影响力指数

34.07/100

前 19.9%

全站排名 #12,833

发表论文3 篇

平均评分5.9

年均产出1.5 篇/年

Seungju Cho

Researcher@Samsung·韩国·OpenReview

研究方向

adversarial attack · computer vision

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

ICLR 2026Withdrawn

Long-tailed Adversarial Training with Self-Distillation

ICLR 2025Poster

Indirect Gradient Matching for Adversarial Robust Distillation

ICLR 2025Poster

合作者 (6)

博士导师3 篇