BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030247Z
LOCATION:Hall 3F/G Concourse\, Level 3
DTSTART;TZID=Asia/Hong_Kong:20251216T090000
DTEND;TZID=Asia/Hong_Kong:20251216T180000
UID:siggraphasia_SIGGRAPH Asia 2025_sess205_pos_436@linklings.com
SUMMARY:Enabling Visually Aware Conversational Data Visualization Through 
 LLM Augmentation
DESCRIPTION:Omar Mena (King Abdullah University of Science and Technology 
 (KAUST)), Alexandre Kouyoumdjian (KAUST), Lonni Besançon (Linköping Univer
 sity), Michael Gleicher (University of Wisconsin Madison), Ivan Viola (Kin
 g Abdullah University of Science and Technology (KAUST)), and Anders Ynner
 man (Linköping University)\n\nWe introduce a method that makes Large Langu
 age Models both data-aware and visually-aware by augmenting them with stru
 ctured metadata. Visual features and textual descriptions are combined int
 o a compact JSON file, enabling accurate, context-specific answers without
  fine-tuning. Tested on geospatial datasets, a user study confirmed its ef
 fectiveness and user appeal.\n\nRegistration Category: Enhanced Access, Ex
 hibit & Experience Access, Experience Hall Exhibitor, Full Access, Full Ac
 cess Supporter, Trade Exhibitor\n\n
END:VEVENT
END:VCALENDAR