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

Chanyoung Park

ICLR 2026×3KDD 2026×3AAAI 2026ACL 2026IROS 2026智能体与工具检索与知识推理强化学习与后训练可解释性
新星分资深
47
一作贡献30
核心/参与22
方向广度19
合作网络12
1 一作 · 9 篇 · ICLR 2026 / KDD 2026 / AAAI 2026 / ACL 2026 / IROS 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

9
作者位次 #4/4ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs

Jiwan Kim · Kibum Kim · Sangwoo Seo · Chanyoung Park

多模态推理强化学习与后训练OpenReview
作者位次 #4/4ACL 2026Poster· Natural Language Processing

Reasoning Structure Matters for Safety Alignment of Reasoning Models

Yeonjun In · Wonjoong Kim · Sangwu Park · Chanyoung Park

摘要

Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks but often generate harmful responses to malicious user queries. This paper investigates the underlying cause of these safety risks and shows that the issue lies in the reasoning structure itself. Based on this ins...

强化学习与后训练安全推理OpenReview 项目页
一作IROS 2026Poster· Learned Reasoning and Dynamics Models in Robotics

Distilling Collaborative Dynamics into Latent Space for Implicit Coordination in Decentralized Multi-Agent Manipulation

Chanyoung Park · Minsung Yoon · Andrew Jeong · Sung-eui Yoon

智能体与工具推理强化学习与后训练Multi-Robot SystemsMachine Learning for Robot ControlDeep Learning MethodsOpenReview

常见合作者