5 papers
TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning
Etienne Le Naour, Tahar Nabil, Adrien Petralia
Foundation models mark a profound paradigm shift in time series modeling, with task-specific models being superseded by general-purpose zero-shot models. Yet, current approaches pr…
Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS
Gaspard Berthelier, Mariia Baranova, Andrei-Tiberiu Pantea +4
Time Series Foundation Models (TSFMs) have recently achieved state-of-the-art performance, often outperforming supervised models in zero-shot settings. Recent TSFM architectures, s…
On the Role of Reversible Instance Normalization
Gaspard Berthelier, Tahar Nabil, Etienne Le Naour +3
Data normalization is a crucial component of deep learning models, yet its role in time series forecasting remains insufficiently understood. In this paper, we identify three centr…
Are Time-Indexed Foundation Models the Future of Time Series Imputation?
Etienne Le Naour, Tahar Nabil, Adrien Petralia +1
Foundation models for time series imputation remain largely unexplored. Recently, two such models, TabPFN-TS and MoTM, have emerged. These models share a common philosophy that pla…
MoTM: Towards a Foundation Model for Time Series Imputation based on Continuous Modeling
Etienne Le Naour, Tahar Nabil, Ghislain Agoua
Recent years have witnessed a growing interest for time series foundation models, with a strong emphasis on the forecasting task. Yet, the crucial task of out-of-domain imputation…