Long Tan Le
Ph.D. · Research Data Scientist
Research data scientist with expertise in computer science, machine learning, data mining, and multimodal analytics. I develop resource-efficient, interpretable, and personalised AI frameworks for human-centred and data-intensive environments, with experience building end-to-end data and machine-learning pipelines.
Education
PhD in Computer Science
The University of Sydney
BEng in Computer Engineering (Honours)
HCMUT
Experience
Research Data Scientist
Intersect Australia
Member of the Advanced Analytics & AI (3AI) team, applying data mining, machine learning, and statistical methods to cross-disciplinary projects and developing end-to-end analytical workflows.
Graduate Research and Teaching Assistant
Faculty of Engineering, The University of Sydney
Research and teaching across AI, machine learning, generative AI, data mining, distributed systems, anomaly detection, time-series forecasting, and multimodal data analysis.
Research Engineer
Faculty of Computer Science and Engineering, HCMUT
Research and development in cloud and edge computing, IoT, data mining, network anomaly detection, and environmental sensing systems.
Selected publications
Distributionally Robust Wireless Semantic Communication With Large AI Models. IEEE Journal on Selected Areas in Communications, 2026.
Federated Koopman-Reservoir Learning for Large-Scale Multivariate Time-Series Anomaly Detection. SIAM SDM, 2025.
Federated Deep Equilibrium Learning: Harnessing Compact Global Representations to Enhance Personalization. ACM CIKM, 2024.
Federated PCA on Grassmann Manifold for IoT Anomaly Detection. IEEE/ACM Transactions on Networking, 2024.
Federated PCA on Grassmann Manifold for Anomaly Detection in IoT Networks. IEEE INFOCOM, 2023.
View complete publication record →