# FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Prediction

arXiv: https://arxiv.org/abs/2604.13453 · HTML: https://mlsanity.com/paper/2604.13453/

## Key facts

- Cited by 3 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 53 of its 82 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## 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 53)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [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)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [HiPPO: Recurrent Memory with Optimal Polynomial Projections](https://mlsanity.com/paper/2008.07669/) (2020)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [GMAN: A Graph Multi-Attention Network for Traffic Prediction](https://mlsanity.com/paper/1911.08415/) (2019)
- [U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation](https://mlsanity.com/paper/2401.04722/) (2024)
- [VideoMamba: State Space Model for Efficient Video Understanding](https://mlsanity.com/paper/2403.06977/) (2024)
- [Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting](https://mlsanity.com/paper/2012.09641/) (2020)
- [FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving](https://mlsanity.com/paper/2505.17685/) (2025)
- [Graph Neural Controlled Differential Equations for Traffic Forecasting](https://mlsanity.com/paper/2112.03558/) (2021)
- [AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents](https://mlsanity.com/paper/2506.00641/) (2025)
- [JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation](https://mlsanity.com/paper/2509.22548/) (2025)
- [Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version](https://mlsanity.com/paper/2203.15737/) (2022)
- [MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents](https://mlsanity.com/paper/2601.03236/) (2026)
- [Parameter-Efficient and Student-Friendly Knowledge Distillation](https://mlsanity.com/paper/2205.15308/) (2022)
- [FastPillars: A Deployment-friendly Pillar-based 3D Detector](https://mlsanity.com/paper/2302.02367/) (2023)
- [HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval](https://mlsanity.com/paper/2512.02792/) (2025)
- [DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignment](https://mlsanity.com/paper/2403.18274/) (2024)
- [Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges](https://mlsanity.com/paper/2601.20913/) (2026)
- [FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation](https://mlsanity.com/paper/2310.00339/) (2023)
- [GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning](https://mlsanity.com/paper/2502.12913/) (2025)
- [Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations](https://mlsanity.com/paper/2602.19320/) (2026)
- [AutoNeural: Co-Designing Vision-Language Models for NPU Inference](https://mlsanity.com/paper/2512.02924/) (2025)
- [Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance](https://mlsanity.com/paper/2509.21486/) (2025)
- [Learn from Global Correlations: Enhancing Evolutionary Algorithm via Spectral GNN](https://mlsanity.com/paper/2412.17629/) (2024)

## Built on by (most cited first, 3 of 3)

- [Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite](https://mlsanity.com/paper/2606.11257/) (2026)
- [LLM-Augmented Traffic Signal Control with LSTM-Based Traffic State Prediction and Safety-Constrained Decision Support](https://mlsanity.com/paper/2604.23902/) (2026)
- [Enhancing Human Mobility Prediction with Spatially Aware LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2609.14227/) (2026)

## Abstract (arXiv)

Traffic forecasting requires modeling complex temporal dynamics and long-range spatial dependencies over large sensor networks. Existing methods typically face a trade-off between expressiveness and efficiency: Transformer-based models capture global dependencies well but suffer from quadratic complexity, while recent selective state-space models are computationally efficient yet less effective at modeling spatial interactions in graph-structured traffic data. We propose FAST, a unified framework that combines attention and state-space modeling for scalable spatiotemporal traffic forecasting. FAST adopts a Temporal-Spatial-Temporal architecture, where temporal attention modules capture both short- and long-term temporal patterns, and a Mamba-based spatial module models long-range inter-sensor dependencies with linear complexity. To better represent heterogeneous traffic contexts, FAST further introduces a learnable multi-source spatiotemporal embedding that integrates historical traffic flow, temporal context, and node-level information, together with a multi-level skip prediction mechanism for hierarchical feature fusion. Experiments on PeMS04, PeMS07, and PeMS08 show that FAST consistently outperforms strong baselines from Transformer-, GNN-, attention-, and Mamba-based families. In particular, FAST achieves the best MAE and RMSE on all three benchmarks, with up to 4.3% lower RMSE and 2.8% lower MAE than the strongest baseline, demonstrating a favorable balance between accuracy, scalability, and generalization.