影响力指数

36.69/100

前 17.1%

全站排名 #11,017

发表论文3 篇

平均评分5.5

年均产出1.5 篇/年

Anna Soligo

PhD student@Imperial College London·英国·OpenReview

研究方向

reinforcement learning · interpretability · explainability

Emergent Misalignment is Easy, Narrow Misalignment is Hard

ICLR 2026Poster

Interactions between crosscoder features: a compact proofs perspective

ICLR 2026Rejected

Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning

ICML 2025Poster

合作者 (11)

Dmitry Manning-Coe

Oliver Clive-Griffin

Rajashree Agrawal

博士导师1 篇

博士导师1 篇