Related papers: PromptCast: A New Prompt-based Learning Paradigm f…

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…

This paper surveys and organizes research works in a new paradigm in natural language processing, which we dub "prompt-based learning". Unlike traditional supervised learning, which trains a model to take in an input x and predict an output…

The past decade has witnessed significant advances in time series modeling with deep learning. While achieving state-of-the-art results, the best-performing architectures vary highly across applications and domains. Meanwhile, for natural…

Time series forecasting is crucial in strategic planning and decision-making across various industries. Traditional forecasting models mainly concentrate on numerical time series data, often overlooking important textual information such as…

We propose an efficient design of Transformer-based models for multivariate time series forecasting and self-supervised representation learning. It is based on two key components: (i) segmentation of time series into subseries-level patches…

Time-series forecasting (TSF) finds broad applications in real-world scenarios. Prompting off-the-shelf Large Language Models (LLMs) demonstrates strong zero-shot TSF capabilities while preserving computational efficiency. However, existing…

Time series forecasting is prevalent in extensive real-world applications, such as financial analysis and energy planning. Previous studies primarily focus on time series modality, endeavoring to capture the intricate variations and…

Large language models have achieved remarkable success in time series prediction tasks, but their substantial computational and memory requirements limit deployment on lightweight platforms. In this paper, we propose the Symbolic Transition…

Temporal Interaction Graphs (TIGs) are widely utilized to represent real-world systems. To facilitate representation learning on TIGs, researchers have proposed a series of TIG models. However, these models are still facing two tough gaps…

With the advancement of large language models, language-based forecasting has recently emerged as an innovative approach for predicting human mobility patterns. The core idea is to use prompts to transform the raw mobility data given as…

Time series forecasts are often influenced by exogenous contextual features in addition to their corresponding history. For example, in financial settings, it is hard to accurately predict a stock price without considering public sentiments…

Turn-taking prediction models are essential components in spoken dialogue systems and conversational robots. Recent approaches leverage transformer-based architectures to predict speech activity continuously and in real-time. In this study,…

Recent advances in Large Language Models (LLMs) have demonstrated new possibilities for accurate and efficient time series analysis, but prior work often required heavy fine-tuning and/or ignored inter-series correlations. In this work, we…

Time series forecasting underpins applications in finance, healthcare, and environmental monitoring. Despite the success of Time Series Foundation Models (TSFMs), existing approaches operate in a unimodal setting and rely on static prompts…

Self-supervised learning has been actively studied in time series domain recently, especially for masked reconstruction. Most of these methods follow the "Pre-training + Fine-tuning" paradigm in which a new decoder replaces the pre-trained…

We introduce a novel modeling approach for time series imputation and forecasting, tailored to address the challenges often encountered in real-world data, such as irregular samples, missing data, or unaligned measurements from multiple…

Time series forecasting traditionally relies on unimodal numerical inputs, which often struggle to capture high-level semantic patterns due to their dense and unstructured nature. While recent approaches have explored representing time…

With the evolution of large language models (LLMs), there is growing interest in leveraging LLMs for time series tasks. In this paper, we explore the characteristics of LLMs for time series forecasting by considering various existing and…

Recent innovations in diffusion probabilistic models have paved the way for significant progress in image, text and audio generation, leading to their applications in generative time series forecasting. However, leveraging such abilities to…

Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus achieving efficiency…