About me

I am currently a Postdoctoral Research Fellow at Hong Kong Baptist University (HKBU). I received my Ph.D. in Software Engineering from the South China University of Technology (SCUT), advised by Prof. Mingkui Tan and co-supervised by Dr. Feng Liu and Prof. Bo Han. I hold a Bachelor’s degree in Mathematics from the School of Mathematics, South China University of Technology. My research focuses on AI-generated content detection, adversarial defense, and efficient large-scale model learning and acceleration, with publications in leading conferences and journals including NeurIPS, ICML, ICLR, CVPR, ICCV, IJCAI, TPAMI, TIP, Neural Networks and TCSVT. I also actively serve as a reviewer for leading conferences (NeurIPS, ICML, ICLR, ACMMM) and journals (TPAMI, TNNLS, Neural Networks).

🔥 News

• 2026.09: 🎉 🎉 One survey paper is accepted by MIR 2026.
• 2026.08:  🎉🎉 One paper is accepted by TPAMI 2026.
• 2026.05:  🎉🎉 One paper is accepted by ICML 2026.
• 2025.09:  🎉🎉 One paper is accepted by NeurIPS 2025 Spotlight.
• 2025.06:  🎉🎉 One paper is accepted by TIP 2025.
• 2025.05:  🎉🎉 Three papers are accepted by ICML 2025.
• 2025.05:  🎉🎉 One papers is accepted by IJCAI 2025.
• 2025.01:  🎉🎉 One papers is accepted by ICLR 2025.

📝 Publications * indicates co-first author

• A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference. Shuaicheng Niu, Guohao Chen, Yaofo Chen, Zhiquan Wen, Jinwu Hu, Zeshuai Deng, Deyu Chen, Shuhai Zhang, Renjie Chen, Zihao Lian, Shoukai Xu, Gang Dai, Yunbei Zhang, Wei Luo, Yifan Zhang, Mingkui Tan, Cheng Deng. MIR 2026
• Adversarial Purification by Consistency-aware Latent Space Optimization on Data Manifolds. Shuhai Zhang, Jiahao Yang, Hui Luo, Jincheng Chen, Lei Wang, Feng Liu, Bo Han, Mingkui Tan. TPAMI 2026
• Zero-source LLM Hallucination Detection with Human-like Criteria Probing. Jiahao Yang, Shuhai Zhang^*, Haokun Kang, Feng Liu, Qian Chen, Mingkui Tan. ICML 2026
• Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection. Shuhai Zhang, ZiHao Lian, Jiahao Yang, Daiyuan Li, Guoxuan Pang, Feng Liu, Bo Han, Shutao Li, Mingkui Tan. NeurIPS 2025 Spotlight
• Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment. Kai Zhou, Shuhai Zhang^*, Zeng You, Jinwu Hu, Mingkui Tan. TIP 2025
• Curse of High Dimensionality Issue in Transformer for Long-context Modeling. Shuhai Zhang, Zeng You, Yaofo Chen, Zhiquan Wen, Qianyue Wang, Zhijie Qiu, Yuanqing Li, Mingkui Tan. ICML 2025
• Core Context Aware Attention for Long Context Language Modeling. Yaofo Chen, Zeng You, Shuhai Zhang^*, Haokun Li, Yirui Li, Yaowei Wang, Mingkui Tan. ICML 2025
• Deep Electromagnetic Structure Design Under Limited Evaluation Budgets. Shijian Zheng, Fangxiao Jin, Shuhai Zhang, Quan Xue, Mingkui Tan. ICML 2025
• Dynamic Ensemble Reasoning for LLM Experts. Jinwu Hu, Yufeng Wang, Shuhai Zhang^*, Kai Zhou, Guohao Chen, Yu Hu, Bin Xiao, Mingkui Tan. IJCAI 2025
• Deep Kernel Relative Test for Machine-generated Text Detection. Yiliao Song, Zhenqiao Yuan, Shuhai Zhang, Zhen Fang, Jun Yu, Feng Liu. ICLR 2025
• Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy. Shuhai Zhang, Yiliao Song, Jiahao Yang, Yuanqing Li, Bo Han, Mingkui Tan. ICLR 2024
• Cross-Device Collaborative Test-Time Adaptation Guohao Chen, Shuaicheng Niu, Deyu Chen, Shuhai Zhang, Changsheng Li, Yuanqing Li, Mingkui Tan. NeurIPS 2024
• HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models Yifan Yang, Dong Liu, Shuhai Zhang, Zeshuai Deng, Zixiong Huang, Mingkui Tan. CVPR 2024
• Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score. Shuhai Zhang, Feng Liu, Jiahao Yang, Yifan Yang, Changsheng Li, Bo Han, Mingkui Tan. ICML 2023
• Cross-ray neural radiance fields for novel-view synthesis from unconstrained image collections Yifan Yang, Shuhai Zhang, Zixiong Huang, Yubing Zhang, Mingkui Tan. ICCV 2023 Oral
• Learning to Generate Diverse Data From a Temporal Perspective for Data-Free Quantization Hui Luo, Shuhai Zhang, Zhuangwei Zhuang, Jiajie Mai, Mingkui Tan, Jianlin Zhang. TCSVT 2024
• Generative data free model quantization with knowledge matching for classification Shoukai Xu, Shuhai Zhang^*, Jing Liu, Bohan Zhuang, Yaowei Wang, Mingkui Tan. TCSVT 2023
• Learning defense transformations for counterattacking adversarial examples Jincheng Li, Shuhai Zhang^*, Jiezhang Cao, Mingkui Tan. Neural Networks 2023

💼 Experience

• 2026 - now, Postdoctoral Research Fellow, Hong Kong Baptist University, Hong Kong.

📖 Education

• 2020.06 - 2026, Ph.D. in Software Engineering, South China University of Technology, Guangzhou.
• 2016.09 - 2020.06, B.Sc. in Mathematics, South China University of Technology, Guangzhou.

💬 Invited Talks

• 2023.11, A Special Topic on Trustworthy Machine Learning for Incomplete Data | [video]