BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Copenhagen
BEGIN:DAYLIGHT
DTSTART:20260329T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261025T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260911T120120Z
UID:309FD270-12DA-4AC1-BB7D-E4F5E7ECF47C
DTSTART;TZID=Europe/Copenhagen:20260911T130000
DTEND;TZID=Europe/Copenhagen:20260911T140000
DESCRIPTION:Foundation models are changing the landscape of artificial inte
 lligence by enabling a single pretrained model to adapt to a wide range of
  tasks. This presentation explores whether a similar paradigm can be appli
 ed for human mobility\, where data are inherently heterogeneous and irregu
 lar. I will first introduce the concept of human mobility foundation model
 s and discuss the main approaches currently emerging in the field. I will 
 then present an ongoing survey and comparative evaluation of existing mode
 ls\, focusing on the challenges of establishing a common and reproducible 
 testing methodology. Finally\, I will present my own research direction\, 
 focusing on space-invariant tokenization\, and discuss future directions f
 or developing general-purpose models for human mobility data.\n\nCo-sponso
 red by: Sean Bin Yang\n\nSpeaker(s): \, Colombin\n\nRoom: 0.2.90 \, Bldg: 
 SLV300\, Selma Lagerløfs Vej 300\, Aalborg Ø\, Nordjyllands Amt\, Denmar
 k
LOCATION:Room: 0.2.90 \, Bldg: SLV300\, Selma Lagerløfs Vej 300\, Aalborg 
 Ø\, Nordjyllands Amt\, Denmark
ORGANIZER:seany@cs.aau.dk
SEQUENCE:11
SUMMARY:Foundation Models for Human Mobility: From Current Approaches to Ne
 w Directions
URL;VALUE=URI:https://events.vtools.ieee.org/m/576498
X-ALT-DESC:Description: <br /><p>Foundation models are changing the landsca
 pe of artificial intelligence by enabling a single pretrained model to ada
 pt to a wide range of tasks. This presentation explores whether a similar 
 paradigm can be applied for human mobility\, where data are inherently het
 erogeneous and irregular. I will first introduce the concept of human mobi
 lity foundation models and discuss the main approaches currently emerging 
 in the field. I will then present an ongoing survey and comparative evalua
 tion of existing models\, focusing on the challenges of establishing a com
 mon and reproducible testing methodology. Finally\, I will present my own 
 research direction\, focusing on space-invariant tokenization\, and discus
 s future directions for developing general-purpose models for human mobili
 ty data.</p>
END:VEVENT
END:VCALENDAR