paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

LW

Lanjun Wang

AAAI 2026×3CCS 2026CVPR 2026ICLR 2026多模态安全智能体与工具强化学习与后训练推理

新星分贡献者

72

一作贡献0

核心/参与43

方向广度19

合作网络9

0 一作 · 6 篇 · AAAI 2026 / CCS 2026 / CVPR 2026 / ICLR 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· Computer Vision / Vision Models & Multimodal

Thinking as Society: Multi-Social-Agent Self-Distillation for Multimodal Misinformation Detection

Yifei Gao · Ning Xu · Wenhui Li · Hongshuo Tian · Lanjun Wang · Anan Liu

多模态智能体与工具强化学习与后训练OpenReview

作者位次 #5/9CVPR 2026Poster· Computer Vision & Pattern Recognition

Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers

Ruidong Chen · Yancheng Bai · Xuanpu Zhang · Jianhao Zeng · Lanjun Wang · Dan Song · Lei Sun · Xiangxiang Chu · Anan Liu

多模态OpenReview 项目页

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

Key Decision-Makers in Multi-Agent Debates: Who Holds the Power?

Qian Zhang · Jinyi Liu · YAN ZHENG · Hebin Liang · Lanjun Wang

智能体与工具OpenReview

作者位次 #2/6AAAI 2026Poster· Artificial Intelligence

Reason2Attack: Jailbreaking Text-to-Image Models via LLM Reasoning

Chenyu Zhang · Lanjun Wang · Yiwen Ma · Wenhui Li · Guoqing Jin · Anan Liu

安全推理多模态OpenReview

作者位次 #3/6AAAI 2026Poster· Artificial Intelligence

T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model

Chenyu Zhang · Tairen Zhang · Lanjun Wang · Ruidong Chen · Wenhui Li · Anan Liu

安全评测与基准多模态OpenReview

作者位次 #2/6CCS 2026Oral· Computer & Communications Security

What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers

Chenyu Zhang · Lanjun Wang · Yueyang Cheng · Ruidong Chen · Wenhui Li · An-an Liu

安全OpenReview

常见合作者

ALAnan Liu×4 RCRuidong Chen×3 CZChenyu Zhang×3 WLWenhui Li×2 WLWenhui Li×2 YGYifei Gao NXNing Xu HTHongshuo Tian YBYancheng Bai XZXuanpu Zhang JZJianhao Zeng DSDan Song