Yannis Montreuil

Logo

PhD Candidate
AISG and A*MA Recipient
School of Computing
National University of Singapore

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.

Research Interests

Learning-to-Defer, Learning from Abstention, Human-AI Collaboration, Learning Theory.

Scholarships

I am supported by AI Singapore and A*STAR, as part of my involvement in the DesCartes Program with CNRS@CREATE.

Research Overview

I study the mathematical foundations of decision-making under uncertainty, focusing on Learning-to-Defer: models that learn not only what to decide, but when to defer to experts.

Publications

2026

  1. Learning to Defer in Non-Stationary Time Series via Switching State-Space Models. Yannis Montreuil*, Letian Yu*, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi.
  2. Why Ask One When You Can Ask k? Learning-to-Defer to the Top-k Experts. Yannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. ICLR 2026. arXiv:2504.12988.
  3. Online Learning-to-Defer with Varying Experts. Yannis Montreuil*, Duy Dang Hoang*, Maxime Meyer*, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. AISTATS 2026.
  4. Adversarial Robustness in One-Stage Learning-to-Defer. Yannis Montreuil*, Letian Yu*, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. AISTATS 2026. arXiv:2510.10988.
  5. Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees. Yannis Montreuil*, Yeo Shu Heng*, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. AISTATS 2026. arXiv:2410.15761.
  6. Towards Robust Human–AI Decision-Making via Learning-to-Defer. Yannis Montreuil. AAAI-26 Doctoral Consortium.

2025

  1. Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees. Yannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. ICML 2025. arXiv:2502.01027.
  2. A Two-Stage Learning-to-Defer Approach for Multi-Task Learning. Yannis Montreuil*, Yeo Shu Heng*, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. ICML 2025. arXiv:2410.15729.

* indicates equal contribution. For abstracts and more details, see Detailed Publications.