影响力指数

7.68/100

超过 24%

全站排名 #48,913

发表论文2 篇

平均评分4.8

年均产出1.0 篇/年

Yanrui Du

PhD student@Harbin Institute of Technology·OpenReview

研究方向

Robustness and interpretability of NLP models

Towards Secure Tuning: Mitigating Security Risks Arising from Benign Instruction Fine-Tuning

ICLR 2025Withdrawn

MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their Usability

NeurIPS 2024Poster

合作者 (11)

博士导师2 篇

博士导师2 篇