Tongliang Liu

Prior to joiing MBZUAI, Professor Liu was ranked among the Best Rising Stars of Science in Australia by Research.com in 2022; he was ranked among the Global Top Young Chinese Scholars in AI by Baidu Scholar in 2022; he was named in the Early Achievers Leaderboard by The Australian in 2020. Professor Liu He is also the director of Sydney AI Centre and a senior lecturer at University of Sydney, Australia; a visiting professor of University of Science and Technology of China, Hefei, China; and a visiting scientist of RIKEN AIP, Tokyo, Japan.

Professor Liu works as a Future Fellow of the Australian Research Council (ARC). He has been widely recognised by his research. His research interests lie in providing mathematical and theoretical foundations to justify and understand (deep) machine learning models and designing efficient learning algorithms for problems in computer vision and data mining, with a particular emphasis on:

• Learning with noisy labels.
• Deep adversarial learning.
• Causal representation learning.
• Deep transfer learning.
• Deep unsupervised learning.
• Statistical deep learning theory.

He is the Action Editor of Transactions on Machine Learning Research, Associate Editor of ACM Computing Surveys, and in the Editorial Board of Journal of Machine Learning Research and the Machine Learning journal.

• Ph.D. in machine learning from University of Technology Sydney, Australia
• Bachelor in engineering from University of Science and Technology of China, China

• 2022, Future Fellowship - Australian Research Council (ARC)
• 2022, Faculty Award - OPPO
• 2022, Best Paper Honorable Mention Award- IEEE MMSP
• 2022, Best Paper Award - ACM Mobiarch
• 2022, Meituan Faculty Research Award for Collaboration Exploration
• 2022, Global Top Young Chinese Scholars in AI – Baidu Scholar 2022
• 2021, Early Career Research Excellence – Faculty of Engineering, University of Sydney
• 2021, Best VisNotes Paper Award – IEEE PacificVis
• 2021, Best Workshop Paper Runner-up Award – Masked Face Recognition Challenge and Workshop, CVPR
• 2021, Quantification of Uncertainties in Biomedical Image Quantification Challenge Award (2nd place) – MICCAI
• 2021, Bioengineering and Digital Science Catalyst Award – Cardiovascular Initiative
• 2020, Early Career Researcher Award Honourable Mention – Australian Pattern Recognition Society (APRS)
• 2020, Named in the Early Achievers Leadboard (five across Australia in Engineering and Computer Sciences) - The Australian
• 2019, Best Paper Award - IEEE International Conference on Multimedia and Expo (ICME)
• 2019, J G Russell Award Shortlisted - Australian Academy of Science (AAS)
• 2019, Discovery Early Career Research Award (DECRA) Fellowship - Australian Research Council (ARC)
• 2017, Distinguished Paper Candidate - International Joint Conference on Artificial Intelligence (IJCAI)
• 2016, IEEE Transactions on Cybernetics Outstanding Reviewer Award- IEEE
• 2014, Best Paper Award - IEEE International Conference on Information Science and Tech (ICIST)
• 2014, Computational Statistics and Data Analysis Outstanding Reviewer Award - ELSEVIER

Lui has previously been the senior meta-reviewer of AAAI and IJCAI and is regularly the meta-reviewer of ICML, NeurIPS, ICLR, AAAI, and IJCAI.

• Classification with Noisy Labels by Importance Reweighting. T. Liu and D. Tao. IEEE T-PAMI, 38(3): 447-461, 2016.
• Algorithmic Stability and Hypothesis Complexity. T. Liu, G. Lugosi, G. Neu and D. Tao. In ICML , 2017.
• Modeling Adversarial Noise for Adversarial Defense. D. Zhou, N. Wang, B. Han, and T. Liu. In ICML, 2022.
• Part-dependent Label Noise: Towards Instance-dependent Label Noise. [Spotlight] X. Xia, T. Liu, B. Han, N. Wang, M. Gong, H. Liu, G. Niu, D. Tao, and M. Sugiyama. In NeurIPS, 2020.
• Domain Adaptation with Conditional Transferable Components. M. Gong, K. Zhang, T. Liu, D. Tao, C. Glymour, and B. Schölkopf. In ICML, 2016.
• Instance-Dependent Label-Noise Learning under Structural Causal Models. Y. Yao, T. Liu, M. Gong, B. Han, G. Niu, and K. Zhang. In NeurIPS, 2021.