Theme: Geometrization of AI (TDAI Speaker Series)
Workshop: Spatial AI and Learned Geometric Representations — Embeddings, Multimodal Data, and Environmental Context
Speaker: Yao-Yi Chiang, University of Minnesota
Date & Time: Thursday, March 12, 2026 · 10:00 AM–12:00 PM (ET)
Location: Pomerene Hall Room 350 (Project Zone)
Food: Morning coffee, light refreshments, and lunch for registered attendees
Host: Dena Asta, Subhadeep Paul (TDAI Geometrization of AI Theme Leads)
This interactive workshop will build on the previous day’s seminar and focus on emerging research directions in Spatial AI and representation learning for geographic and environmental data.
Dr. Chiang will lead discussion around autocorrelation-aware representation learning, spatiotemporal embedding construction, and the integration of structured geographic data with natural language. The session will explore how learned geometric spaces can replace predefined notions of spatial similarity, enabling improved prediction, entity alignment, and semantic reasoning across multimodal data sources.
The workshop will feature short research presentations from Ohio State faculty and graduate students working in spatial modeling, geospatial AI, multimodal learning, and environmental data science. These brief talks will frame guided discussion around interpretability, generalization, robustness, and the geometric foundations of spatial reasoning systems.
Participants will engage in structured discussion and collaborative research prompts aimed at identifying shared challenges and opportunities across disciplines. The workshop is designed to foster dialogue among faculty, postdocs, and students and to highlight ongoing and emerging work at Ohio State related to the Geometrization of AI and Spatial AI systems.
About the Speaker:
Dr. Yao-Yi Chiang is an Associate Professor in the Department of Computer Science & Engineering at the University of Minnesota. His research focuses on spatial artificial intelligence, representation learning, and multimodal geographic data integration.
His work develops machine learning systems that learn embedding spaces grounded in environmental and spatial context, enabling robust prediction, entity disambiguation, and semantic reasoning across heterogeneous geographic data sources.