mlsanityData to 14 Oct 2026

EXAONE Demand 1.0: A Time Series Foundation Model for Demand Forecasting

arXiv 2609.30880 ↗First posted 25 Sep 2026cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Time series foundation models (TSFMs) are pretrained on series from diverse domains, where demand series make up only a small fraction. Demand data has properties that such corpora rarely contain: Short histories, frequent zeros, censoring by stock-outs, and exogenous events that the series does not record. To this end, we propose EXAONE Demand, built on 1) a demand-specific corpus and 2) a demand-aware adapter. For the corpus, we assemble 11.3M series and 48.4B observations from 73 sources, and a synthetic generator supplies the behaviour that open demand data under-represents. For the adapter, we attach low-rank branches to a frozen general-domain backbone, one for each of the four demand classes (smooth, intermittent, erratic, and lumpy), and a router that reads eight scale-free statistics of the input series decides how much each branch contributes. We build EXAONE Demand in two versions, one trained on real-world and synthetic demand together and one trained on the synthetic corpus alone. On 22 held-out datasets, both versions outperform 36 TSFMs, and real-world demand adds a gain over synthetic data alone.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 71 references that are in the map. First posted on arXiv 25 Sep 2026.

Builds on

42 of 71 references.

References · 42

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  2. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  3. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  4. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  5. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  6. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  7. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  8. 2024DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Modelscited by 867
  9. 2024Chronos: Learning the Language of Time Seriescited by 759
  10. 2023A decoder-only foundation model for time-series forecastingcited by 692
  11. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  12. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 482
30 more
  1. 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 332
  2. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Expertscited by 287
  3. 2021Monash Time Series Forecasting Archivecited by 267
  4. 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 240
  5. 2024GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluationcited by 212
  6. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 208
  7. 2025Chronos-2: From Univariate to Universal Forecastingcited by 194
  8. 2025Sundial: A Family of Highly Capable Time Series Foundation Modelscited by 180
  9. 2023Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuningcited by 150
  10. 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Seriescited by 127
  11. 2025TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learningcited by 120
  12. 2024Is Mamba Effective for Time Series Forecasting?cited by 114
  13. 2024Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Expertscited by 95
  14. 2024VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasterscited by 88
  15. 2025fev-bench: A Realistic Benchmark for Time Series Forecastingcited by 64
  16. 2025From Tables to Time: Extending TabPFN-v2 to Time Series Forecastingcited by 60
  17. 2024Toto: Time Series Optimized Transformer for Observabilitycited by 48
  18. 2023Learning to Embed Time Series Patches Independentlycited by 35
  19. 2025Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Modelcited by 24
  20. 2025TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecastingcited by 17
  21. 2025CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Datacited by 13
  22. 2026Reverso: Efficient Time Series Foundation Models for Zero-shot Forecastingcited by 13
  23. 2024ANT: Adaptive Noise Schedule for Time Series Diffusion Modelscited by 11
  24. 2025FinCast: A Foundation Model for Financial Time-Series Forecastingcited by 10
  25. 2025Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Modelscited by 9
  26. 2025FlowState: Sampling-Rate-Equivariant Time-Series Forecastingcited by 8
  27. 2024Sequential Order-Robust Mamba for Time Series Forecastingcited by 5
  28. 2026Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecastingcited by 4
  29. 2024Dataset-Driven Channel Masks in Transformers for Multivariate Time Seriescited by 3
  30. 2026EXAONE Finance 1.0: An Attention-free Time Series Foundation Model for Financial Time Seriescited by 3

Built on by

Not cited yet.