mlsanityData to 14 Oct 2026

TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state

arXiv 2505.20774 ↗First posted 27 May 2025cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

In long-term time series forecasting, different variables often influence the target variable over distinct time intervals, a challenge known as the multi-delay issue. Traditional models typically process all variables or time points uniformly, which limits their ability to capture complex variable relationships and obtain non-trivial time representations. To address this issue, we propose TimePro, an innovative Mamba-based model that constructs variate- and time-aware hyper-states. Unlike conventional approaches that merely transfer plain states across variable or time dimensions, TimePro preserves the fine-grained temporal features of each variate token and adaptively selects the focused time points to tune the plain state. The reconstructed hyper-state can perceive both variable relationships and salient temporal information, which helps the model make accurate forecasting. In experiments, TimePro performs competitively on eight real-world long-term forecasting benchmarks with satisfactory linear complexity. Code is available at https://github.com/xwmaxwma/TimePro.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 23 of its 32 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

23 of 32 references.

References · 23

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  2. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  3. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  4. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  5. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  6. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  7. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  8. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 608
  9. 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 391
  10. 2022Diagonal State Spaces are as Effective as Structured State Spacescited by 350
  11. 2024TimeMixer: Decomposable Multiscale Mixing for Time Series Forecastingcited by 346
  12. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 338
11 more
  1. 2022Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structurescited by 160
  2. 2024Is Mamba Effective for Time Series Forecasting?cited by 114
  3. 2024SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusioncited by 76
  4. 2024TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecastingcited by 64
  5. 2024Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applicationscited by 50
  6. 2019Recurrent Neural Networks for Time Series Forecastingcited by 19
  7. 2024Bi-Mamba+: Bidirectional Mamba for Time Series Forecastingcited by 15
  8. 2024Channel-Aware Low-Rank Adaptation in Time Series Forecastingcited by 12
  9. 2024A Mamba Foundation Model for Time Series Forecastingcited by 9
  10. 2024Linearly-evolved Transformer for Pan-sharpeningcited by 5
  11. 2023Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scalecited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 13.

16 papers.

Sort:

By area:

  1. 2025AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecastingcited by 12
  2. 2026Enhancing Multivariate Time Series Forecasting with Global Temporal Retrievalcited by 5
  3. 2025TimeExpert: Boosting Long Time Series Forecasting with Temporal Mix of Expertscited by 4
  4. 2026vLinear: A Powerful Linear Model for Multivariate Time Series Forecastingcited by 1
  5. 2026DMamba: Decomposition-enhanced Mamba for Time Series Forecastingcited by 1
  6. 2026DualWeaver: Synergistic Feature Weaving Surrogates for Multivariate Forecasting with Univariate Time Series Foundation Modelscited by 1
  7. 2026What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable Dependenciescited by 1
  8. 2025Ada-MoGE: Adaptive Mixture of Gaussian Expert Model for Time Series Forecastingcited by 0
  9. 2026ACFormer: Mitigating Non-linearity with Auto Convolutional Encoder for Time Series Forecastingcited by 0
  10. 2026Permutation-Equivariant 2D State Space Models: Theory and Canonical Architecture for Multivariate Time Seriescited by 0
  11. 2026MICA: Multivariate Infini Compressive Attention for Time Series Forecastingcited by 0
  12. 2026Generalizing Multi-Scale Time-Series Modeling with a Single Operatorcited by 0
4 more
  1. 2026VLBM: Variational Latent Basis Modeling for OOD Robust Multivariate Time Series Forecastingcited by 0
  2. 2026TSSM: Triaxial State Space Model for Global Station Weather Forecasting with Temporal-Variable-Historical Modelingcited by 0
  3. 2026CARNet Cycle-Conditioned Core Aggregation and Redistribution for Multivariate Time Series Forecastingcited by 0
  4. 2026UniGIO: Unified Generative Global In-situ Weather Modeling from Spatiotemporal Incomplete Observationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting
  2. 2026UniMamba: A Unified Spatial-Temporal Modeling Framework with State-Space and Attention Integration
  3. 2024CMamba: Channel Correlation Enhanced State Space Models for Multivariate Time Series Forecasting
  4. 2025ParallelTime: Dynamically Weighting the Balance of Short- and Long-Term Temporal Dependencies
  5. 2024Integration of Mamba and Transformer -- MAT for Long-Short Range Time Series Forecasting with Application to Weather Dynamics
  6. 2025DC-Mamber: A Dual Channel Prediction Model based on Mamba and Linear Transformer for Multivariate Time Series Forecasting
  7. 2025S2TX: Cross-Attention Multi-Scale State-Space Transformer for Time Series Forecasting
  8. 2026AdaMamba: Adaptive Frequency-Gated Mamba for Long-Term Time Series Forecasting