影响力指数

-/100

发表论文2 篇

平均评分4.7

年均产出1.0 篇/年

Jingwei Yi

Researcher@Beijing Academy of Artificial Intelligence (BAAI)·中国·OpenReview

研究方向

LLM Safety and Security · Federated Learning · Recommendation System

Elephant in the Room: Unveiling the Pitfalls of Human Proxies in Alignment

ICLR 2025Rejected

Open-Source Can Be Dangerous: On the Vulnerability of Value Alignment in Open-Source LLMs

ICLR 2024Rejected

合作者 (15)

博士导师2 篇

Bin Benjamin Zhu

博士导师1 篇