mlsanityData to 14 Oct 2026

Are Time-Indexed Foundation Models the Future of Time Series Imputation?

arXiv 2511.05980 ↗First posted 8 Nov 2025cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

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 places them within the family of time-indexed foundation models. This paper presents the first large-scale empirical study of these models for zero-shot imputation, which enables missing value recovery without retraining across a wide range of scenarios. We conduct extensive univariate experiments across 33 out-of-domain datasets (approximately 1.3M imputation windows) and evaluate their ability to integrate covariates at inference time to improve accuracy without fine-tuning. Our results demonstrate that time-indexed foundation models are a powerful and practical step toward achieving general-purpose, zero-shot imputation for real-world time series.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 55 references that are in the map. First posted on arXiv 8 Nov 2025.

Builds on

34 of 55 references.

References · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  3. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  4. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  5. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  6. 2024Chronos: Learning the Language of Time Seriescited by 759
  7. 2023A decoder-only foundation model for time-series forecastingcited by 692
  8. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  9. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  10. 2018Deep learning for time series classification: a reviewcited by 576
  11. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 482
  12. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 290
22 more
  1. 2021Monash Time Series Forecasting Archivecited by 267
  2. 2024GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluationcited by 212
  3. 2022From data to functa: Your data point is a function and you can treat it like onecited by 187
  4. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 169
  5. 2018Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecastingcited by 146
  6. 2025TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learningcited by 120
  7. 2024TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysiscited by 116
  8. 2024TSLANet: Rethinking Transformers for Time Series Representation Learningcited by 74
  9. 2025From Tables to Time: Extending TabPFN-v2 to Time Series Forecastingcited by 60
  10. 2023ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputationcited by 50
  11. 2023ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modelingcited by 47
  12. 2023BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecastingcited by 26
  13. 2023LibCity: A Unified Library Towards Efficient and Comprehensive Urban Spatial-Temporal Predictioncited by 20
  14. 2022Learning Deep Time-index Models for Time Series Forecastingcited by 18
  15. 2023Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representationscited by 17
  16. 2023PyPOTS: A Python Toolkit for Machine Learning on Partially-Observed Time Seriescited by 12
  17. 2025Zero-Shot Time Series Forecasting with Covariates via In-Context Learningcited by 12
  18. 2023Bridging AI and Energy Forecasting: An Autonomous Workflow with Customized Toolkitcited by 7
  19. 2024NuwaTS: a Foundation Model Mending Every Incomplete Time Seriescited by 4
  20. 2025ImputeINR: Time Series Imputation via Implicit Neural Representations for Disease Diagnosis with Missing Datacited by 3
  21. 2025A synthetic dataset of French electric load curves with temperature conditioningcited by 2
  22. 2025MoTM: Towards a Foundation Model for Time Series Imputation based on Continuous Modelingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learningcited by 4