The paper introduces a hybrid attention model that learns a unified time‑aware patch representation for irregular multivariate time series (IMTS) forecasting. It employs a time‑aware patch encoding to embed variable‑length intra‑patch timestamps, a time bias attention mechanism to adjust for temporal misalignment and asynchronous cross‑channel dependencies, and a hybrid causal mask on a decoder‑only Transformer to balance historical context with autoregressive forecasting. The authors also curate VersaTSA, a 30 B‑observation dataset preserving native sampling sparsity, and demonstrate state‑of‑the‑art zero‑shot performance on three IMTS benchmarks while remaining competitive on regular MTS tasks.
arXiv:2605. 28166v3 Announce Type: replace-cross Abstract: Irregular Multivariate Time Series (IMTS) are common in practice, yet their irregular sampling complicates effective modeling.
arXiv:2405. 16440v2 Announce Type: replace-cross Abstract: In recent years, Transformers have become the de-facto architecture for long-term time series forecasting (LTSF), yet they face challenges associated with the self-attention mechanism, including quadratic complexity and permutation-invariant bias.
arXiv:2607. 02344v1 Announce Type: cross Abstract: Transformer architectures have shown strong potential in time series forecasting, where multi-head self-attention is widely used to capture temporal dependencies across historical timestamps.
NeST is a framework that adapts large language models (LLMs) for continuous time‑series forecasting by creating neighborhood‑aware text prototypes and aligning them with temporal representations through a nearest‑neighbor contrastive objective. It retrieves the most relevant prototypes and uses them to conditionally modulate time‑series features, enabling more effective integration of textual and temporal information. Experiments show that NeST outperforms state‑of‑the‑art methods on eight benchmarks, reduces MSE by 1.2% for long‑term forecasting, improves zero‑shot forecasting by 4.9%, and boosts R² by 3.3% on a real‑world photovoltaic power forecasting task.
arXiv:2606. 05878v1 Announce Type: new Abstract: Foundation models mark a profound paradigm shift in time series modeling, with task-specific models being superseded by general-purpose zero-shot models.
arXiv:2605. 11287v2 Announce Type: replace-cross Abstract: A persistent paradox in time-series forecasting is that structurally simple MLP and linear models often outperform high-capacity Transformers.
arXiv:2608. 13262v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) have advanced primarily through architectural innovation, while training regimes for large-scale heterogeneous corpora remain under-explored.
arXiv:2601.20845v2 Announce Type: replace Abstract: Time series forecasting is a fundamental problem with applications in climate, energy, healthcare, and finance. Many existing approaches require do...
arXiv:2606. 08601v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently demonstrated impressive potential for time series forecasting.
arXiv:2606. 10798v1 Announce Type: new Abstract: Pretrained time series foundation models (TSFMs) have enabled zero-shot forecasting on unseen target series.
arXiv:2606. 07291v1 Announce Type: new Abstract: Multivariate time-series forecasting requires models to reason over temporal dynamics, cross-variable dependencies, and historical input-output correspondences.
arXiv:2606. 01289v1 Announce Type: new Abstract: Zero-shot time series forecasting aims to predict future values for previously unseen series, requiring models to generalize temporal dynamics beyond the training distribution.