Can a sequence model remain competitive with only a few thousand parameters and an explicitly auditable prediction interface? We introduce ALPHABET, a compact linear-time model that compresses tempora...
arXiv:2603.19198v3 Announce Type: replace Abstract: We introduce the exponentially weighted signature (EWS), a continuous-time model that computes iterated integrals of a path, where each increment i...
arXiv:2608. 01587v1 Announce Type: cross Abstract: Machine-learning benchmarks often pair a label that aggregates a long temporal horizon with input observed through one or a few short windows.
arXiv:2605. 15690v2 Announce Type: replace Abstract: Accurate and efficient long-term multivariate time series forecasting requires capturing recurring temporal structure while keeping inference cheap across many variables and horizons.
arXiv:2608. 16098v1 Announce Type: cross Abstract: Multivariate time-series forecasting faces a structural dilemma: sharing one temporal predictor across variables is parameter-efficient but forces heterogeneous variables through an identical history-to-future map, whereas learning an independent predictor per variable restores flexibility at a cost that grows with the product of variable count, context length, and horizon.
arXiv:2606. 17572v1 Announce Type: new Abstract: Learned dynamics models often answer global physical questions, such as fault severity or impact stiffness, by pooling a per-step feature sequence into one readout vector.
arXiv:2607. 13006v1 Announce Type: new Abstract: A growing family of indices scores how predictable a series is from its spectrum.
arXiv:2606. 19412v1 Announce Type: new Abstract: Time series forecasting leverages historical patterns to predict future values, but traditional methods face challenges when dealing with complex, non-stationary patterns that are difficult to memorize during training.
arXiv:2608. 14691v1 Announce Type: new Abstract: Sequence models are conventionally distinguished by their backbone, the mechanism that routes information across positions, such as attention or recurrence.
arXiv:2609.15344v1 Announce Type: new Abstract: We study the adaptation of pretrained language models to univariate time-series forecasting through a parameter-efficient transfer learning framework,...
arXiv:2609.06006v1 Announce Type: cross Abstract: Deep learning for time series has progressed through successive architectural paradigms, from recurrent networks and transformers to structured state...
The paper introduces CoSPOT, an online time series forecasting framework that uses a frozen pre‑trained large language model (LLM) as the core forecaster. CoSPOT adapts to evolving data by applying compositional spectral prompts—frequency‑domain basis prompts weighted by their amplitudes—allowing the model to represent unseen patterns as new combinations of learned bases while updating few parameters. Experiments on real‑world datasets show CoSPOT’s effectiveness in extended online phases and cross‑dataset scenarios with significant distribution shifts.