影响力指数

28.98/100

前 25.6%

全站排名 #16,491

发表论文3 篇

平均评分6.1

年均产出1.5 篇/年

Robert McCarthy

PhD student@University College London, University of London·英国·OpenReview

研究方向

LLM Safety & Alignment · Robot Learning

Early Signs of Steganographic Capabilities in Frontier LLMs

ICLR 2026Poster

Large language models can learn and generalize steganographic chain-of-thought under process supervision

NeurIPS 2025Poster

Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs

ICLR 2025Rejected

合作者 (19)

Edward James Young

Hannes Whittingham

Lorena Gonzalez-Manzano

Luis Ibanez-Lissen