paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

YZ

Yechao Zhang

AAAI 2026×2ICML 2026×2CCS 2026安全理论与学习动力学多模态智能体与工具对齐与偏好

新星分贡献者

66

一作贡献0

核心/参与31

方向广度16

合作网络12

0 一作 · 5 篇 · AAAI 2026 / ICML 2026 / CCS 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

5

作者位次 #5/12ICML 2026Poster· Theory / Optimization

PASO: Step Parallel Stochastic Optimization

Jianrong Lu · Zhuoya Gu · Haobo Li · Zhiyu Zhu · Yechao Zhang · Jianhai Chen · Minghui Yang · Junwei Liu · Jian Wang · Qinming He · Hui LIU · Junhui Hou

理论与学习动力学OpenReview

作者位次 #2/5ICML 2026Poster· Applications / Computer Vision

VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority

Chenhao Qiu · Yechao Zhang · Xin Luo · Shien Song · Xusheng Liu

多模态智能体与工具对齐与偏好OpenReview

作者位次 #5/9AAAI 2026Poster· Artificial Intelligence

Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure

Lulu Xue · Shengshan Hu · Linqiang Qian · Peijin Guo · Yechao Zhang · Minghui Li · Yanjun Zhang · Dayong Ye · Leo Yu Zhang

安全效率与系统OpenReview

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

MHB: Medical Hallucination Benchmark for Large Language Models in Complex Clinical Tasks

Jianrong Lu · Junwei Liu · Xingyun Zheng · Minghui Yang · Jian Wang · Ping Wang · Yechao Zhang

社会与人本安全评测与基准OpenReview

作者位次 #3/8CCS 2026Oral· Computer & Communications Security

ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models

Xiaogeng Liu · Xinyan Wang · Yechao Zhang · Sanjay Kariyappa · Chong Xiang · Muhao Chen · G. Edward Suh · Chaowei Xiao

推理安全OpenReview

常见合作者

JLJianrong Lu×2 MYMinghui Yang×2 JLJunwei Liu×2 ZGZhuoya Gu HLHaobo Li ZZZhiyu Zhu JCJianhai Chen JWJian Wang QHQinming He HLHui LIU JHJunhui Hou CQChenhao Qiu