presentations
A list of our past presentations.
- ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary PlanningYihong Tang, Zhaokai Wang, Ao Qu, Yihao Yan, ... Zhan Zhao, Wei Ma, (2024)Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track , pp. 1413–1432
| 2025.09.08 |
Tracking carbon emissions in near-real-time is essential for informing timely climate action and evaluating the effectiveness of mitigation policies. In this talk, Dr. Dou will introduce her work on developing the world’s first high-resolution, near-real-time datasets of CO2 and CH4 emissions by integrating satellite observations, ground-based activity data, and machine learning. The innovative methods are adopted in multiple international collaborative projects such as Carbon Monitor and GRACED, providing daily CO2 and CH4 emission estimates across multiple sectors for global coverage. Dr. Dou will also share how these data have been used to assess the immediate impact of socio-economic changes, such as the pandemic or energy crises, on emissions. Moving forward, this research aspires to shed light on the dance between the energy transition and GHG emissions, offering insights to guide future policy decisions and technological advancements.
Dr. Xinyu Dou is a Postdoctoral Research Fellow in the Department of Earth System Science at Stanford University, supported by the Stanford Energy Postdoctoral Fellowship. Her research centers on near-real-time monitoring of anthropogenic greenhouse gas emissions, with a particular focus on integrating top-down (satellite and ground atmospheric observations) and bottom-up (activity-based) data. She earned her PhD in ecology from Tsinghua University under the supervision of Prof. Zhu Liu, developing GRACED, the world’s first near-real-time, grid-level carbon emissions database on a daily scale. Xinyu is a key member of the international Carbon Monitor project and a contributor to the Global Carbon Project. Currently, she is collaborating with Prof. Rob Jackson to advance the study of methane emissions monitoring. Xinyu’s general research interests include high-resolution carbon emissions monitoring, carbon footprint, methane leak and energy transition.
| 2025.08.27 |
Cities are complex systems shaped by rich patterns across space and time. Understanding and predicting these patterns requires more than accurate models—it requires trustworthy spatial intelligence. In this talk, Dingyi Zhuang will present his research agenda along three complementary directions. First, he develops spatiotemporal and multimodal modeling frameworks with graph neural networks and tensor learning to capture and predict correlations across space and time. Second, he designs uncertainty quantification and calibration techniques to ensure that the relationships learned by these models are reliable, interpretable, and fair. Third, he extends toward spatial reasoning, leveraging large language models and vision-language models to embed physical constraints and social norms into learned structures, advancing toward richer world models of cities. Together, these directions outline a coherent vision: from learning relationships in spatiotemporal data, to validating their trustworthiness, to reasoning about the rules that govern urban environments.
Dingyi Zhuang is a final-year Ph.D. candidate in Transportation at MIT’s JTL Transit Lab, supervised by Prof. Jinhua Zhao. He received his M.Eng. from McGill University and B.Sc. from Shanghai Jiao Tong University. His research develops trustworthy AI and machine learning methods for transportation and urban systems, spanning spatiotemporal data modeling, uncertainty quantification, intelligent transportation systems, and generative AI for spatial reasoning and planning. Dingyi has also worked as a machine learning intern at the Bosch Center for AI, Morgan Stanley’s ML research group, and the Chicago Transit Agency. He received the UPS Fellowship at MIT, and won four workshop Best Paper Awards, with publications bridging both leading transportation journals (TR-C, AAP, IEEE T-ITS) and top computer science venues (IEEE TPAMI, ICLR (Spotlight), NeurIPS, AAAI, KDD, and EMNLP). Looking ahead, he envisions spatial intelligence as a foundation for trustworthy world models that integrate data with physical and social reasoning for urban decision-making.
