影响力指数

-/100

发表论文1 篇

平均评分4.0

年均产出1.0 篇/年

Seokil Ham

PhD student@KAIST·韩国·OpenReview

研究方向

Multimodal Large Language Model · Large Langugae Model · Diffusion Model

Safety-Aligned Weights Are Not Enough: Refusal-Teacher-Guided Finetuning Enhances Safety and Downstream Performance under Harmful Finetuning Attacks

ICLR 2026Withdrawn

合作者 (5)

博士导师1 篇