Related papers: UniCast: A Unified Framework for Instance-Conditio…

With the rapid development of diffusion models in image generation, the demand for more powerful and flexible controllable frameworks is increasing. Although existing methods can guide generation beyond text prompts, the challenge of…

Pre-trained foundation models (FMs) have shown exceptional performance in univariate time series forecasting tasks. However, several practical challenges persist, including managing intricate dependencies among features and quantifying…

Time series forecasting plays a crucial role in decision-making across many real-world applications. Despite substantial progress, most existing methods still treat forecasting as a static, single-pass regression problem. In contrast, human…

Time series foundation models (TSFMs) have recently achieved remarkable success in universal forecasting by leveraging large-scale pretraining on diverse time series data. Complementing this progress, incorporating frequency-domain…

Most existing single-modal time series models rely solely on numerical series, which suffer from the limitations imposed by insufficient information. Recent studies have revealed that multimodal models can address the core issue by…

Irregular multivariate time series forecasting (IMTSF) is challenging due to non-uniform sampling and variable asynchronicity. These irregularities violate the equidistant assumptions of standard models, hindering local temporal modeling…

Time series forecasting aims to model temporal dependencies among variables for future state inference, holding significant importance and widespread applications in real-world scenarios. Although deep learning-based methods have achieved…

To gain finer regional forecasts, many works have explored the regional integration from the global atmosphere, e.g., by solving boundary equations in physics-based methods or cropping regions from global forecasts in data-driven methods.…

Current Text-to-Speech (TTS) systems typically use separate models for speech-prompted and text-prompted timbre control. While unifying both control signals into a single model is desirable, the challenge of cross-modal alignment often…

Multivariate time series data provide a robust framework for future predictions by leveraging information across multiple dimensions, ensuring broad applicability in practical scenarios. However, their high dimensionality and mixing…

Reliable uncertainty quantification is critical in multivariate time series forecasting problems arising in domains such as energy systems and transportation networks, among many others. Although Transformer-based architectures have…

Multimodal learning has seen great success mining data features from multiple modalities with remarkable model performance improvement. Meanwhile, federated learning (FL) addresses the data sharing problem, enabling privacy-preserved…

Multivariate time series classification (MTSC) plays a crucial role in various domains, including biomedical signal analysis and motion monitoring. However, existing approaches, particularly deep learning models, often require high…

Cross-domain generalization is very important in Time Series Forecasting because similar historical information may lead to distinct future trends due to the domain-specific characteristics. Recent works focus on building unimodal time…

Time series foundation models have shown impressive performance on a variety of tasks, across a wide range of domains, even in zero-shot settings. However, most of these models are designed to handle short univariate time series as an…

Accurate weather forecasts are important for disaster prevention, agricultural planning, etc. Traditional numerical weather prediction (NWP) methods offer physically interpretable high-accuracy predictions but are computationally expensive…

Demand is spiking in industrial fields for multidisciplinary forecasting, where a broad spectrum of sectors needs planning and forecasts to streamline intelligent business management, such as demand forecasting, product planning, inventory…

With large quantities of data typically available nowadays, forecasting models that are trained across sets of time series, known as Global Forecasting Models (GFM), are regularly outperforming traditional univariate forecasting models that…

Conventional forecasting methods rely on unimodal time series data, limiting their ability to exploit rich textual information. Recently, large language models (LLMs) and time series foundation models (TSFMs) have demonstrated powerful…

Transformer-based models have greatly pushed the boundaries of time series forecasting recently. Existing methods typically encode time series data into $\textit{patches}$ using one or a fixed set of patch lengths. This, however, could…