影响力指数

28.03/100

前 26.8%

全站排名 #17,246

发表论文4 篇

平均评分4.4

年均产出1.3 篇/年

Xiaomeng Hu

PhD student@The Chinese University of Hong Kong·中国香港·OpenReview

研究方向

Large Language Models · Reinforcement Learning

ReAlign: Safety-Aligning Reasoning Models with Verifier-Guided Reinforcement Learning

ICLR 2026Rejected

Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs

ICLR 2026Rejected

CARE: Decoding-Time Safety Alignment via Rollback and Introspection Intervention

NeurIPS 2025Poster

合作者 (5)

博士导师4 篇