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

My PhD is funded by AI Singapore and A*STAR under the DesCartes program (CNRS@CREATE).

About

I’m a PhD candidate in Computer Science at the National University of Singapore. I work on statistical machine learning, mostly on choosing between several models when each is reliable on different inputs. My papers have appeared at NeurIPS, ICML, ICLR, and AISTATS.

I finish my PhD in January 2027 and am looking for full-time roles and internships in quantitative research or machine learning research. If you’re hiring or want to work together, please email me.

Research

I study how to choose among several models or experts. Given an input $x$, I learn which model $f_i$ should handle it, under constraints such as cost or latency. This problem is known as learning-to-defer or model routing. I prove guarantees for these methods and test them in experiments.

Routing an input to one of several models A time series and its context form input x. A learned router selects the second of three available experts, a tree model, to produce a prediction. Selection considers predictive performance and constraints such as cost or latency. The highlighted route is illustrative. Input x History + context Router r(x) Goal + constraints Models / experts f₁ Linear model f₂ Tree model f₃ Neural model Prediction ŷ Routing an input to one of several models Input x passes through a router, which selects a tree model from three available experts. Selection considers predictive performance and constraints such as cost or latency. The selected model produces the prediction. Input x History + context Goal + constraints Router r(x) f₁ Linear f₂ Tree model f₃ Neural ŷ Prediction: f₂(x)
One input, one selected expert: ŷ = fr(x)(x).

I have applied them to language models, time-series forecasting, and computer vision. They apply wherever several models or experts can be queried.

Keywords: statistical machine learning, model routing, model orchestration, learning-to-defer, online learning, time series, large language models.

Publications

2026

  1. Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer. Yannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. NeurIPS26. Link
  2. A Query Is Not a Commitment: Learning to Correct Expert Answers in Online Deferral. Yannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. Preprint. Link
  3. Consistent Learning-to-Defer with Expert-Conditional Advice. Yannis Montreuil, Leina Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. ICML26 AgenticUG Workshop; under review. Link
  4. 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. Under review. Link
  5. Transition Affinity: A Unified Notion of Geometry for LLMs and Text Corpora. Maxime Meyer*, Yannis Montreuil*, Zongmin Li*, Caroline Chaux, Vincent Y. F. Tan. Under review.
  6. 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. Link.
  7. Online Learning-to-Defer with Varying Experts. Yannis Montreuil*, Duy Dang Hoang*, Maxime Meyer*, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. AISTATS 2026. Link.
  8. Adversarial Robustness in One-Stage Learning-to-Defer. Yannis Montreuil*, Letian Yu*, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi. AISTATS 2026. Link.
  9. 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. Link.
  10. 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. Link.
  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. Link.

* indicates equal contribution. Abstracts and details are on the learning-to-defer publications page.