Stephen Casper

~Stephen_Casper1

2

论文总数

1.0

年均投稿

5.0

平均评分

接收情况0/2

会议分布

ICLR

2

发表论文 (2 篇)

20251 篇

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

ICLR 2025Rejected

20241 篇

Explore, Establish, Exploit: Red Teaming Language Models from Scratch

ICLR 2024Rejected

合作者 (13)

Dylan Hadfield-Menell2 篇

Abhay Sheshadri1 篇

Aengus Lynch1 篇

Aidan Ewart1 篇

Asa Cooper Stickland1 篇

Ethan Perez1 篇

Henry Sleight1 篇