Cameron Tice

~Cameron_Tice1

2

论文总数

2.0

年均投稿

7.2

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

Large language models can learn and generalize steganographic chain-of-thought under process supervision

NeurIPS 2025Poster

合作者 (19)

Connor Watts1 篇

David Lindner1 篇

Edward James Young1 篇

Hannes Whittingham1 篇

Lorena Gonzalez-Manzano1 篇

Luis Ibanez-Lissen1 篇

Puria Radmard1 篇