Quentin Bertrand
Appointment
CIFAR Global Scholars 2026-2028
Learning in Machines & Brains
About
Quentin Bertrand currently works on generative models and multi-agent learning. More broadly, Bertrand studies how learning algorithms can leverage and interact with synthetic data from deep generative models.
Relevant Publications
- Bertrand, Q., Gagneux, A., Massias, M., & Emonet, R. (2025). On the closed-form of flow matching: Generalization does not arise from target stochasticity. NeurIPS 2025 (Oral)
- Bertrand, Q., Bose, A. J., Duplessis, A., Jiralerspong, M., & Gidel, G. (2024). On the stability of iterative retraining of generative models on their own data. ICLR 2024 (Spotlight)
- Lachapelle, S., Deleu, T., Mahajan, D., Mitliagkas, I., Bengio, Y., Lacoste-Julien, S., & Bertrand, Q. (2023). Synergies between disentanglement and sparsity: Generalization and identifiability in multi-task learning. ICML 2023 (pp. 18171-18206). PMLR.