影响力指数

13.81/100

超过 42.4%

全站排名 #37,059

发表论文2 篇

平均评分5.8

年均产出2.0 篇/年

Cameron Holmes

Instructor@UK AI Security Institute·英国·OpenReview

研究方向

Mechanistic Interpretability · AI Alignment

Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences

ICLR 2026Poster

Real-Time Detection of Hallucinated Entities in Long-Form Generation

ICLR 2026Rejected

合作者 (10)

Helena Casademunt

Javier Ferrando