mlsanityData to 14 Oct 2026

Toto: Time Series Optimized Transformer for Observability

arXiv 2407.07874 ↗First posted 10 Jul 2024cs.LG cs.AIcited by 48

Not on the map. Why?

Abstract (arXiv)

This technical report describes the Time Series Optimized Transformer for Observability (Toto), a new state of the art foundation model for time series forecasting developed by Datadog. In addition to advancing the state of the art on generalized time series benchmarks in domains such as electricity and weather, this model is the first general-purpose time series forecasting foundation model to be specifically tuned for observability metrics. Toto was trained on a dataset of one trillion time series data points, the largest among all currently published time series foundation models. Alongside publicly available time series datasets, 75% of the data used to train Toto consists of fully anonymous numerical metric data points from the Datadog platform. In our experiments, Toto outperforms existing time series foundation models on observability data. It does this while also excelling at general-purpose forecasting tasks, achieving state-of-the-art zero-shot performance on multiple open benchmark datasets.

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). Builds on 23 of its 47 references that are in the map. First posted on arXiv 10 Jul 2024.

Builds on

23 of 47 references.

References · 23

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  3. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  4. 2020GLU Variants Improve Transformercited by 1,804
  5. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  6. 2021ViViT: A Video Vision Transformercited by 1,620
  7. 2019Root Mean Square Layer Normalizationcited by 1,480
  8. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  9. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  10. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  11. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  12. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
11 more
  1. 2020On Layer Normalization in the Transformer Architecturecited by 922
  2. 2023A decoder-only foundation model for time-series forecastingcited by 692
  3. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  4. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 500
  5. 2021A Survey of Transformerscited by 401
  6. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 338
  7. 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 332
  8. 2019On the Relationship between Self-Attention and Convolutional Layerscited by 300
  9. 2022A Length-Extrapolatable Transformercited by 127
  10. 2024SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attentioncited by 44
  11. 2018A mixture autoregressive model based on Student's t-distributioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 15; 2026: 30.

48 papers.

Sort:

By area:

  1. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 197
  2. 2025Moirai 2.0: When Less Is More for Time Series Forecastingcited by 69
  3. 2025From Tables to Time: Extending TabPFN-v2 to Time Series Forecastingcited by 60
  4. 2024Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHRscited by 39
  5. 2026Toto 2.0: Time Series Forecasting Enters the Scaling Eracited by 30
  6. 2026Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scalingcited by 28
  7. 2024Specialized Foundation Models Struggle to Beat Supervised Baselinescited by 24
  8. 2025Foundation Models for Time Series: A Surveycited by 23
  9. 2025CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Datacited by 13
  10. 2026TiRex-2: Generalizing TiRex to Multivariate Data and Streamingcited by 13
  11. 2025TimeCopilotcited by 9
  12. 2025FlowState: Sampling-Rate-Equivariant Time-Series Forecastingcited by 8
36 more
  1. 2025Xihe: Scalable Zero-Shot Time Series Learner Via Hierarchical Interleaved Block Attentioncited by 8
  2. 2025MoTime: A Dataset Suite for Multimodal Time Series Forecastingcited by 7
  3. 2025Synapse: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Modelscited by 7
  4. 2025Byte Pair Encoding for Efficient Time Series Forecastingcited by 5
  5. 2025time2time: Causal Intervention in Hidden States to Simulate Rare Events in Time Series Foundation Modelscited by 4
  6. 2026Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecastingcited by 4
  7. 2026Reasoning-Aware Training for Time Series Forecastingcited by 3
  8. 2026EXAONE Finance 1.0: An Attention-free Time Series Foundation Model for Financial Time Seriescited by 3
  9. 2025Goal-Oriented Time-Series Forecasting: Foundation Framework Designcited by 2
  10. 2026ProbFM: Probabilistic Time Series Foundation Model with Uncertainty Decompositioncited by 2
  11. 2026OpenMHC: Accelerating the Science of Wearable Foundation Modelscited by 2
  12. 2026t0: A Time-Series Foundation Model for Forecasting with Contextcited by 2
  13. 2026DiTS: Multimodal Diffusion Transformers Are Time Series Forecasterscited by 1
  14. 2026WaveMoE: A Wavelet-Enhanced Mixture-of-Experts Foundation Model for Time Series Forecastingcited by 1
  15. 2026RareCP: Regime-Aware Retrieval for Efficient Conformal Predictioncited by 1
  16. 2026Towards Resilient and Autonomous Networks: A BlueSky Vision on AI-Native 6Gcited by 1
  17. 2026APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operationscited by 1
  18. 2026On Subquadratic Architectures: From Applications to Principlescited by 1
  19. 2026Evaluating Time Series Foundation Models for Electricity Price Forecasting: Contamination Risk, Distributional Shifts, and Covariate Dependencecited by 1
  20. 2026Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Modelscited by 1
  21. 2026Tabby: An Open Pretraining Recipe for Time Series Foundation Modelscited by 1
  22. 2025Foundation Model Forecasts: Form and Functioncited by 0
  23. 2025Tiny-TSM: Efficiently Training a Lightweight SOTA Time Series Foundation Modelcited by 0
  24. 2025TraCeR: Transformer-Based Competing Risk Analysis with Longitudinal Covariatescited by 0
  25. 2026A Scalable Multi-Task Model for Virtual Sensorscited by 0
  26. 2026Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Seriescited by 0
  27. 2026TimeBlocks: Foundational and Continual Time-Series Blockbase -- Extended Versioncited by 0
  28. 2026LakeFM: Toward a Foundation Model for Aquatic Ecosystems Using Irregular Multivariate Multi-depth Time Series Datacited by 0
  29. 2026When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasterscited by 0
  30. 2026Align-RAG: Alignment Is All You Need for TSFM In-Context Learningcited by 0
  31. 2026ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learningcited by 0
  32. 2026EXAONE Demand 1.0: A Time Series Foundation Model for Demand Forecastingcited by 0
  33. 2026READ-Bench: Benchmarking Historical Instance Retrieval for Time-Series Diagnosiscited by 0
  34. 2026OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoningcited by 0
  35. 2026Foundations without Fundamentals: Zero-Shot Blind Spots in Time Series FMscited by 0
  36. 2026What Does an Observability Foundation Model Know?cited by 0