BEGIN:VCALENDAR VERSION:2.0 PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4// BEGIN:VEVENT UID:20260426T094559EDT-3551X8lDiH@132.216.98.100 DTSTAMP:20260426T134559Z DESCRIPTION:Foundation Models for Time-Series and Spatio-Temporal Data\n\nB y Flora Salim\n\nProfessor University of New South Wales\n\nDate: Friday\, February 13\, 2026\n Time: 8:00 a.m. to 9:30 a.m.\n Location: Online\n\nAtt end online\n\nView poster\n\n\nAbstract\n\nThis talk explores the foundati ons of AI for time-series and multimodal sensor data\, emphasizing the pre ssing challenges and frontier solutions for real-world spatio-temporal lea rning. Time-series data from sensors in domains such as transport\, energy \, and urban systems are often riddled with missing values\, heterogeneity \, irregular sampling\, high noise\, and label scarcity. These issues are compounded by modality differences across sensors\, domain shifts\, and dy namic environments. We present a comprehensive overview of recent advances \, grounded in a series of foundational works. We also introduce a massive traffic forecasting\, building IoT time-series\, and human mobility datas ets and benchmarks. and pretrained models for generalizable spatio-tempora l inference across diverse urban contexts. We ground this discussion in br oader trends outlined in a recent comprehensive survey on foundation model s for spatio-temporal data science\, which articulates how pretraining\, c ross-domain transfer\, and unified architectures are reshaping the field. \n\nIn summary\, this talk offers a unified vision of foundational AI for time-series and multimodal sensors\, combining robust temporal modeling\, cross-modal alignment\, and scalable representation learning to unlock new capabilities in dynamic\, real-world environments.\n DTSTART:20260213T130000Z DTEND:20260213T143000Z SUMMARY:MCCHE Precision Convergence Webinar Series with Flora Salim URL:/desautels/channels/event/mcche-precision-converge nce-webinar-series-flora-salim-371165 END:VEVENT END:VCALENDAR