Fields
Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.
Field
Time-series analysis (forecasting, foundation models, anomaly detection, classification)
Time-series ML covers point and probabilistic forecasting (long-horizon multivariate benchmarks and the M-competition tradition), pretrained zero-shot forecasting models, anomaly detection and classification. The field has repeatedly found that simple baselines (seasonal naive, linear models, classical statistics, 1-NN DTW, random convolution kernels) match or beat complex deep models under fair protocols, so credible results depend on standard splits, scale-free metrics (MASE, CRPS), many datasets, and avoiding known evaluation flaws such as look-back tuning on the test set, drop-last batching and point-adjusted F1.