影响力指数

28.78/100

前 25.8%

全站排名 #16,624

发表论文6 篇

平均评分4.2

年均产出2.0 篇/年

Stephen Hailes

Full Professor@University College London·英国·OpenReview

研究方向

IoT · Trust · Complex networks · Security

Opponent Shaping in LLM Agents

ICLR 2026Poster

Mutual Information Preserving Neural Network Pruning

ICLR 2026Rejected

A Generalized Information Bottleneck Theory of Deep Learning

ICLR 2026Desk Rejected

Moral Alignment for LLM Agents

ICLR 2025Poster

Mutual Information Preserving Neural Network Pruning

ICLR 2025Rejected

合作者 (5)

Charles Westphal

PhD Advisee3 篇

Victor-Alexandru Darvariu

PhD Advisee1 篇

Elizaveta Tennant

PhD Advisee1 篇

Marta Emili García Segura

PhD Advisee1 篇