Laurent Charlin
About
Appointed Canada CIFAR AI Chair – 2019
Renewed Canada CIFAR AI Chair – 2024
Laurent Charlin is a Canada CIFAR AI Chair at Mila, an associate professor in the Department of Decision Sciences at HEC Montréal, and an adjunct professor at the Department of Computer Science and Operations Research (DIRO) at the University of Montreal.
Charlin’s research focuses on developing novel machine-learning models to aid in decision-making. His recent work focuses on continual learning and applications in recommender systems, optimization, and civil engineering. He has a number of highly cited publications in dialogue systems. He co-developed the Toronto Paper Matching System (TPMS) to recommend and match papers to reviewers. It was adopted by more than 100 conferences over the last ten years.
Awards
- Google Focused Research Award, 2017
- Ray Reiter Graduate Award, University of Toronto, 2012
- Doctoral Completion Award, University of Toronto, 2012
- Alexander Graham Bell Canada Graduate Scholarships, 2009-2011
- Ontario Graduate Scholarship in Science and Technology (OGSST), 2008-2009
Relevant Publications
- Ostapenko, O., Lesort, T., Rodriguez, P., Arefin, M.R., Douillard, A., Rish, I. & Charlin, L.. (2022). Continual Learning with Foundation Models: An Empirical Study of Latent Replay. in Proceedings of Machine Learning Research 199:60-91.
- Paulus, MB, Zarpellon, G., Krause, A., Charlin, L., Maddison, C. Learning to cut by looking ahead: Cutting plane selection via imitation learning In Proceeding of International conference on machine learning, 17584-17600
- Ostapenko, O., Rodriguez, P., Caccia, M., Charlin L. (2021). Continual learning via local module composition. In Advances in Neural Information Processing Systems. 34:30298-30312.
St-Hilaire, F., Burns, N., Belfer, R., Shayan, M., Smofsky, A., Do Vu, D., … & Kochmar, E. (2021). A Comparative Study of Learning Outcomes for Online Learning Platforms. In International Conference on Artificial Intelligence in Education (pp. 331-337). Springer, Cham.
Devailly, F. X., Larocque, D., & Charlin, L. (2021). Ig-rl: Inductive graph reinforcement learning for massive-scale traffic signal control. IEEE Transactions on Intelligent Transportation Systems.