影响力指数

37.53/100

前 16.3%

全站排名 #10,510

发表论文3 篇

平均评分6.2

年均产出3.0 篇/年

Christoph Dann

Research Scientist@Google·瑞士·OpenReview

研究方向

RLHF · Language model alignment · Reinforcement Learning

Principled Model Routing for Unknown Mixtures of Source Domains

NeurIPS 2025Poster

Design Considerations in Offline Preference-based RL

ICML 2025Poster

Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective

ICML 2025Poster

合作者 (7)

Teodor Vanislavov Marinov