Dingyi Zhuang (庄丁奕)
Scholar

Dingyi Zhuang (庄丁奕)

Google Scholar ID: 8fYfUB0AAAAJ
MIT
Machine LearningUrban ComputingTime SeriesIntelligent TransportationLLM
Citations & Impact
All-time
Citations
758
 
H-index
17
 
i10-index
19
 
Publications
20
 
Co-authors
17
list available
Publications
20 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • 2025: Paper 'Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Composite Spatial Reasoning' received Best Paper Award at IJCAI MKLM Workshop
  • 2025: Paper 'Dynamic autoregressive tensor factorization for pattern discovery of spatiotemporal systems' accepted by IEEE TPAMI
  • 2025: Paper 'Mitigating Spatial Disparity in Urban Prediction Using Residual-Aware Spatiotemporal Graph Neural Networks' received Best Paper Award at WWW WebsST 2025, also accepted at WWW 2025 and TRB 2025
  • 2025: Paper 'Reliable Imputation of Incomplete Crash Data for Predicting Driver Injury Severity' accepted by Accident Analysis & Prevention (AAP)
  • 2025: Paper 'GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks' accepted at ICLR 2025 (Spotlight)
  • 2025: Paper 'Time Series Supplier Allocation via Deep Black-Litterman Model' accepted at AAAI 2025 (Oral)
  • 2024: Paper 'ItiNera: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning' accepted at EMNLP 2024 (Industry Track) and received Best Paper Award at KDD UrbComp 2024
  • 2024: Paper 'Uncertainty-aware Probabilistic Graph Neural Networks for Road-level Traffic Crash Prediction' accepted by Accident Analysis & Prevention (AAP)
  • 2024: Paper 'SAUC: Sparsity-Aware Uncertainty Calibration for Spatiotemporal Prediction with Graph Neural Networks' accepted at SIGSPATIAL 2024 (Oral) and presented as Spotlight at TGL Workshop, NeurIPS 2023