First end-to-end RAG on mobile NPU delivers 18.1x faster prefilling, 4x lower latency and energy than CPU on Snapdragon X Elite with equivalent quality.
FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Prediction
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
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.
years
2026 3verdicts
UNVERDICTED 3representative citing papers
An LLM-augmented framework combining LSTM traffic prediction, structured LLM reasoning, and safety-constrained filtering improves simulated traffic efficiency under dynamic conditions with zero safety violations.
EnergyMamba improves energy consumption prediction accuracy by about 5% and uncertainty quantification by about 6% over 15 baselines on four real-world US datasets by combining graph-enhanced Mamba with adaptive sequential conformalized quantile regression.
citing papers explorer
-
Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite
First end-to-end RAG on mobile NPU delivers 18.1x faster prefilling, 4x lower latency and energy than CPU on Snapdragon X Elite with equivalent quality.
-
LLM-Augmented Traffic Signal Control with LSTM-Based Traffic State Prediction and Safety-Constrained Decision Support
An LLM-augmented framework combining LSTM traffic prediction, structured LLM reasoning, and safety-constrained filtering improves simulated traffic efficiency under dynamic conditions with zero safety violations.
-
EnergyMamba: An Uncertainty-Aware Graph-Enhanced Selective State Space Model for Energy Consumption Prediction
EnergyMamba improves energy consumption prediction accuracy by about 5% and uncertainty quantification by about 6% over 15 baselines on four real-world US datasets by combining graph-enhanced Mamba with adaptive sequential conformalized quantile regression.