paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

XR

Xuankun Rong

AAAI 2026×2NeurIPS 2026×2CVPR 2026安全多模态社会与人本对齐与偏好可解释性

新星分新星

87

一作贡献70

核心/参与15

方向广度16

合作网络12

2 一作 · 5 篇 · AAAI 2026 / NeurIPS 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

5

作者位次 #6/9NeurIPS 2026Poster· Social Aspects / Trustworthy Machine Learning

Consistency-Verified Backdoor Defense for Federated Graph Learning via Cross-Layer Drift

Yanwen Jia · Yinuo Zhang · Zitong Shi · Yuxin Wu · Zihan Tan · Xuankun Rong · Liangtao Zheng · Wenke Huang · Mang Ye

安全社会与人本OpenReview

作者位次 #6/9NeurIPS 2026Poster· Deep Learning / Graph Neural Networks

E²Gen: Evidential Energy-Based Generation for Fair Federated Graph Learning

Jingbo Wang · Zitong Shi · Yuxin Wu · Zihan Tan · Qiqi Lin · Xuankun Rong · Liangtao Zheng · Wenke Huang · Mang Ye

一作CVPR 2026Poster· Computer Vision & Pattern Recognition

SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization

Xuankun Rong · Wenke Huang · Tingfeng Wang · Daiguo Zhou · Bo Du · Mang Ye

多模态对齐与偏好安全OpenReview 项目页

作者位次 #3/7AAAI 2026Poster· Artificial Intelligence

PurMM: Attention-Guided Test-Time Backdoor Purification in Multimodal Large Language Models

Wenzheng Jiang · Ke Liang · Xuankun Rong · Jingxuan Zhou · Zhengyi Zhong · Guancheng Wan · Ji Wang

安全多模态OpenReview

一作AAAI 2026Poster· Artificial Intelligence

Probing Semantic Insensitivity for Inference-Time Backdoor Defense in Multimodal Large Language Model

Xuankun Rong · Wenke Huang · Wenzheng Jiang · Yiming Li · Wenxuan Wang · Mang Ye

安全可解释性多模态OpenReview

常见合作者

ZSZitong Shi×2 YWYuxin Wu×2 ZTZihan Tan×2 LZLiangtao Zheng×2 WHWenke Huang×2 MYMang Ye×2 WHWenke Huang×2 MYMang Ye×2 WJWenzheng Jiang×2 YJYanwen Jia YZYinuo Zhang JWJingbo Wang