Hi, I am Ziquan Liu, a Lecturer (Assistant Professor) at the School of Electronic Engineering and Computer Science, Queen Mary University of London. I am affiliated with the Centre for Multimodal AI and the Computer Vision group, and an academic fellow at the Digital Environment Research Institute. My research interest is machine learning, including trustworthy and reliable machine learning, uncertainty of foundation models and interpretable machine learning. I worked as a postdoc research fellow in machine learning in Information, Inference and Machine Learning group at University College London from April to December of 2023. I spent five wonderful years at City University of Hong Kong in Video, Image, and Sound Analysis Lab as a PhD student under the supervision of Prof. Antoni B. Chan, and got my PhD in 2023. I obtained my Bachelor of Engineering in Information Engineering from Beihang University and secondary Bachelor of Science in Mathematics from the same university, both in 2017.
Email: ziquanliu.cs@gmail.com
Address: Peter Landin Building, 4th Floor, Queen Mary University of London, London, United Kingdom
[May 3, 2024]
Check our work on improving conformal prediction efficiency under adversarial environment.
[March 26, 2023]
Our code for TWINS is released, check it out!
[December 31, 2022]
Our code for Improved Fine-Tuning by Better Leveraging Pre-Training Data is released, check it out!
[November 22, 2022]
Our code for Boosting Adversarial Robustness From The Perspective of Effective Margin Regularization is released, check it out!
Seminar at Samsung AI Center Cambridge, 15 May 2024
Digital Environment Research Institute Seminar, 2 May 2024
Workshop on Trustworthy Multimodal Learning with Foundation Models: Bridging the Gap between AI Research and Real World Applications, supported by BMVA, 24 April 2024
Workshop on Responsible Data Science and AI Research, supported by Software Sustainability Institute, DERI and Queen Mary's School of Business and Management, 21 March 2024
January 2024 - Now, Lecturer in Computer Science @ Queen Mary University of London
April 2023 - December 2023, Research Fellow in Machine Learning @ University College London
July 2021 - May 2022, Research Intern @ Alibaba DAMO Academy
September 2017 - January 2023, Ph.D. @ City University of Hong Kong
September 2013 - June 2017, B.Sc. in Mathematics @ Beihang University
September 2013 - June 2017, B.Eng. in Information Engineering @ Beihang University
Zengqun Zhao, Ziquan Liu, Yu Cao, Shaogang Gong, Ioannis Patras, "AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 [code]
Zhuo Zhi, Yuxuan Sun, Qiangqiang Wu, Ziquan Liu, Miguel R. D. Rodrigues, "Wasserstein Modality Alignment Makes Your Multimodal Transformer More Robust", Transactions on Machine Learning Research (TMLR), 2025
Adarsh Kappiyath, Abhra Chaudhuri, Ajay Kumar Jaiswal, Ziquan Liu, Yunpeng Li, Xiatian Zhu, Lu Yin, "SEBRA: Debiasing through Self-Guided Bias Ranking", International Conference on Learning Representations (ICLR), 2025 [code]
Norah Alballa, Wenxuan Zhang, Ziquan Liu, Ahmed M. Abdelmoniem, Mohamed Elhoseiny, Marco Canini, "Query-based Knowledge Transfer for Heterogeneous Learning Environments", International Conference on Learning Representations (ICLR), 2025
Chen Feng, Ziquan Liu, Zhuo Zhi, Ilija Bogunovic, Carsten Gerner-Beuerle, Miguel R.D. Rodrigues, "PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks", The 39th Annual AAAI Conference on Artificial Intelligence (AAAI), 2025 (Oral Presentation)
Zhaohan Zhang, Ziquan Liu, Ioannis Patras, "Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization", International Conference on Computational Linguistics (COLING), 2025 (Oral Presentation)
Reem Masoud, Ziquan Liu, Martin Ferianc, Philip Colin Treleaven and Miguel R. D. Rodrigues, "Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions", International Conference on Computational Linguistics (COLING), 2025 [code]
Feiyu Chen, Wei Lin, Ziquan Liu, Antoni B. Chan, "A Secure Image Watermarking Framework with Statistical Guarantees via Adversarial Attacks on Secret Key Networks", European Conference on Computer Vision (ECCV), 2024
Zhuo Zhi, Ziquan Liu, Moe Elbadawi, Adam Daneshmend, Mine Orlu, Abdul W Basit, Andreas Demosthenous, Miguel R. D. Rodrigues, "Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcity", ICML 2024 Trustworthy Multi-modal Foundation Models and AI Agents (TiFA) Workshop, 2024
Ziquan Liu, Yufei Cui, Yan Yan, Yi Xu, Xiangyang Ji, Xue Liu, Antoni B. Chan, "The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks", International Conference on Machine Learning (ICML), 2024 [code]
Yufei Cui, Ziquan Liu, Yixin Chen, Yuchen Lu, Xinyue Yu, Xue Liu, Tei-Wei Kuo, Miguel R.D. Rodrigues, Chun Jason Xue, and Antoni B. Chan, "Retrieval-Augmented Multiple Instance Learning", Neural Information Processing Systems (NeurIPS), 2023 [code]
Ziquan Liu, Yi Xu, Xiangyang Ji, Antoni B. Chan, "TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 [code]
Qiangqiang Wu, Tianyu Yang, Ziquan Liu, Baoyuan Wu, Ying Shan, Antoni B. Chan, "DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 [code]
Yufei Cui, Ziquan Liu, Xiangyu Liu, Xue Liu, Cong Wang, Tei-Wei Kuo, Chun Jason Xue, Antoni B. Chan, "Bayes-MIL: A New Probabilistic Perspective on Attention-based Multiple Instance Learning for Whole Slide Images", International Conference on Learning Representations (ICLR), 2023 [code]
Yufei Cui, Yu Mao, Ziquan Liu, Qiao Li, Antoni B. Chan, Xue Liu, Tei-Wei Kuo, Chun Jason Xue, "Variational Nested Dropout", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023 [code]
Ziquan Liu, Yi Xu, Yuanhong Xu, Qi Qian, Hao Li, Xiangyang Ji, Antoni B. Chan, Rong Jin, "Improved Fine-Tuning by Better Leveraging Pre-Training Data", Neural Information Processing Systems (NeurIPS), 2022 (Spotlight Presentation) [code]
Ziquan Liu, Yi Xu, Yuanhong Xu, Qi Qian, Hao Li, Rong Jin, Xiangyang Ji, Antoni B. Chan, "An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation", NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications, 2022
Ziquan Liu and Antoni B. Chan, "Boosting Adversarial Robustness From The Perspective of Effective Margin Regularization", British Machine Vision Conference (BMVC), 2022 [code]
Ziquan Liu, Lei Yu, Janet H. Hsiao and Antoni B. Chan, "PRIMAL-GMM: PaRametrIc MAnifold Learning of Gaussian Mixture Models", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 [code]
Ziquan Liu, Yufei Cui, Antoni B. Chan, "Improve Generalization and Robustness of Neural Networks via Weight Scale Shifting Invariant Regularizations", ICML Workshop on Adversarial Machine Learning, 2021
Jia Wan, Ziquan Liu, and Antoni B. Chan, "A Generalized Loss Function for Crowd Counting and Localization", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 [code]
Yufei Cui, Ziquan Liu, Qiao Li, Yu Mao, Antoni B. Chan, Chun Jason Xue, "Bayesian Nested Neural Networks for Uncertainty Calibration and Adaptive Compression", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 [code]
Hui Lan, Ziquan Liu, Janet H. Hsiao, Dan Yu, Antoni B. Chan, "Clustering Hidden Markov Models with Variational Bayesian Hierarchical EM", IEEE Transactions on Neural Networks and Learning Systems, 2021
Yufei Cui, Ziquan Liu, Wuguanguan Yao, Qiao Li, Antoni B. Chan, Tei-Wei Kuo, Chun Jason Xue. "Fully Nested Neural Network for Adaptive Compression and Quantization", Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI), 2020
Ziquan Liu, Lei Yu, Janet H. Hsiao and Antoni B. Chan. "Parametric Manifold Learning of Gaussian Mixture Models", Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI), 3073-3079, 2019 [code]
I am fortunate to work with the following talented PhD students:
Zixu Cheng @ QMUL with Prof. Shaogang Gong
Yu Cao @ QMUL with Prof. Shaogang Gong
Zhaohan Zhang @ QMUL with Prof. Ioannis Patras
Zengqun Zhao @ QMUL with Prof. Ioannis Patras
Tatiana Gaintseva @ QMUL with Prof. Greg Slabaugh
Zhuo Zhi @ UCL with Prof. Miguel Rodrigues
Feiyu Chen @ CityUHK with Prof. Antoni B. Chan
Lecturer at Queen Mary University of London
ECS797U/ECS797P - Machine Learning for Visual Data Analysis - 2023/24
ECS7020P - Principles of Machine Learning - 2024/25
Teaching Assistant at City University of Hong Kong:
CS1103 - Introduction to Media Computing - 2017/2018
GE2326 - Probability in Action - 2017/2018
CS5188 - Virtual Reality Technologies and Applications - 2018/2019
CS4185 - Multimedia Technologies and Applications - 2018/2019
CS5489 - Machine Learning: Algorithms and Applications - 2019/2020, 2020/2021
CS5486 - Intelligent Systems - 2019/2020, 2020/2021
Reviewer:
Conference: NeurIPS 2021-2025, ICLR 2021-2025, ICML 2021-2025, AAAI 2021-2025, CVPR 2021-2025, ICCV 2021-2025, ECCV 2022-2024
Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence, Transactions on Machine Learning Research, International Journal of Computer Vision
Grant: Engineering and Physical Sciences Research Council (EPSRC) of UKRI
Service Award:
Outstanding Reviewer: NeurIPS 2021