SAE Latents in GPT-2

ICLR 2025desk_rejected

合作者 (7)

Bilal Chughtai1 篇

Marius Hobbhahn1 篇

Nicholas Goldowsky-Dill1 篇

Chatrik Singh Mangat1 篇

Giorgi Giglemiani1 篇

Jett Janiak1 篇

Nora Petrova1 篇