LLMs Meet Cross-Modal Time Series Analytics: Overview and Directions

2025/07/13 by Liu, Chenxi, Miao, Hao, Long, Cheng +3 · 1 citation
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2507.10620

Abstract

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.

Citations

• Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language
• Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillation
• LLM-Powered User Simulator for Recommender System
• C2F-TP: A Coarse-to-Fine Denoising Framework for Uncertainty-Aware Trajectory Prediction
• EF-LLM: Energy Forecasting LLM with AI-assisted Automation, Enhanced Sparse Prediction, Hallucination Detection
• Unsupervised Time Series Anomaly Prediction with Importance-based Generative Contrastive Learning
• From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection
• TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment
• Score-CDM: Score-Weighted Convolutional Diffusion Model for Multivariate Time Series Imputation
• LightTR: A Lightweight Framework for Federated Trajectory Recovery
• A Unified Replay-based Continuous Learning Framework for Spatio-Temporal Prediction on Streaming Data
• ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model
• CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning
• TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
• Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning
• Large Language Models for Time Series: A Survey
• Spatial-Temporal Large Language Model for Traffic Prediction
• DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
• Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach
• Large Language Models Are Zero-Shot Time Series Forecasters
• TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• LightCTS: A Lightweight Framework for Correlated Time Series Forecasting
• Leveraging Language Foundation Models for Human Mobility Forecasting
• Contrastive Learning for Unsupervised Domain Adaptation of Time Series
• A Survey on Neural Open Information Extraction: Current Status and Future Directions
• Time Series Supplier Allocation via Deep Black-Litterman Model

Cited by

• Spatio-Temporal Trajectory Foundation Model - Recent Advances and Future Directions

Related

• Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era
• Large Language Models for Time Series: A Survey
• Empowering Time Series Analysis with Large Language Models: A Survey
• Large Language models for Time Series Analysis: Techniques, Applications, and Challenges
• FiCoTS: Fine-to-Coarse LLM-Enhanced Hierarchical Cross-Modality Interaction for Time Series Forecasting