About
Appointed Canada CIFAR AI Chair – 2026
Xingyu’s research lies at the intersection of deep learning, computer vision, and data mining, focusing on building reliable and safe intelligent systems in open and changing environments. Her research examines how a learning system can recognize the limits of its own knowledge and avoid making confident errors in unfamiliar situations. She develops learning methods that enable models not only to “see” but also to detect novel or unfamiliar situations, trigger timely alerts, and adapt their behavior accordingly. This research supports the safe deployment of AI in real-world applications, including anomaly detection, medical imaging, autonomous driving, and embodied AI. In addition to her theoretical contributions to machine learning, she is strongly motivated to translate AI advances into impactful healthcare innovations.
Awards
- Early-Career Research Award, Faculty of Engineering, University of Alberta (2025)
- Best Reproducible Paper Runner-Up, MICCAI workshop on Simulation and Synthesis in Medical Imaging (SASHIMI) (2023)
- Vector Postgraduate Affiliate, The Vector Institute (2019)
- Multiple top-3 finishes in international competitions/challenges (e.g. RoboSense 2025, VAND 2024, MOOD 2021, AutoImplant 2021, etc.)
Relevant Publications
- Deng, H., & Li, X. (2022). "Anomaly Detection via Reverse Distillation from One-Class Embedding." in proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9737-9746.
- Hou, P., Han, J., & Li, X. (2023). "Improving Adversarial Robustness with Self-Paced Hard-Class Pair Reweighting." in Proc. AAAI Conference on Artificial Intelligence (AAAI), pp. 14883 - 14891.
- Martell, M., Haven, N., McAlister, E., Restall, B., Cikaluk, B., Mittal, R., Adam, B., Giannakopoulos, N., Peiris, L., Silverman, S., Deschenes, J., Li, X., & Zemp, R. (2023). “Deep learning-enabled realistic virtual histology with ultraviolet photoacoustic remote sensing microscopy.” Nature Communications, no. 5967.
- Ou, Y., Soleymani, A., Li. X., & Tavakoli, M. (2024). “Autonomous Blood Suction for Robot-Assisted Surgery: A Sim-to-Real Approach Using Reinforcement Learning." IEEE Robotics and Automation Letters (RAL), Vol. 9, No. 8, pp. 7246-7253.
- Li, S., Ma, L., & Li, X. (2024). “Domain Generalization of 3D Object Detection by Density-Resampling.” in Proc. European Conference on Computer Vision (ECCV), pp. 456–473.