I am an Assistant Professor at the Department of Computer Science, City University of Hong Kong since January 2024. I received my Ph.D. and M.Phil degree from School of Computer Science, University of Sydney, supervised by Dr. Chang Xu. Before that, I received my BS degrees in Software Engineering and Information Technology from both Dalian University of Technology and University of Sydney. My research interests include trustworthy machine learning algorithms and their related applications in computer vision. Currently, my research focuses on: adversarial robustness, model calibration, efficient neural network, neural architecture search, generative model, and human motion analytics.
📯 Opening
I am looking for self-motivated MPhil/PhD students enrolled in the year of 2027. If you are interested in trustworthy machine learning research, computer vision, generative models, adversarial robustness, model calibration, or efficient neural networks, feel free to send me an email (dong_serj[AT]hotmail[dot]com), with your CV, transcript, and publication. Successful PhD applicants will enroll in 2027 with scholarship.
📝 Publications
PA-Attack: Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes and Attention
Hefei Mei, Zirui Wang, Chang Xu, Jianyuan Guo, Minjing Dong†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM Perception
Yuheng Shi, Xiaohuan Pei, Minjing Dong, Chang Xu
International Conference on Learning Representations (ICLR), 2026
VEattack: Downstream-agnostic vision encoder attack against large vision language models
Hefei Mei, Zirui Wang, Shen You, Minjing Dong†, Chang Xu
International Conference on Learning Representations (ICLR), 2026
Diversifying Counterattacks: Orthogonal Exploration for Robust CLlP Inference
Chengze Jiang, Minjing Dong, Xinli Shi, Jie Gui
AAAI Conference on Artificial Intelligence (AAAI), 2026
Rethinking Frequency Modeling: Tail-Aware Dynamic Adversarial Training for Long-Tailed Robustness
Chengze Jiang, Minjing Dong, Zhuangzhuang Wang, Jie Gui, Ju Jia, Yuan Yan Tang, James Tin-Yau Kwok
IEEE Transactions on Information Forensics and Security (TIFS), 2026
Efficient Rectified Flow for Image Fusion
Zirui Wang, Jiayi Zhang, Tianwei Guan, Yuhan Zhou, Xingyuan Li, Minjing Dong, Jinyuan Liu
Conference on Neural Information Processing Systems (NeurIPS), 2025
Improving fast adversarial training paradigm: An example taxonomy perspective
Jie Gui, Chengze Jiang, Minjing Dong, Kun Tong, Xinli Shi, Yuan Yan Tang, Dacheng Tao
IEEE Transactions on Dependable and Secure Computing (TDSC), 2025
Gradient Perturbation Guidance for Boosting Sparse Adversarial Attack Transferability
Chengze Jiang, Zhuangzhuang Wang, Minjing Dong, Jie Gui, Lu Dong, Yuan Yan Tang, James Tin-Yau Kwok
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025
Exploring the Coordination of Frequency and Attention in Masked Image Modeling
Jie Gui, Tuo Chen, Minjing Dong, Zhengqi Liu, Hao Luo, James Tin-Yau Kwok, Yuan Yan Tang
IEEE Transactions on Image Processing (TIP), 2025
Yu-Xin Zhang, Jie Gui, Minjing Dong, Xiaofeng Cong, Yu Cao, Xin Gong, Yuan Yan Tang, James Tin-Yau Kwok
IEEE Transactions on Information Forensics and Security (TIFS), 2025
Improving Fast Adversarial Training via Self-Knowledge Guidance
Chengze Jiang, Junkai Wang, Minjing Dong, Jie Gui, Xinli Shi, Yuan Cao, Yuan Yan Tang, James Tin-Yau Kwok
IEEE Transactions on Information Forensics and Security (TIFS), 2025
Backdooring Self-Supervised Contrastive Learning by Noisy Alignment
Tuo Chen, Jie Gui, Minjing Dong, Ju Jia, Lanting Fang, Jian Liu
International Conference on Computer Vision (ICCV), 2025
VSSD: Vision Mamba with Non-Causal State Space Duality
Yuheng Shi, Minjing Dong, Chang Xu
International Conference on Computer Vision (ICCV), 2025
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation
Yuheng Shi, Minjing Dong, Chang Xu
International Conference on Computer Vision (ICCV), 2025
Adversarial Robustness via Deformable Convolution with Stochasticity
Yanxiang Ma, Zixuan Huang, Minjing Dong, Shan You, Chang Xu
International Conference on Machine Learning (ICML), 2025
Beyond One-Hot Labels: Semantic Mixing for Model Calibration
Haoyang Luo, Linwei Tao, Minjing Dong†, Chang Xu
International Conference on Machine Learning (ICML), 2025
Uncertainty Weighted Gradients for Model Calibration
Jinxu Lin, Linwei Tao, Minjing Dong, Chang Xu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Model
Jinxu Lin, Linwei Tao, Minjing Dong, Chang Xu
International Conference on Learning Representations (ICLR), 2025
Feature Clipping for Uncertainty Calibration
Linwei Tao, Minjing Dong, Chang Xu
AAAI Conference on Artificial Intelligence (AAAI), 2025
Efficient Image-to-Image Diffusion Classifier for Adversarial Robustness
Hefei Mei, Minjing Dong†, Chang Xu
AAAI Conference on Artificial Intelligence (AAAI), 2025
Adversarially Robust Neural Architectures
Minjing Dong, Yanxi Li, Yunhe Wang, Chang Xu
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model
Yuheng Shi, Minjing Dong, Chang Xu
Conference on Neural Information Processing Systems (NeurIPS), 2024
Imitation Learning from Purified Demonstrations
Yunke Wang, Minjing Dong, Yukun Zhao, Bo Du, Chang Xu
International Conference on Machine Learning (ICML), 2024
Random Entangled Tokens for Adversarially Robust Vision Transformer
Huihui Gong, Minjing Dong, Siqi Ma, Seyit Camtepe, Surya Nepal, Chang Xu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
A Benchmark Study on Calibration
Linwei Tao, Younan Zhu, Haolan Guo, Minjing Dong, Chang Xu
International Conference on Learning Representations (ICLR), 2024
Xiaohuan Pei, Yanxi Li, Minjing Dong, Chang Xu
International Conference on Learning Representations (ICLR), 2024
AMD: Autoregressive Motion Diffusion
Bo Han, Hao Peng, Minjing Dong, Chang Xu, Yi Ren, Yixuan Shen, Yuheng Li
AAAI Conference on Artificial Intelligence (AAAI), 2024
Stealthy Physical Masked Face Recognition Attack via Adversarial Style Optimization
Huihui Gong, Minjing Dong, Siqi Ma, Seyit Camtepe, Surya Nepal, Chang Xu
IEEE Transactions on Multimedia, 2023
Adversarial Robustness through Random Weight Sampling
Yanxiang Ma, Minjing Dong, Chang Xu
Conference on Neural Information Processing Systems (NeurIPS), 2023
Improving Lightweight AdderNet via Distillation from ℓ2 to ℓ1-Norm
Minjing Dong, Xinghao Chen, Yunhe Wang, Chang Xu
IEEE Transactions on Image Processing, 2023
Neural architecture search for wide spectrum adversarial robustness
Zhi Cheng, Yanxi Li, Minjing Dong, Xiu Su, Shan You, Chang Xu
AAAI Conference on Artificial Intelligence (AAAI), 2023
Boosting semi-supervised semantic segmentation with probabilistic representations
Haoyu Xie, Changqi Wang, Mingkai Zheng, Minjing Dong, Shan You, Chong Fu, Chang Xu
AAAI Conference on Artificial Intelligence (AAAI), 2023
Dual Focal Loss for Calibration
Linwei Tao *, Minjing Dong *, Chang Xu
International Conference on Machine Learning (ICML), 2023
Adversarial Robustness via Random Projection Filters
Minjing Dong, Chang Xu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Calibrating a Deep Neural Network with Its Predecessors
Linwei Tao, Minjing Dong, Daochang Liu, Changming Sun, Chang Xu
International Joint Conference on Artificial Intelligence (IJCAI), 2023
Random normalization aggregation for adversarial defense
Minjing Dong, Xinghao Chen, Yunhe Wang, Chang Xu
Conference on Neural Information Processing Systems (NeurIPS), 2022
Neural architecture search via proxy validation
Yanxi Li, Minjing Dong, Yunhe Wang, Chang Xu
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022
Spatial-channel token distillation for vision mlps
Yanxi Li, Xinghao Chen, Minjing Dong, Yehui Tang, Yunhe Wang, Chang Xu
International Conference on Machine Learning (ICML), 2022
Skeleton-based human motion prediction with privileged supervision
Minjing Dong, Chang Xu
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022
An empirical study of adder neural networks for object detection
Xinghao Chen, Chang Xu, Minjing Dong, Chunjing Xu, Yunhe Wang
Conference on Neural Information Processing Systems (NeurIPS), 2021
Handling long-tailed feature distribution in addernets
Minjing Dong, Yunhe Wang, Xinghao Chen, Chang Xu
Conference on Neural Information Processing Systems (NeurIPS), 2021
Towards stable and robust addernets
Minjing Dong, Yunhe Wang, Xinghao Chen, Chang Xu
Conference on Neural Information Processing Systems (NeurIPS), 2021
Neural architecture search in a proxy validation loss landscape
Yanxi Li, Minjing Dong, Yunhe Wang, Chang Xu
International Conference on Machine Learning (ICML), 2020
Adversarial recurrent time series imputation
Shuo Yang, Minjing Dong, Yunhe Wang, Chang Xu
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020
Crafting Efficient Neural Graph of Large Entropy
Minjing Dong, Hanting Chen, Yunhe Wang, Chang Xu
International Joint Conference on Artificial Intelligence (IJCAI), 2019
On Retrospecting Human Dynamics with Attention
Minjing Dong, Chang Xu
International Joint Conference on Artificial Intelligence (IJCAI), 2019
🏆 Awards
- 2025, CORE Award for Australasian Distinguished Doctoral Dissertation Commendation, 2025
- 2024, Best PhD Thesis Award, University of Sydney
- 2023, AAAI-23 Distinguished Paper Award (12/8777)
- 2020, Faculty of Engineering Research Scholarship, University of Sydney
📖 Teaching
- 2025-2026, Lecturer, CS2468: Data Structures and Data Management, City University of Hong Kong
- 2024-2026, Lecturer, CS1302: Introduction to Computer Programming, City University of Hong Kong
- 2023, Guest Lecturer, HTIN5005: Applied Healthcare Data Science, University of Sydney
- 2023, Guest Lecturer, COMP5329: Deep Learning, University of Sydney
- 2019, Teaching Assistant, COMP5329: Deep Learning, University of Sydney
💗 Services
- 2026, Area Chair of ICLR 2026
- 2026, Area Chair of ICML 2026
- 2025, Area Chair of NeurIPS 2025
- 2025, Area Chair of ICML 2025
- 2025, Organizer of Workshop “The Workshop on Sustainable AI for the Future Web”, WWW 2025
- 2024, Area Chair of NeurIPS 2024
- 2024, Organizer of Tutorial “Efficient_and_Secure_Foundation_Models”, IJCNN 2024
- 2022-2023, Event Co-organizer of Coding Fest, University of Sydney
- 2022, Event Co-organizer of DICTA 2022 Workshop
- PC member of CVPR, ICML, AAAI, NeurIPS, ACMMM, ICLR, ICCV, ICDM, WCCI, WACV, KDD
- Reviewer of Knowledge-based Systems, IEEE Transactions on Multimedia, Neurocomputing, Pattern Recognition, Transactions on Machine Learning Research
💬 Experience
- 2020.07-2021.12, Research Intern in Noah’s Ark Lab
- 2019.03-2019.12, Research Associate in University of Sydney
-
Last Update: Apr 27, 2026