Saved in:
Bibliographic Details
Main Authors: Yang, Sean Bin, Sun, Ying, Cheng, Yunyao, Lin, Yan, Torp, Kristian, Hu, Jilin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.20729
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912729550290944
author Yang, Sean Bin
Sun, Ying
Cheng, Yunyao
Lin, Yan
Torp, Kristian
Hu, Jilin
author_facet Yang, Sean Bin
Sun, Ying
Cheng, Yunyao
Lin, Yan
Torp, Kristian
Hu, Jilin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20729
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spatio-Temporal Trajectory Foundation Model - Recent Advances and Future Directions
Yang, Sean Bin
Sun, Ying
Cheng, Yunyao
Lin, Yan
Torp, Kristian
Hu, Jilin
Machine Learning
Artificial Intelligence
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.
title Spatio-Temporal Trajectory Foundation Model - Recent Advances and Future Directions
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.20729