影响力指数

24.63/100

前 31.9%

全站排名 #20,535

发表论文2 篇

平均评分6.5

年均产出1.0 篇/年

Caleb Biddulph

Researcher@Google·美国·OpenReview

研究方向

artificial intelligence · AI alignment · AI safety

Breaking Barriers: Do Reinforcement Post Training Gains Transfer To Unseen Domains?

ICLR 2026Poster

MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking

ICML 2025Poster

合作者 (12)

Sebastian Farquhar

Antony Kellermann