Publications

TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning

Etienne Le Naour*, Tahar Nabil*, Adrien Petralia

arXiv preprint, June 2026.

Are Time-Indexed Foundation Models the Future of Time Series Imputation?

Etienne Le Naour*, Tahar Nabil*, Adrien Petralia, Ghislain Agoua

Transaction on Machine Learning Research (TMLR), 2026.

Presented at NeurIPS 2025, Workshop on Recent Advances in Time Series Foundation Models (BERT2S).

NILMFormer: Non-Intrusive Load Monitoring that Accounts for Non-Stationarity

Adrien Petralia, Philippe Charpentier, Youssef Kadhi, Themis Palpanas

ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), Toronto, ON, Canada, August 2025

Few Labels are all you need: A Weakly Supervised Framework for Appliance Localization in Smart-Meter Series

Adrien Petralia, Paul Boniol, Philippe Charpentier, Themis Palpanas

IEEE International Conference on Data Engineering (ICDE), Hong Kong SAR, China, May 2025

DeviceScope: An Interactive App to Detect and Localize Appliance Patterns in Electricity Consumption Time Series

Adrien Petralia, Paul Boniol, Philippe Charpentier, Themis Palpanas

IEEE International Conference on Data Engineering (ICDE), Hong Kong SAR, China, May 2025

Time Series Analytics for Electricity Consumption Data

Adrien Petralia

Very Large Data Bases (VLDB) PhD Workshop, Guangzhou, China, August 2024

ADF & TransApp: A Transformer-Based Framework for Appliance Detection Using Smart Meter Consumption Series

Adrien Petralia, Philippe Charpentier, Themis Palpanas

Proceedings of the VLDB Endowment (PVLDB) Journal, December 2023

Presented at the 50th International Conference on Very Large DataBases (VLDB), Guangzhou, China, August 2024

Détection d’appareils électriques à partir de séries temporelles de consommation très basse fréquence

Adrien Petralia, Philippe Charpentier, Paul Boniol, Themis Palpanas

39ème Conférence sur la Gestion de Données (BDA), Montpellier, France, October 2023

Appliance Detection Using Very Low-Frequency Smart Meter Time Series

Adrien Petralia, Philippe Charpentier, Paul Boniol, Themis Palpanas

ACM International Conference on Future Energy Systems (e‑Energy), Orlando, FL, USA, June 2023

Pumping station design based on shape optimization process

Florent Taccone, Cédric Goeury, Fabrice Zaoui, Adrien Petralia

Proceedings of the TELEMAC‑MASCARET User Conference, Online, October 2020

Determining the Activation Over Time of a Given Device Within a Set of Devices Based on Collected Data

Adrien Petralia, Themis Palpanas, Philippe Charpentier, Claire Lambert

PCT/EP2026/062782

Extracting the Power Consumption of an Individual Device Within a set of Devices Connected to an Electrical Network

Adrien Petralia, Themis Palpanas, Philippe Charpentier, Claire Lambert

PCT/EP2025/076327

Détermination d'une activation au cours du temps d'un équipement donné au sein d'un ensemble d'équipements à partir de données collectées

Adrien Petralia, Paul Boniol, Themis Palpanas, Philippe Charpentier

French Patent FR2504769

Characterisation for Optimising the Power Consumption of a Set of Devices Connected to an Electrical Network

Luc Dufour, Pascal Chaussumier, Adrien Petralia, Philippe Charpentier, Themis Palpanas, Justin Capik

European Patent EP4571461

Extraction de la consommation électrique d'un équipement individuel au sein d'un ensemble d'équipements connectés à un réseau électrique

Adrien Petralia, Themis Palpanas, Philippe Charpentier, Claire Lambert

French Patent FR2410061

Caractérisation pour l'optimisation de la consommation électrique d'un ensemble d'équipements connectés à un réseau électrique

Luc Dufour, Pascal Chaussumier, Adrien Petralia, Philippe Charpentier, Themis Palpanas, Justin Capik

French Patent FR3156961