Long input windows are required to identify the generative process in time series forecasting even for short-memory processes, and decoupling identification from forecasting improves scalability.
Zero-Shot Time Series Forecasting with Covariates via In-Context Learning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Pretrained time series models, capable of zero-shot forecasting, have demonstrated significant potential in enhancing both the performance and accessibility of time series forecasting. However, existing pretrained models either do not support covariates or fail to incorporate them effectively. We introduce COSMIC, a zero-shot forecasting model that utilizes covariates via in-context learning. To address the challenge of data scarcity, we propose Informative Covariate Augmentation, which enables the training of COSMIC without requiring any datasets that include covariates. COSMIC achieves state-of-the-art performance in zero-shot forecasting, both with and without covariates. Our quantitative and qualitative analysis demonstrates that COSMIC effectively leverages covariates in zero-shot forecasting.
years
2026 4representative citing papers
A curated 142-billion-point real-world multivariate time series corpus improves zero-shot forecasting when combined with existing synthetic and univariate pretraining data across four foundation models.
TiRex-2 is a recurrent xLSTM time series foundation model for multivariate forecasting with future covariates and constant-cost streaming that reports SOTA zero-shot results on GIFT-Eval and fev-bench.
A 7M-parameter patch Transformer with Shifted Attention and CovSynth synthetic covariates reaches SOTA zero-shot skill among sub-10M TSFMs on fev-bench with sub-0.1s CPU inference.
citing papers explorer
-
Why Do Time Series Models Need Long Context Windows?
Long input windows are required to identify the generative process in time series forecasting even for short-memory processes, and decoupling identification from forecasting improves scalability.
-
RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models
A curated 142-billion-point real-world multivariate time series corpus improves zero-shot forecasting when combined with existing synthetic and univariate pretraining data across four foundation models.
-
TiRex-2: Generalizing TiRex to Multivariate Data and Streaming
TiRex-2 is a recurrent xLSTM time series foundation model for multivariate forecasting with future covariates and constant-cost streaming that reports SOTA zero-shot results on GIFT-Eval and fev-bench.
-
CITRAS-FM: Tiny Time Series Foundation Model for Covariate-Informed Zero-Shot Forecasting
A 7M-parameter patch Transformer with Shifted Attention and CovSynth synthetic covariates reaches SOTA zero-shot skill among sub-10M TSFMs on fev-bench with sub-0.1s CPU inference.