Recent advancements in time-series forecasting are increasingly focused on enhancing model efficiency and adaptability, particularly for deployment in constrained environments like edge devices. New architectures, such as the Fourier-Efficient Adaptive Temporal Hierarchy Forecaster, demonstrate that accurate long-term forecasting can be achieved with minimal parameters, making them suitable for real-time industrial applications. Meanwhile, the Phasor Transformer introduces a novel approach to mitigate the computational bottlenecks associated with traditional attention mechanisms, allowing for scalable modeling of complex temporal dynamics. Additionally, efforts to integrate textual data into forecasting models are gaining traction, with approaches like the Temporal Evolution Semantic Space showing promise in bridging the gap between qualitative and quantitative data. However, the field is also grappling with the need for more nuanced evaluation metrics, as current benchmarks may obscure the true performance of models, particularly in non-stationary contexts. This shift emphasizes the importance of domain-specific approaches and robust comparisons against classical methods.
Time-series forecasting is fundamental in industrial domains like manufacturing and smart factories. As systems evolve toward automation, models must operate on edge devices (e.g., PLCs, microcontroll...
Accurate forecasting of multivariate time series remains challenging due to the need to capture both short-term fluctuations and long-range temporal dependencies. Transformer-based models have emerged...
Transformer models have redefined sequence learning, yet dot-product self-attention introduces a quadratic token-mixing bottleneck for long-context time-series. We introduce the \textbf{Phasor Transfo...
Incorporating textual information into time-series forecasting holds promise for addressing event-driven non-stationarity; however, a fundamental modality gap hinders effective fusion: textual descrip...
Time-series foundation models have emerged as a new paradigm for forecasting, yet their ability to effectively leverage exogenous features -- critical for electricity demand forecasting -- remains unc...
Accurate short-term air-quality forecasting is essential for public health protection and urban management, yet many recent forecasting frameworks rely on complex, data-intensive, and computationally ...
We argue that the current practice of evaluating AI/ML time-series forecasting models, predominantly on benchmarks characterized by strong, persistent periodicities and seasonalities, obscures real pr...