activity
20242026
most citedMulti-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving

32 citations · 33 across the 18 of their papers we have counts for

collaborators
Showing stat.MLShow all

7 papers · 1 filter

stat.ML2026

Online Learning-to-Defer with Varying Experts

Dang Hoang Duy, Yannis Montreuil, Maxime Meyer +3

Learning-to-Defer (L2D) methods route each query either to a predictive model or to external experts. While existing work studies this problem in batch settings, real-world deploym…

stat.ML2026

Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer

Yannis Montreuil, Axel Carlier, Lai Xing Ng +1

A learning-to-defer (L2D) system decides, for each input, whether to predict on its own or to hand it to one of several available experts. The very well established recipe trains c…

stat.ML2026

Learning-to-Defer with Expert-Conditional Advice

Yannis Montreuil, Leïna Montreuil, Axel Carlier +2

Learning-to-Defer routes each input to the expert that minimizes expected cost, but it assumes that the information available to every expert is fixed at decision time. Many modern…

stat.ML2026

Adversarial Robustness in One-Stage Learning-to-Defer

Yannis Montreuil, Letian Yu, Axel Carlier +2

Learning-to-Defer (L2D) enables hybrid decision-making by routing inputs either to a predictor or to external experts. While promising, L2D is highly vulnerable to adversarial pert…

stat.ML2025

One-Stage Top- Learning-to-Defer: Score-Based Surrogates with Theoretical Guarantees

Yannis Montreuil, Axel Carlier, Lai Xing Ng +1

We introduce the first one-stage Top- Learning-to-Defer framework, which unifies prediction and deferral by learning a shared score-based model that selects the most cost-ef…

stat.ML2025

Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees

Yannis Montreuil, Axel Carlier, Lai Xing Ng +1

Two-stage Learning-to-Defer (L2D) enables optimal task delegation by assigning each input to either a fixed main model or one of several offline experts, supporting reliable decisi…