LAK (International Conference on Learning Analytics & Knowledge): 2026
ICCE (International Conference on Computers in Education): 2024 · 2025
AI4ED Workshop @ AAAI: 2026
RKDE Workshop @ ECML-PKDD: 2024
Reviewer
IJAIED (International Journal of Artificial Intelligence in Education): 2024 · 2025
JEDM (Journal of Educational Data Mining): 2025
Volunteering
AIED (International Conference on Artificial Intelligence in Education): 2024
NeurIPS (Neural Information Processing Systems): 2021
Invitation
Panelist @ PraTIC Symposium 2023 (CHF)
Workshop chair @ PraTIC Symposium 2023 (CHF)
Supervision
Cagla Koprulu, Hugo Pham, Nathan Guetteville (M1 Computer Science students, co-supervised with Badmavasan Kirouchenassamy, 3mo., 2025): Context-specific fairness for large language models.
Matthieu Marthe, Douaa Jabrane, Safia Bounafaa (M1 Engineering students, co-supervised with Dr. Xavier Morel, 1yr., 2024-25): Mixed-method analyses of usage and effects of LLMs on performance and answer quality among engineering students during exams (1 submitted publication).
Chunyang Fan (M2 Maths student, 6mo., 2024): Improving and generalizing algorithmic fairness evaluation and mitigation for machine learning (2 publications: JEDM 2025, RKDE @ ECML-PKDD 2024).
Tool
maddlib (doc): a Python library that provides every tool to measure, mitigate, and visualize algorithmic unfairness with the MADD metric
Illustration of MADD (d) in the red zone (vs. the fair zone in green), obtained from the density estimations (c) based on the outputs of a ML model for 2 groups (a) and (b).
Anonymized data and open-source code
ateneo: code to preprocess educational data from Canvas LMS and perform algorithmic (un)fairness analyses in a Filipino context
mooc-gdp: data and code to analyze algorithmic (un)fairness according to demographics and contextual variables in French and African contexts
madd-repo: data and code to replicate experiments with the MADD metric from several papers
