LLM-CMTS - SSTD 2025

Introduction

Large Language Models (LLMs) have emerged as a promising paradigm for time series analytics, leveraging their massive parameters and the shared sequential nature of textual and time series data. However, a cross-modality gap exists between time series and textual data, as LLMs are pre-trained on textual corpora and are not inherently optimized for time series. In this tutorial, we provide an up-to-date overview of LLM-based cross-modal time series analytics. We introduce a taxonomy that classifies existing approaches into three groups based on cross-modal modeling strategies, e.g., conversion, alignment, and fusion, and then discuss their applications across a range of downstream tasks. In addition, we summarize several open challenges. This tutorial aims to expand the practical application of LLMs in solving real-world problems in cross-modal time series analytics while balancing effectiveness and efficiency. Participants will gain a thorough understanding of current advancements, methodologies, and future research directions in cross-modal time series analytics. Our tutorial slides can be found here.

Intended Audience

This tutorial is designed for a broad audience of researchers who are interested in time series analytics, LLMs, and multimodal learning.

We assume participants have a basic understanding of machine learning and sequential data modeling, making the content accessible to professionals and students alike. Attendees will gain a comprehensive understanding of the methodologies and challenges in cross-modal time series analytics. They will also become familiar with emerging applications across domains, and will learn how to integrate textual knowledge into time series tasks using LLMs.

Tutorial Outline

Time	Session	Presenter
11:00-11:15	Welcome & Introduction	Chenxi Liu
11:15-11:30	LLMs for TS Outlier Detection	Hao Miao
11:30-11:50	Spatio-Temporal LLMs	Ziyue Li
11:50-12:15	Cross-Modal Modeling	Chenxi Liu
12:15-12:25	Future Directions, Q&A	All