Webinar

Cross-Modal Knowledge Transfer in Time Series AI via Large Vision Models

Jingchao Ni, Assistant Professor, Department of Computer Science, University of Houston

Abstract

Time series analysis has progressed from traditional autoregressive models to deep learning, Transformers, and foundation models (FMs), including large language models (LLMs) and large vision models (LVMs). These advances have expanded model design possibilities and, notably, enabled time series problem-solving across multiple modalities, greatly improving downstream applications in domains such as climate, energy, and healthcare. This talk will provide an overview of recent developments in large FMs for time series, highlighting frameworks for transferring knowledge from other modalities to time series, and identifying the advantages of LVMs over LLMs in cross-modal knowledge transfer. I will then delve into our recent research on LVMs for time series, discussing (1) mainstream techniques for imaging time series; (2) key strengths and limitations of LVMs in time series modeling; and (3) LVM-inspired approaches to time series forecasting. This talk will conclude with applications and future directions. The aim of the talk is to review state-of-the-art AI techniques for time series, highlight unique challenges, and share our recent findings in this promising area.

Speaker Bio

Jingchao Ni is an Assistant Professor in the Department of Computer Science at the University of Houston. Prior to this, he was a researcher at the Data Science Department of NEC Labs from 2018 to 2022 and the AWS AI Labs from 2022 to 2024. He received his Ph.D. degree from the College of IST, The Pennsylvania State University in 2018, advised by Prof. Xiang Zhang. His research is centered around machine learning, data mining, and artificial intelligence, with a focus on time series analysis through cross-modal learning, multimodal integration, and LLM reasoning. His research has been extended to applications in healthcare, biomedicine, cyber-physical systems, and AIOps, and published in refereed conferences including ICLR, ICML, NeurIPS, ACL, AAAI, CVPR, KDD, and WWW, and journals including IEEE TKDE and ACM TKDD, with more than 20 patents filed or granted.