# STM3: Mixture of Multiscale Mamba for Long-Term Spatio-Temporal Time-Series Prediction

arXiv: https://arxiv.org/abs/2508.12247 · HTML: https://mlsanity.com/paper/2508.12247/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 34 of its 72 references that are in the map.
- First posted on arXiv 17 Aug 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)

## Builds on (most cited first, 30 of 34)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction](https://mlsanity.com/paper/1811.05320/) (2018)
- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [Long Range Language Modeling via Gated State Spaces](https://mlsanity.com/paper/2206.13947/) (2022)
- [Graph Neural Controlled Differential Equations for Traffic Forecasting](https://mlsanity.com/paper/2112.03558/) (2021)
- [TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis](https://mlsanity.com/paper/2410.16032/) (2024)
- [Inductive Graph Neural Networks for Spatiotemporal Kriging](https://mlsanity.com/paper/2006.07527/) (2020)
- [PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecasting](https://mlsanity.com/paper/2002.12898/) (2020)
- [Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting](https://mlsanity.com/paper/2206.04038/) (2022)
- [Theory on Mixture-of-Experts in Continual Learning](https://mlsanity.com/paper/2406.16437/) (2024)
- [Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities](https://mlsanity.com/paper/2402.10835/) (2024)
- [Self-Supervised Learning Disentangled Group Representation as Feature](https://mlsanity.com/paper/2110.15255/) (2021)
- [Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting](https://mlsanity.com/paper/2406.03751/) (2024)
- [Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts](https://mlsanity.com/paper/2309.13850/) (2023)
- [Graph Deep Learning for Time Series Forecasting](https://mlsanity.com/paper/2310.15978/) (2023)
- [On Least Square Estimation in Softmax Gating Mixture of Experts](https://mlsanity.com/paper/2402.02952/) (2024)
- [MLPST: MLP is All You Need for Spatio-Temporal Prediction](https://mlsanity.com/paper/2309.13363/) (2023)
- [PromptST: Prompt-Enhanced Spatio-Temporal Multi-Attribute Prediction](https://mlsanity.com/paper/2309.09500/) (2023)
- [An overview of domain-specific foundation model: key technologies, applications and challenges](https://mlsanity.com/paper/2409.04267/) (2024)
- [SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series Forecasting](https://mlsanity.com/paper/2404.14757/) (2024)

## Built on by (most cited first, 1 of 1)

- [PIMSM: Physics-Informed Multi-Scale Mamba for Stable Neural Representations under Distribution Shift](https://mlsanity.com/paper/2605.16351/) (2026)

## Abstract (arXiv)

Recently, spatio-temporal time-series prediction has developed rapidly, yet existing deep learning methods struggle with learning complex long-term spatio-temporal dependencies efficiently. The long-term spatio-temporal dependency learning brings two new challenges: 1) The long-term temporal sequence naturally includes multiscale information, which is hard to extract efficiently; 2) The multiscale temporal information from different nodes is highly correlated and hard to model. To address these challenges, we propose Spatio-Temporal Mixture of Multiscale Mamba (STM3). STM3 integrates a Multiscale Mamba architecture within a novel Disentangled Mixture-of-Experts (DMoE) framework to capture diverse multiscale information efficiently, while utilizing an adaptive graph causal network to model complex spatial dependencies. To ensure robust representation learning, we introduce a stable routing strategy and a causal contrastive learning strategy, which work in tandem with hierarchical information aggregation to guarantee scale distinguishability. We theoretically prove that STM3 achieves superior routing smoothness and guarantees pattern disentanglement for each expert. Extensive experiments on 10 real-world benchmarks across domains demonstrate STM3's superior performance, achieving state-of-the-art results in long-term spatio-temporal time-series prediction. Notably, on the PEMSD8 dataset, it achieves significant improvements, surpassing the second-best model by 7.1% in MAE, 8.5% in RMSE, and 15.9% in MAPE. Code is available at https://github.com/IfReasonable/STM3_KDD26.