mlsanityData to 14 Oct 2026

Zero-Shot Time Series Forecasting with Covariates via In-Context Learning

arXiv 2506.03128 ↗First posted 3 Jun 2025cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 3 Jun 2025.

Builds on

24 of 37 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  6. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  7. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  8. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  9. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  10. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  11. 2024Chronos: Learning the Language of Time Seriescited by 759
  12. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
12 more
  1. 2023A decoder-only foundation model for time-series forecastingcited by 692
  2. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 674
  3. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  4. 2021Transformers Can Do Bayesian Inferencecited by 360
  5. 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 240
  6. 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Seriescited by 127
  7. 2020Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmarkcited by 108
  8. 2021Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSxcited by 64
  9. 2019GluonTS: Probabilistic Time Series Models in Pythoncited by 46
  10. 2023LibCity: A Unified Library Towards Efficient and Comprehensive Urban Spatial-Temporal Predictioncited by 20
  11. 2023Bridging AI and Energy Forecasting: An Autonomous Workflow with Customized Toolkitcited by 7
  12. 2022HERMES: Hybrid Error-corrector Model with inclusion of External Signals for nonstationary fashion time seriescited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 8.

12 papers.

  1. 2025Chronos-2: From Univariate to Universal Forecastingcited by 194
  2. 2026TiRex-2: Generalizing TiRex to Multivariate Data and Streamingcited by 13
  3. 2025Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classificationcited by 9
  4. 2026Why Do Time Series Models Need Long Context Windows?cited by 3
  5. 2026CITRAS-FM: Tiny Time Series Foundation Model for Covariate-Informed Zero-Shot Forecastingcited by 2
  6. 2026t0: A Time-Series Foundation Model for Forecasting with Contextcited by 2
  7. 2025Are Time-Indexed Foundation Models the Future of Time Series Imputation?cited by 1
  8. 2026RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Modelscited by 1
  9. 2025Foundation Model Forecasts: Form and Functioncited by 0
  10. 2026One-Shot Price Forecasting with Covariate-Guided Experts under Privacy Constraintscited by 0
  11. 2026A Scalable Multi-Task Model for Virtual Sensorscited by 0
  12. 2026Assessing Covariate-Informed Grid Load Forecasting with a Time-Series Foundation Modelcited by 0