影响力指数

-/100

发表论文2 篇

平均评分3.3

年均产出1.0 篇/年

Yeonjea Kim

PhD student@Korea Advanced Institute of Science & Technology·韩国·OpenReview

研究方向

AI Safety · Trustworthy AI · LLM · Interpretability · Explainability

Distributed Knowledge Storage Hypothesis: Evidence from Generalization Failure in Knowledge Editing

ICLR 2026Rejected

Measuring Effects of Steered Representation in Large Language Models

ICLR 2025Withdrawn

合作者 (6)

博士导师2 篇

Cheongwoong Kang