影响力指数

-/100

发表论文2 篇

平均评分4.8

年均产出1.0 篇/年

Raymond Douglas

Researcher@ACS Research·捷克·OpenReview

AI Models Can Provably Hide Arbitrary Capabilities

ICLR 2026Withdrawn

Mitigating the Influence of Distractor Tasks in LMs with Prior-Aware Decoding

ICLR 2025Rejected

合作者 (4)

Tomáš Gavenčiak

Christian Schroeder de Witt

Sumeet Ramesh Motwani