activity
20242026
collaborators

10 papers

cs.LG2026

Counterfactual learning of new adaptive instructional policies using logged data

Samuel Girard, Sein Minn, Amel Bouzeghoub +1

Optimizing instructional policies in Intelligent Tutoring Systems (ITS) typically requires costly online experimentation or student simulators that may fail to capture real-world d…

cs.LG2026

Reinforcement Learning Foundation Models Should Already Be A Thing

Abdelrahman Zighem, Jill-Jênn Vie

Foundation models for language and vision are powered by internet-scale data, while structured domains such as tabular prediction are powered by synthetic data. This substitute shi…

stat.ML2026

Counterfactually Fair Regression via Optimal Transport

M. Generali Lince, S. Gaucher, J-J. Vie +1

We consider the problem of learning a counterfactually fair regressor. We adopt a causal uncertainty view in which counterfactual fairness is defined with resampled noise. We focus…

cs.CY2026

Estimating Learners' Skill Acquisition Without Temporal Information

Ryosuke Nagai, Kyohei Atarashi, Koh Takeuchi +2

Recent research in educational data mining, especially knowledge tracing, has focused on predicting learners' future knowledge states to support adaptive instruction. However, in m…

cs.CL2026

Large Language Models as Students Who Think Aloud: Overly Coherent, Verbose, and Confident

Conrad Borchers, Jill-Jênn Vie, Roger Azevedo

Large language models (LLMs) are increasingly embedded in AI-based tutoring systems. Can they faithfully model novice reasoning and metacognitive judgments? Existing evaluations em…

cs.LG2026

Live Knowledge Tracing: Real-Time Adaptation using Tabular Foundation Models

Mounir Lbath, Alexandre Parésy, Abdelkayoum Kaddouri +2

Deep knowledge tracing models have achieved significant breakthroughs in modeling student learning trajectories. However, these architectures require substantial training time and…