Xuankun Rong

PhD student, School of Computer Science, Wuhan University

Joined

July 2024

Names

Xuankun Rong (Preferred)

Emails

****@whu.edu.cn (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

PhD student

School of Computer Science, Wuhan University (whu.edu.cn)

2025 – Present

Undergrad student

School of Cyber Science and Engineering, Wuhan University (whu.edu.cn)

2021 – 2025

Advisors, Relations & Conflicts

PhD Advisor

Mang Ye

2024 – Present

Expertise

AI Safety

2024 – Present

Publications

SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
Xuankun Rong, Wenke Huang, Tingfeng Wang, Daiguo Zhou, Bo Du, Mang Ye
- 6thAdvML
- Readers: Everyone
MAPO: MIXED ADVANTAGE POLICY OPTIMIZATION
Wenke Huang, QUAN ZHANG, Yiyang Fang, Jian Liang, Xuankun Rong, Huanjin Yao, Guancheng Wan, KE LIANG, Wenwen He, JIAN LI, Leszek Rutkowski, Mang Ye, Bo Du, Dacheng Tao
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
MOTION: Multi-Sculpt Evolutionary Coarsening for Federated Continual Graph Learning
Guancheng Wan, Fengyuan Ran, Ruikang Zhang, Wenke Huang, Xuankun Rong, Guibin Zhang, Yuxin Wu, Bo Du, Mang Ye
- NeurIPS 2025 poster
- Readers: Everyone
Backdoor Cleaning without External Guidance in MLLM Fine-tuning
Xuankun Rong, Wenke Huang, Jian Liang, Jinhe Bi, Xun Xiao, Yiming Li, Bo Du, Mang Ye
- NeurIPS 2025 poster
- Readers: Everyone
Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model
Wenke Huang, Jian Liang, Xianda Guo, Yiyang Fang, Guancheng Wan, Xuankun Rong, Chi Wen, Zekun Shi, Qingyun Li, Didi Zhu, Yanbiao Ma, Ke Liang, Bin Yang, He Li, Jiawei Shao, Mang Ye, Bo Du
- CoRR 2025
- Readers: Everyone
A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
Mang Ye, Xuankun Rong, Wenke Huang, Bo Du, Nenghai Yu, Dacheng Tao
- CoRR 2025
- Readers: Everyone
CAN: Leveraging Clients As Navigators for Generative Replay in Federated Continual Learning
Xuankun Rong, Jianshu Zhang, Kun He, Mang Ye
- ICML 2025 poster
- Readers: Everyone

Co-Authors

View all 35 co-authors

Xuankun Rong

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

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

MAPO: MIXED ADVANTAGE POLICY OPTIMIZATION

MOTION: Multi-Sculpt Evolutionary Coarsening for Federated Continual Graph Learning

Backdoor Cleaning without External Guidance in MLLM Fine-tuning

Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations

CAN: Leveraging Clients As Navigators for Generative Replay in Federated Continual Learning

Co-Authors