Thomas Kwa

~Thomas_Kwa1

3

论文总数

1.5

年均投稿

6.8

平均评分

接收情况3/3

会议分布

NeurIPS

3

发表论文 (3 篇)

20251 篇

Measuring AI Ability to Complete Long Software Tasks

NeurIPS 2025Poster

20242 篇

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

NeurIPS 2024Poster

Compact Proofs of Model Performance via Mechanistic Interpretability

NeurIPS 2024Poster

合作者 (20)

Lawrence Chan2 篇

Alex Gibson1 篇

Chun Hei Yip1 篇

Jason Gross1 篇

Rajashree Agrawal1 篇

Soufiane Noubir1 篇