Yannis Montreuil
About Me
I am Yannis, a PhD Candidate at the School of Computing, National University of Singapore, under the guidance of Prof. Wei Tsang Ooi, Dr. Lai Xing Ng, and Prof. Axel Carlier.
Scholarships
I am supported by AI Singapore and A*STAR, as part of my involvement in the DesCartes Program with CNRS@CREATE.
Keywords
Machine Learning Theory, Statistical Learning Theory, Routing Problems.
Research Interests
I study the mathematical foundations of routing and decision-making problems under uncertainty, with applications to multi-agent and hybrid systems. A central focus of my work is Learning-to-Defer — a framework in which predictive models learn not only to make decisions, but also to strategically abstain and defer to external experts when confidence is low.
My research focuses on formally characterizing when deferral is beneficial and how models can learn to defer in a provably optimal way, drawing on tools from statistical learning theory and decision theory.
TLDR: In essence, I teach models not only what to decide, but when to ask for help
Publications
- Yannis Montreuil, Towards Robust Human–AI Decision-Making via Learning-to-Defer (2025). AAAI-26 Doctoral Consortium.
- Yannis Montreuil, Duy Dang Hoang*, Maxime Meyer*, Axel Carlier, Lai Xing Ng, & Wei Tsang Ooi (2025). Online Learning-to-Defer with Varying Experts.
- Yannis Montreuil*, Letian Yu*, Axel Carlier, Lai Xing Ng, & Wei Tsang Ooi (2025). Adversarial Robustness in One-Stage Learning-to-Defer. arXiv preprint arXiv:2510.10988.
- Yannis Montreuil, Axel Carlier, Lai Xing Ng, & Wei Tsang Ooi (2025). Why Ask One When You Can Ask k? Learning-to-Defer to the Top-k Experts. arXiv preprint arXiv:2504.12988.
- Yannis Montreuil, Axel Carlier, Lai Xing Ng, & Wei Tsang Ooi (2025). Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees. arXiv preprint arXiv:2502.01027. Accepted to ICML 2025
- Yannis Montreuil*, Yeo Shu Heng*, Axel Carlier, Lai Xing Ng, & Wei Tsang Ooi (2025). A Two-Stage Learning-to-Defer Approach for Multi-Task Learning. arXiv preprint arXiv:2410.15729. Accepted to ICML 2025
- Yannis Montreuil*, Yeo Shu Heng*, Axel Carlier, Lai Xing Ng, & Wei Tsang Ooi (2024). Optimal Query Allocation in Extractive QA with LLMs. arXiv preprint arXiv:2410.15761.