Title: Urban Computing: Enabling Spatio-temporal Intelligences in Cities

Abstract: Urban computing aims to tackle the challenges that cities face in the physical world, where tasks and data are naturally endowed with spatial and temporal properties. Affected by many complex factors, urban spaces are massive, dynamic, high-dimensional and nonlinear, and thus are difficult to model. Urban computing creates a data-centric computing framework, which connects urban sensing, urban data management, urban data analytics and providing services into a recurrent process to unlock the power of urban big data (particularly spatial and spatio-temporal data), for an unobtrusive and continuous improvement of people’s lives, city operation systems, and the environment. This talk will present unique properties of spatio-temporal data and the framework that can enable spatio-temporal intelligences. In each layer of urban computing, we will discuss its key research challenges, such as capturing spatio-temporal properties in AI models and cross-domain multimodal data fusion in the physical world, and introduce fundamental methodologies to tackle these challenges. Real-world deployments of urban computing will be also presented at the end of this talk.

Bio: Dr. Yu Zheng is the Vice President and Chief Data Scientist of JD.COM, and the president of JD Intelligent Cities Research. Before Joining JD.COM, he was a senior research manager at Microsoft Research. He is also a chair professor at Shanghai Jiao Tong University and an adjunct professor at Hong Kong University of Science and Technology. Zheng had published over 200 quality papers at prestigious conferences and journals and received over 6,6000 citations (H-index 116). He founded the research field of urban computing, which had been widely followed by world-class scientists. His monograph published by MIT Press becomes the first text book of this field. He was the Editor-in-Chief of ACM Transactions on Intelligent Systems and Technology (2015-2021) and had served as the program co-chair of ICDE 2014 and CIKM 2017. He was a keynote speaker of AAAI 2019, KDD 2019 Plenary Keynote Panel and IJCAI 2019 Industrial Days. He received SIGKDD Test-of-Time Award twice (in 2023 and 2024) and SIGSPATIAL 10-Year-Impact Award four times (in 2019, 2020, 2022, and 2024). He was named one of the Top Innovators under 35 by MIT Technology Review (TR35), an ACM Distinguished Scientist (2016) and an IEEE Fellow (2020), for his contributions to spatio-temporal data mining and urban computing. After joining JD.COM, he has served over 70 cities with his technology, generating a revenue over 1 billion USD.

Title: Generative AI in Urban Planning

Abstract: Urban planning is confronting a convergence of complex and interrelated challenges, including rapid urbanisation, escalating climate risks, infrastructure strain, widening social inequities, and growing expectations for participatory, transparent, and evidence-informed decision-making, and this keynote explores how generative artificial intelligence (GenAI) is reshaping planning thought and practice by augmenting human capacity to analyse complexity, generate design alternatives, and govern cities more intelligently, inclusively, and responsibly. The talk situates contemporary planning challenges within the broader digital transformation of cities, outlining how data-intensive urban systems are redefining planning processes, before providing an overview of the current GenAI technology landscape, including large language models (LLMs), multimodal systems, and agent-based architectures, and explaining their relevance to spatial analysis, policy reasoning, and collaborative planning. It traces the evolution of AI in planning practice from early decision-support tools and GIS-based spatial analytics to today's generative, conversational, and adaptive systems, positioning GenAI within smart and sustainable cities frameworks aligned with long-term resilience, liveability, and equity goals. The keynote then introduces the emerging paradigm of quantum cities, where advanced AI, pervasive sensing, and next-generation computational capabilities interact dynamically with urban systems in near real time. Attention is given to the characteristics and functional roles of LLMs in planning, such as knowledge synthesis, scenario exploration, policy interpretation, design ideation, and stakeholder engagement, alongside an examination of human-AI collaboration patterns that keep planners firmly in the loop as critical thinkers, ethical stewards, and context-aware decision-makers. The talk also highlights prompt engineering as an emerging planning skill for designing effective AI support, and concludes with a critical reflection on the opportunities and challenges of GenAI adoption, including transparency, bias, governance, and capacity building, outlining pathways for its responsible and meaningful integration into urban planning practice.

Bio: Tan Yigitcanlar is a world-leading Australian scholar and one of the most influential figures in urban sustainability, technology, and planning. He is Professor of Urban Studies and Planning at Queensland University of Technology, where he leads transformative research through the QUT Urban AI Hub, and the City 4.0 Lab. He also holds an Adjunct Professorship at the Sepuluh Nopember Institute of Technology, Indonesia. A highly respected member of the Australian Research Council College of Experts, Professor Yigitcanlar has held prestigious academic appointments across six countries and is internationally recognised for his pioneering contributions at the intersection of artificial intelligence, urban innovation, and sustainable city development. He has authored more than 350 journal articles and 35 books, attracting over 36,000 citations and achieving an h-index exceeding 100. Ranked number one in Australia and among the top ten scholars globally in urban studies and planning, Professor Yigitcanlar is widely regarded as a visionary thought leader shaping the global discourse on smart, sustainable, and resilient cities of the future.

We welcome full-length papers, work-in-progress, extended abstracts, and position papers for the regular track. Papers should be submitted in the AAAI 2026 format.

• Both short papers (up to 4 pages) and long papers (up to 8 pages) are accepted.
• Papers previously submitted to other venues are welcome.
• All submissions undergo double-blind peer review.
• Accepted papers will be recommended to top journals for publication, with topics matched to the appropriate venue.

we welcome proposals that outline the content, objectives, and expected contributions to the community.

• Proposals should be no more than 2 pages.

we welcome proposals that outline the content, objectives, and expected contributions to the community.

• Proposals should be no more than 2 pages.