影响力指数

33.8/100

前 20.2%

全站排名 #13,021

发表论文7 篇

平均评分4.8

年均产出2.3 篇/年

Rongyi Zhu

PhD student@Stony Brook University, State University of New York at Stony Brook·美国·OpenReview

研究方向

Machine Interpretability · Trustworthy Machine Learning

Self-Destructive Language Models

ICLR 2026Poster

Self-Improving Model Steering

ICLR 2026Rejected

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models

ICLR 2026Withdrawn

Safeguarding Vision-Language Models via Dynamic Token Reweighting

ICLR 2026Withdrawn

Steering Protein Language Models

ICML 2025Poster

Is Forward Gradient an Effective Tool for Explaining Black-box Models?

ICLR 2025Rejected

合作者 (15)

博士导师4 篇