{"ID":3083895,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T07:39:45.869976485Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05878","arxiv_id":"2606.05878","title":"TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning","abstract":"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models mark a profound paradigm shift in time series modeling, with task-specific models being superseded by general-purpose zero-shot models.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 primarily focus on forecasting, while real-world time series are often irregularly and partially observed, requiring models that can jointly forecast, impute missing values, and handle degraded sampling conditions. To address these challenges, we introduce TS-ICL, a novel probabilistic In-Context Learning encoder--regressor Transformer that unifies forecasting and imputation. TS-ICL formulates time series tasks as timestamp-aligned regression and naturally incorporates covariates by training on synthetic dependency structures generated from a novel causal data prior. Empirically, TS-ICL achieves a new state-of-the-art in imputation, while remaining competitive with leading forecasting foundation models across both univariate and covariate-aware benchmarks. It shows particularly strong performance in forecasting with partially observed look-back windows.","short_abstract":"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models mark a profound paradigm shift in time series modeling, with task-specific models being superseded by general-purpose zero-shot models.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 primarily focus on forecasting, while real-world time series are often irregularly and partially observed, requiring models that can jointly f...","url_abs":"https://arxiv.org/abs/2606.05878","url_pdf":"https://arxiv.org/pdf/2606.05878v1","authors":"[\"Etienne Le Naour\",\"Tahar Nabil\",\"Adrien Petralia\"]","published":"2026-06-04T08:52:21Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Transformer\"]","has_code":false}