Drake Thomas

~Drake_Thomas1

1

论文总数

1.0

年均投稿

6.3

平均评分

接收情况1/1

会议分布

NeurIPS

1

发表论文 (1 篇)

20241 篇

Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification

NeurIPS 2024Poster

合作者 (2)

Adrià Garriga-Alonso1 篇

Thomas Kwa1 篇