paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
JY

Jeongho Yoon

ACL 2026×2CVPR 2026效率与系统多模态数据与预训练社会与人本对齐与偏好
新星分新星
69
一作贡献30
核心/参与19
方向广度13
合作网络3
1 一作 · 3 篇 · ACL 2026 / CVPR 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

3
一作ACL 2026Poster· Natural Language Processing

Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation

Jeongho Yoon · Chanhee Park · Yongchan Chun · Hyeonseok Moon · Heuiseok Lim

摘要

Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substantial privacy risks, as unauthorized access may expose personal, medical, or legal information. Although prior defenses strived to mitigate these ri...

效率与系统社会与人本对齐与偏好OpenReview 项目页
作者位次 #2/4ACL 2026Poster· Natural Language Processing

L ang SAE Editing: Improving Multilingual Information Retrieval via Post-hoc Language Identity Removal

Dongjun Kim · Jeongho Yoon · Chanjun Park · Heuiseok Lim

摘要

Dense retrieval in multilingual settings often searches over mixed-language collections, yet multilingual embeddings encode language identity alongside semantics. This language signal can inflate similarity for same-language pairs and crowd out relevant evidence written in other languages. We pro...

可解释性检索与知识效率与系统OpenReview 项目页

常见合作者