paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

YD

Yinpeng Dong

ICLR 2026×4AAAI 2026×2安全社会与人本推理检索与知识多模态

新星分贡献者

63

一作贡献0

核心/参与30

方向广度13

合作网络12

0 一作 · 6 篇 · ICLR 2026 / AAAI 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

6

作者位次 #5/6ICLR 2026Poster· Optimization / Everything Else

Unveiling the Basin-Like Loss Landscape in Large Language Models

Huanran Chen · Zeming Wei · Yao Huang · Yichi Zhang · Yinpeng Dong · Jun Zhu

作者位次 #9/10ICLR 2026Poster· Social Aspects / Fairness, Equity, Justice and Safety

Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention

Yichi Zhang · Yue Ding · Jingwen Yang · Tianwei Luo · Dongbai Li · Ranjie Duan · Qiang Liu · Hang Su · Yinpeng Dong · Jun Zhu

社会与人本推理安全OpenReview

作者位次 #7/8ICLR 2026Poster

Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems

Yuhao Wang · Wenjie Qu · Shengfang Zhai · Yanze Jiang · Liu Zichen · Yue Liu · Yinpeng Dong · Jiaheng Zhang

检索与知识安全OpenReview

作者位次 #3/4ICLR 2026Poster· Social Aspects / Trustworthy Machine Learning

Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information

Yifan Zhu · Yibo Miao · Yinpeng Dong · XIAOSHAN GAO

安全社会与人本OpenReview

作者位次 #7/8AAAI 2026Poster· Artificial Intelligence

Any2Critical: Safety-Critical Scenario Generation from Arbitrary Real-World Driving Contexts

Yao Huang · Yubo Chen · Ruochen Zhang · Yitong Sun · Shouwei Ruan · Zhenyu Wu · Yinpeng Dong · Xingxing Wei

安全OpenReview

作者位次 #7/11AAAI 2026Poster· Artificial Intelligence

Benchmarking Trustworthiness in Multimodal LLMs for Video Understanding

Youze Wang · Zijun Chen · Ruoyu Chen · Shishen Gu · Wenbo Hu · Jiayang Liu · Yinpeng Dong · Hang Su · Jun Zhu · Meng Wang · Richang Hong

多模态评测与基准OpenReview

常见合作者

JZJun Zhu×3 YHYao Huang×2 YZYichi Zhang×2 HSHang Su×2 HCHuanran Chen ZWZeming Wei YDYue Ding JYJingwen Yang TLTianwei Luo DLDongbai Li RDRanjie Duan QLQiang Liu