Nathan Helm-Burger

~Nathan_Helm-Burger1

2

论文总数

2.0

年均投稿

7.8

平均评分

接收情况2/2

会议分布

NeurIPS

2

发表论文 (2 篇)

20252 篇

Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models

NeurIPS 2025Poster

CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring

NeurIPS 2025Poster

合作者 (14)

Benjamin Arnav1 篇

Hannes Whittingham1 篇

Mary Phuong1 篇

Pablo Bernabeu-Perez1 篇

Timothy Kostolansky1 篇

Cameron Tice1 篇

Clement Neo1 篇

Fabien Roger1 篇