Yufan Kang is a Research Fellow at Monash University whose work sits at the intersection of trustworthy AI, spatio-temporal modelling, and AI planning. Her research investigates how intelligent systems make decisions over time and space, with an emphasis on robustness, long-term impact, and responsible deployment.

She completed her PhD in Computer Science at RMIT University, where she studied spatial-temporal resource allocation under dynamic and uncertain environments. Her work develops principled learning and optimisation frameworks that integrate predictive modelling with sequential decision-making, enabling AI systems to operate reliably in real-world settings.

In trustworthy AI, she examines the reliability, accountability, and societal implications of automated decision systems. In spatio-temporal modelling, she designs models that capture complex dependencies across space and time for forecasting and allocation tasks. In AI planning, she focuses on reinforcement learning and optimisation methods for large-scale, dynamic decision problems, including routing, allocation, and ranking systems.

Her research has been published in leading venues such as ICLR, KDD, IJCAI, ICDM, ECML PKDD, SIGSPATIAL, and GECCO. She is also a member of the Australian Research Council (ARC) Centre of Excellence for Automated Decision-Making and Society (ADM+S), contributing to interdisciplinary research on the societal implications of automated decision systems.

Her overarching goal is to build AI systems that are technically principled, operationally robust, and aligned with long-term societal values.

Selected Publications

• Keqing Du, Yufan Kang, Xinyu Yang, and Wei Shao. (2026). ST-HHOL: Spatio-Temporal Hierarchical Hypergraph Online Learning for Crime Prediction. In International Conference on Learning Representations (ICLR).
• Yufan Kang, Jie Zhang, Wei Shao, Rui Tang, Mark Andrejevic, Jeffrey Chan, and Flora D. Salim. (2025). Dynamic Budgeted Reinforcement Learning for Fairness in Spatial-Temporal Resource Allocation. In ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL).
• Yufan Kang, Jeffrey Chan, Wei Shao, Flora D. Salim, and Christopher Leckie. (2024). Long-term Fairness in Ride-Hailing Platform. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), pp. 223–239. Springer.
• Wei Shao*, Yufan Kang*, Ziyan Peng, Xiao Xiao, Lei Wang, Yuhui Yang, and Flora D. Salim. (2024). STEMO: Early Spatio-temporal Forecasting with Multi-Objective Reinforcement Learning. In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). (* indicates equal contribution)
• Yufan Kang, Rongsheng Zhang, Wei Shao, Flora Salim, and Jeffrey Chan. (2024). Promoting Two-sided Fairness in Dynamic Vehicle Routing Problems. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), pp. 759–767.
• Wei Shao*, Ziyan Peng*, Yufan Kang*, Xiao Xiao, and Zhiling Jin. (2023). Early Spatiotemporal Event Prediction via Adaptive Controller and Spatiotemporal Embedding. In IEEE International Conference on Data Mining (ICDM). (* indicates equal contribution)
• Yufan Kang, Mohammad Saiedur Rahaman, Yongli Ren, Mark Sanderson, Ryen W. White, and Flora D. Salim. (2022). App Usage on-the-Move: Context- and Commute-Aware Next App Prediction. In Pervasive and Mobile Computing, 87, 101704.