analiza aiqbench
TS-ICL represents a significant advancement in time series foundation models by unifying forecasting and imputation tasks through an In-Context Learning framework that handles irregular sampling conditions. By leveraging synthetic causal priors, this approach achieves state-of-the-art performance on missing value recovery while maintaining competitive accuracy for prediction under degraded data windows. This work addresses critical gaps where current general-purpose models struggle with partial observations, offering a more robust paradigm for real-world time series analysis.
TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning
arXiv:2606.05878v2 Announce Type: replace Abstract: Foundation models mark a profound paradigm shift in time series modeling, with task-specific models being superseded by general-purpose zero-shot models.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.
Abstract:Foundation models mark a profound paradigm shift in time series modeling, with task-specific models being superseded by general-purpose zero-shot models.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.
Machine Learning (cs.LG)
arXiv:2606.05878 [cs.LG]
(or arXiv:2606.05878v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.05878 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 221 cuvinte
Subiecte conexe
Real-Time Intelligence with IBM Time Series Models on Confluent
Hugging Face · 2 sept. 2026
ROCm 7.14: TheRock Goes Production and Expands AMD’s AI Software Platform
AMD · 15 iul. 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · 17 sept. 2026
SQL Data Types: Reference and Best Practices
Databricks · 8 sept. 2026