影响力指数

12.63/100

超过 39.1%

全站排名 #39,225

发表论文2 篇

平均评分6.1

年均产出1.0 篇/年

Raja Mehta Moreno

Researcher@MATS Research·美国·OpenReview

研究方向

AI control

How does information access affect LLM monitors' ability to detect sabotage?

ICLR 2026Rejected

CTRL-ALT-DECEIT Sabotage Evaluations for Automated AI R&D

NeurIPS 2025Spotlight

合作者 (11)

Francis Rhys Ward

Rohan Subramani

Shubhorup Biswas