影响力指数

39.73/100

前 14.6%

全站排名 #9,395

发表论文4 篇

平均评分5.1

年均产出2.0 篇/年

Sangyeon Yoon

Graduate Student@Yonsei University·韩国·OpenReview

研究方向

Large Language Models

A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models

ICLR 2026Poster

Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures

ICLR 2026Poster

DUSK: Do Not Unlearn Shared Knowledge

ICLR 2026Withdrawn

SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment

NeurIPS 2025Poster

合作者 (10)

博士导师4 篇