Spatio-Temporal Trajectory Foundation Model: Recent Advances and Future Directions
Foundation models (FMs) have emerged as a powerful paradigm, enabling a diverse range of data analytics and knowledge discovery tasks across scientific fields. Inspired by the success of FMs—particularly large language models—researchers have recently begun to explore spatio-temporal foundation models (STFMs) to improve adaptability and generalization across a wide spectrum of spatio-temporal (ST) tasks. Despite rapid progress, a systematic investigation of trajectory foundation models (TFMs), a crucial subclass of STFMs, is largely lacking. This tutorial addresses this gap by offering a comprehensive overview of recent advances in TFMs, including a taxonomy of existing methodologies and a critical analysis of their strengths and limitations. In addition, the tutorial highlights open challenges and outlines promising research directions to advance spatio-temporal general intelligence through the development of robust, responsible, and transferable TFMs.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
Loading virtual attendance info...
- Selma Lagerløfs Vej 300
- Aalborg East, Nordjyllands Amt
- Denmark 9220
- Room Number: 0.2.11
- Contact Event Host
- Co-sponsored by Sean Bin Yang
Speakers
Sean Bin Yang of Aalborg University
Spatio-Temporal Trajectory Foundation Model: Recent Advances and Future Directions
Foundation models (FMs) have emerged as a powerful paradigm, enabling a diverse range of data analytics and knowledge discovery tasks across scientific fields. Inspired by the success of FMs—particularly large language models—researchers have recently begun to explore spatio-temporal foundation models (STFMs) to improve adaptability and generalization across a wide spectrum of spatio-temporal (ST) tasks. Despite rapid progress, a systematic investigation of trajectory foundation models (TFMs), a crucial subclass of STFMs, is largely lacking. This tutorial addresses this gap by offering a comprehensive overview of recent advances in TFMs, including a taxonomy of existing methodologies and a critical analysis of their strengths and limitations. In addition, the tutorial highlights open challenges and outlines promising research directions to advance spatio-temporal general intelligence through the development of robust, responsible, and transferable TFMs.
Biography:
Sean Bin Yang is an Assistant Professor in CS at Aalborg University. He received his Ph.D. degree in Computer Science from Aalborg University in 2022. His research interests lie in spatio-temporal data mining and artificial intelligence. He has served on program committees and as a reviewer for several leading international conferences and journals, including KDD, PVLDB, IJCAI, AAAI, and TKDE.
Email:
Address:Selma Lagerløfs Vej 300, , Aalborg, Denmark, 9220