影响力指数

18.75/100

前 44.6%

全站排名 #28,707

发表论文5 篇

平均评分5.0

年均产出2.5 篇/年

Nina Panickssery

Researcher@Anthropic·英国·OpenReview

研究方向

Deep learning · Machine learning interpretability · Machine learning

Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs

ICLR 2026Rejected

Mechanistically Eliciting Latent Behaviors in Language Models

ICLR 2026Rejected

Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct

ICLR 2025Poster

Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models

ICLR 2025Rejected

(Pre-)training Dynamics: Scaling Generalization with First-Order Logic

ICLR 2025Withdrawn

合作者 (15)

Daanish Shabbir

Alexander Matt Turner

Andrew Eric Mack