The field of time series forecasting is witnessing significant advancements with the development of novel techniques and frameworks. Researchers are exploring new methods to improve predictive performance, such as leveraging variational mode decomposition, seasonal and trend decomposition, and physics-informed neural networks. These approaches aim to capture complex patterns and structures in time series data, leading to more accurate forecasts. Notably, the use of adaptive granularity and segment-wise decoding is showing promise in addressing temporal heterogeneity in multivariate time series forecasting. In the realm of quantum computing, innovations in compiler design, quantum simulation, and machine learning are pushing the boundaries of what is possible. The development of verified compilers, such as QBlue, and the introduction of new quantum algorithms, like Kolmogorov-Arnold Networks, are expected to have a significant impact on the field. Furthermore, research on lightweight targeted estimation of layout noise and single-shot quantum machine learning models is helping to mitigate the challenges associated with quantum computing. Some noteworthy papers in this area include: VMDNet, which proposes a causality-preserving framework for time series forecasting with leakage-free samplewise variational mode decomposition and multibranch decoding. Physics-informed time series analysis with Kolmogorov-Arnold Networks under Ehrenfest constraints, which introduces a fundamentally new approach to forecasting the entire temporal evolution of quantum systems. You Only Measure Once, which proposes a simple yet effective design for single-shot quantum machine learning models that achieves accurate inference with dramatically fewer measurements.