mlsanityData to 7 Oct 2026

Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction

arXiv 2402.07570 ↗First posted 12 Feb 2024cs.LG cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

We present General Time Transformer (GTT), an encoder-only style foundation model for zero-shot multivariate time series forecasting. GTT is pretrained on a large dataset of 200M high-quality time series samples spanning diverse domains. In our proposed framework, the task of multivariate time series forecasting is formulated as a channel-wise next curve shape prediction problem, where each time series sample is represented as a sequence of non-overlapping curve shapes with a unified numerical magnitude. GTT is trained to predict the next curve shape based on a window of past curve shapes in a channel-wise manner. Experimental results demonstrate that GTT exhibits superior zero-shot multivariate forecasting capabilities on unseen time series datasets, even surpassing state-of-the-art supervised baselines. Additionally, we investigate the impact of varying GTT model parameters and training dataset scales, observing that the scaling law also holds in the context of zero-shot multivariate time series forecasting.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 23 of its 38 references that are in the map. First posted on arXiv 12 Feb 2024.

Builds on

23 of 38 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  5. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  6. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  7. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  8. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  9. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  10. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  11. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  12. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 906
11 more
  1. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  2. 2023A decoder-only foundation model for time-series forecastingcited by 650
  3. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  4. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  5. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 491
  6. 2021Monash Time Series Forecasting Archivecited by 256
  7. 2023TimeGPT-1cited by 149
  8. 2023AIM: Adapting Image Models for Efficient Video Action Recognitioncited by 145
  9. 2017Conditional Time Series Forecasting with Convolutional Neural Networkscited by 121
  10. 2023ForecastPFN: Synthetically-Trained Zero-Shot Forecastingcited by 102
  11. 2021Voice2Series: Reprogramming Acoustic Models for Time Series Classificationcited by 91

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 5.

11 papers.

  1. 2024Foundation Models for Time Series Analysis: A Tutorial and Surveycited by 234
  2. 2024VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasterscited by 87
  3. 2025VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbonescited by 11
  4. 2025Foundation models for time series forecasting: Application in conformal predictioncited by 6
  5. 2024The impact of data set similarity and diversity on transfer learning success in time series forecastingcited by 3
  6. 2026DualWeaver: Synergistic Feature Weaving Surrogates for Multivariate Forecasting with Univariate Time Series Foundation Modelscited by 1
  7. 2026Towards Unified and Data-Efficient Prognostics and Health Management with Tabular Foundation Modelscited 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. 2026Model-agnostic Retrieval-Augmented Extended Forecasting for time seriescited by 0
  11. 2026CryptoL: Towards Scale Dominance and Physics Constraints Mitigation in Financial Multivariate Time Series Forecastingcited by 0