Related papers: Retrieval Mechanisms Surpass Long-Context Scaling …
Time-series forecasting models (TSFM) have evolved from classical statistical methods to sophisticated foundation models, yet understanding why and when these models succeed or fail remains challenging. Despite this known limitation, time…
At the heart of time-series forecasting (TSF) lies a fundamental challenge: how can models efficiently and effectively capture long-range temporal dependencies across ever-growing sequences? While deep learning has brought notable progress,…
Over the past few decades, the hydrology community has witnessed notable advancements in streamflow prediction, particularly with the introduction of cutting-edge machine-learning algorithms. Recurrent neural networks, especially Long…
Time Series Foundation Models (TSFMs) have introduced zero-shot prediction capabilities that bypass the need for task-specific training. Whether these capabilities translate to mission-critical applications such as electricity demand…
Time series forecasting is vital in diverse sectors such as energy and transportation, where non-stationary dynamics are deeply intertwined with external events in other modalities such as texts. However, incorporating natural…
Existing data-driven methods rely on the extraction of static features from time series to approximate the material removal rate (MRR) of semiconductor manufacturing processes such as chemical mechanical polishing (CMP). However, this leads…
Time series forecasting plays a critical role in domains such as transportation, energy, and meteorology. Despite their success, modern deep forecasting models are typically trained to minimize point-wise prediction loss without leveraging…
Supervised Fine-Tuning (SFT) on long Chain-of-Thought (CoT) trajectories has become a pivotal phase in building large reasoning models. However, how CoT trajectories from different sources influence the generalization performance of models…
Time series are generated in diverse domains such as economic, traffic, health, and energy, where forecasting of future values has numerous important applications. Not surprisingly, many forecasting methods are being proposed. To ensure…
Large pre-trained time series foundation models (TSFMs) have demonstrated promising zero-shot performance across a wide range of domains. However, a question remains: Do TSFMs succeed by memorizing patterns in training data, or do they…
Although the rise of large language models (LLMs) has introduced new opportunities for time series forecasting, existing LLM-based solutions require excessive training and exhibit limited transferability. In view of these challenges, we…
Time-series forecasting in real-world applications such as finance and energy often faces challenges due to limited training data and complex, noisy temporal dynamics. Existing deep forecasting models typically supervise predictions using…
RNN-based methods have faced challenges in the Long-term Time Series Forecasting (LTSF) domain when dealing with excessively long look-back windows and forecast horizons. Consequently, the dominance in this domain has shifted towards…
Recent Transformer-based large language models (LLMs) demonstrate in-context learning ability to perform various functions based solely on the provided context, without updating model parameters. To fully utilize the in-context capabilities…
Sequence modeling faces challenges in capturing long-range dependencies across diverse tasks. Recent linear and transformer-based forecasters have shown superior performance in time series forecasting. However, they are constrained by their…
Multivariate time series forecasting (MTSF) plays a vital role in numerous real-world applications, yet existing models remain constrained by their reliance on a limited historical context. This limitation prevents them from effectively…
Time-Series Foundation Models (TSFMs) are rapidly transitioning from research prototypes to core components of critical decision-making systems, driven by their impressive zero-shot forecasting capabilities. However, as their deployment…
The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…
Recent time-series foundation models exhibit strong abilities to predict physical systems. These abilities include zero-shot forecasting, in which a model forecasts future states of a system given only a short trajectory as context, without…
Large Language Models (LLMs) often falter in complex reasoning tasks due to their static, parametric knowledge, leading to hallucinations and poor performance in specialized domains like mathematics. This work explores a fundamental…