About me

I am Daizong Liu (刘岱宗), a Tenure-track Assistant Professor (Ph.D. Supervisor) in the Institute for Math & AI at Wuhan University (WHU). Prior to joining WHU, I obtained my Ph.D. degree at Wangxuan Institute of Computer Technology of Peking University (PKU) in 2025, supervised by Prof. Wei Hu. I was the recipient of the 2025 Outstanding Doctoral Dissertation Award in PKU. I was also selected as one of the World’s Top 2% Scientists by Stanford University and Elsevier in 2025.

My broad research interests include Multimodal Reasoning, 3D Point Cloud Perception, Adversarial Robustness, and Large Vision-Language Models. I have published several papers in top conferences such as NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, ACL, EMNLP, AAAI, ACM MM, SIGIR, IJCAI and top journals including TPAMI, TIFS, TDSC and TMM. Below are some of my recent research topics:

• Multi-modality (e.g., vision, point cloud and language) learning
• Computer vision (video analysis, action recognition, 3-D scene understanding, etc)
• AI security (Adversarial robustness, backdoor attack)

We are always actively recruiting interns and prospective graduate students! Welcome to contact me (daizongliu@whu.edu.cn) with your detailed CV! （招收27级硕士博士生！每年在武汉大学计算机学院有1个学博名额，2个学硕名额；在湖北应用数学中心有2个专硕名额。欢迎邮件联系！）

Latest News

• [2026/10] One paper is accepted by TPAMI!
• [2026/09] Three papers are accepted by NeurIPS 2026!
• [2026/08] I will serve as an Area Chair for ICLR 2027!
• [2026/07] I will serve as an Area Chair for AAAI 2027!
• [2026/07] One paper is accepted by TMM!
• [2026/06] Two papers are accepted by ECCV 2026!
• [2026/05] One paper is accepted by TDSC!
• [2026/05] Two papers are accepted by ICML 2026!
• [2026/04] One paper is accepted by ACL 2026!
• [2026/03] I will serve as an Area Chair for NeurIPS 2026!
• [2026/02] One paper is accepted by TIFS!
• [2026/02] Two papers are accepted by CVPR 2026!
• [2026/01] I will serve as an SPC for IJCAI 2026!
• [2025/12] One paper is accepted by TMM!
• [2025/11] Three papers are accepted by AAAI 2026!
• [2025/09] Two papers are accepted by NeurIPS 2025!
• [2025/09] I will serve as an Area Chair for ICLR 2026!
• [2025/07] Two papers are accepted by ACMMM 2025!
• [2025/06] One paper is accepted by ICCV 2025!
• [2025/03] One paper is accepted by CVPR 2025!

Representative Works

• Imperceptible Transfer Attack and Defense on 3D Point Cloud Classification.
  Daizong Liu, Wei Hu.
  IEEE Transactions on Pattern Analysis and Machine Intelligence, [TPAMI]
• Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing.
  Daizong Liu, Wei Hu, Xin Li.
  IEEE Transactions on Pattern Analysis and Machine Intelligence, [TPAMI]
• Flexible Targeted Adversarial Alignment with Frequency-based Visual Focus for Attacking Large Vision-Language Models.
  Daizong Liu, Tianyao Luo, Junhao Dong, Xiaowen Cai, Hao He, Weidong Wang, Runwei Guan, Jianfeng Dong, Pan Zhou, Bo Du, Hui Xiong.
  IEEE Transactions on Pattern Analysis and Machine Intelligence, [TPAMI]
• Are Large Vision-Language Models Robust to Adversarial Visual Transformations?.
  Daizong Liu, Xiaowen Cai, Pan Zhou, Xiaoye Qu, Lichao Sun, Wei Hu.
  IEEE Transactions on Information Forensics & Security, [TIFS]
• Hard-Label Black-Box Attacks on 3D Point Clouds.
  Daizong Liu, Yunbo Tao, Junhao Dong, Keke Tang, Pan Zhou, Wei Hu, Yew-Soon Ong.
  IEEE Transactions on Dependable and Secure Computing, [TDSC]
• Context-aware Biaffine Localizing Network for Temporal Sentence Grounding.
  Daizong Liu, Xiaoye Qu, Jianfeng Dong, Pan Zhou, Yu Cheng, Wei Wei, Zichuan Xu, Yulai Xie.
  IEEE Conference on Computer Vision and Pattern Recognition, [CVPR2021]
• Seeing is Not Believing: Adversarial Natural Object Optimization for Hard-Label 3D Scene Attacks.
  Daizong Liu, Wei Hu.
  IEEE Conference on Computer Vision and Pattern Recognition, [CVPR2025]
• Pandora’s Box: Towards Building Universal Attackers against Real-World Large Vision-Language Models.
  Daizong Liu, Mingyu Yang, Xiaoye Qu, Pan Zhou, Xiang Fang, Keke Tang, Yao Wan, Lichao Sun.
  The Thirty-eighth Annual Conference on Neural Information Processing Systems, [NeurIPS2024]
• Fit the Distribution: Cross-Image/Prompt Adversarial Attacks on Multimodal Large Language Models.
  Hai Yan, Haijian Ma, Xiaowen Cai, Daizong Liu#, Zenghui Yuan, Xiaoye Qu, Jianfeng Dong, Runwei Guan, Xiang Fang, Hongyang He, Yulai Xie, Pan Zhou.
  The Thirty-ninth Annual Conference on Neural Information Processing Systems, [NeurIPS2025]
• Attacking Gray-Box Large Vision-Language Models with Adaptive SVD-Structured Adversarial Alignment.
  Daizong Liu, Xiaowen Cai, Junhao Dong, Zhongliang Guo, Xiaoye Qu, Runwei Guan, Xiang Fang, Dengpan Ye.
  The Forty-Third International Conference on Machine Learning, [ICML2026]