Seminars
My seminar presentations and paper discussions.
Reading and debating research is central to how I work. This page gathers the seminar I founded at Michelin, a selection of papers I have presented there, and talks I have been invited to give.
A Research Seminar I Founded
A Paper A Week (APAW)
I founded and organize a bi-monthly research seminar that brings together researchers and data scientists across Michelin. Each session dives into a single paper or topic, recent ones ranging from conformal prediction and Self-Organizing Maps to long-range sequence models and the transformer architecture, always bridging the latest academic ideas and the industrial problems we face daily. The goal is simple: keep learning together and spot opportunities to bring cutting-edge research into production.
April 2024 to Present 路 Clermont-Ferrand 路 Bi-monthly 路 Researchers and Data Scientists
Selected Paper Presentations
A sample of the papers I have presented at A Paper A Week, chosen for how they connect frontier research to the problems we face in industry.
TorchSOM: PyTorch Library for Self-Organizing Maps
GitHub 路 Unsupervised Learning, Dimensionality Reduction
Presented my own open-source library for Self-Organizing Maps in PyTorch, showing how SOMs can power industrial data visualization, anomaly detection, and similarity-based retrieval at scale.
馃捇 GitHubHyenaDNA: Long-Range Genomic Sequence Modeling
arXiv (2023) 路 Sequence Modeling, Genomics, BioAI
A sub-quadratic alternative to transformers for extremely long sequences (up to 1M tokens). I presented this for its potential connections to industrial time-series modeling where sequences can span thousands of process steps.
馃搫 PaperA Gentle Introduction to Conformal Prediction
arXiv (2021) 路 Uncertainty Quantification
An accessible introduction to conformal prediction, a framework for producing prediction intervals with finite-sample coverage guarantees. Directly relevant to my PhD work on uncertainty quantification for industrial quality monitoring.
馃搫 PaperQuality-Diversity Optimization: a novel branch of stochastic optimization
arXiv (2020) 路 Evolutionary Algorithms, Optimization
An overview of QD algorithms, which find not one but an entire repertoire of diverse, high-performing solutions. I presented this from my MSc experience at Imperial College, discussing potential applications to process optimization.
馃搫 PaperAttention Is All You Need
NeurIPS (2017) 路 Deep Learning, Transformers
The foundational paper behind modern language models, vision transformers, and much of today's AI. I discussed the self-attention mechanism and its implications for sequential industrial data, foundational background for most of modern deep learning.
馃搫 PaperInvited Seminars
Talks I was invited to give to research and data-science audiences.
TorchSOM: Applications to Online Sensing and Uncertainty Quantification
October 2025 路 Mathematical PhD Seminar, 脡cole Polytechnique
Presented TorchSOM to the mathematical PhD community at Polytechnique, covering the library's design, its role as a backbone for Just-in-Time Learning, and applications to online quality sensing and conformal prediction in industrial settings.
馃捇 GitHubOnline Sensing for Quality Monitoring
July 2025 路 Data Scientists Network, Michelin
Presented my work on adaptive soft sensing to Michelin's Data Scientists Network, comparing temporal, similarity-based, and hybrid strategies for real-time quality monitoring on the production line.