Yannis Montreuil

Portrait of Yannis Montreuil

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, robust decision-making, and statistical learning theory.

Scholarships

I am supported by AI Singapore and A*STAR through one of Singapore's most selective national AI research scholarship programs, under the DesCartes Program with CNRS@CREATE.

Research Overview

A model that is unsure about an input has two options: answer anyway, or hand the case to someone better placed to decide. I work on how to make that choice well — when to defer, who to defer to, and what it costs to get it wrong. This is called learning-to-defer. Much of it deals with what happens once experts become adversarial, expensive, or simply unavailable.

I expect to finish my PhD in January 2027. I am looking for a research internship in quantitative research or machine learning research, and I am open to full-time roles. The work I enjoy most involves real statistical modeling — prediction under uncertainty, robust decision-making, and systems that have to justify the decisions they make. My email is in the sidebar and I answer everything.

Keywords: learning-to-defer, statistical learning theory, statistical modeling, prediction under uncertainty, multi-expert systems.

Publications

2026

  1. Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer. Yannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. arXiv:2604.09414
  2. Learning-to-Defer with Expert-Conditioned Advice. Yannis Montreuil, Leina Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. arXiv:2603.14324
  3. 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. arXiv:2601.22538
  4. 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.
  5. Online Learning-to-Defer with Varying Experts. Yannis Montreuil*, Duy Dang Hoang*, Maxime Meyer*, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. AISTATS 2026. arXiv:2605.12340.
  6. 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.
  7. 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.
  8. 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. Abstracts and details are on the learning-to-defer publications page.