Yingxue Zhang

Yingxue Zhang is an Assistant Professor in the Computer Science Department at Binghamton University's School of Computing. She holds a PhD in Data Science from Worcester Polytechnic Institute (2022), an MS in Financial Engineering from Stevens Institute of Technology (2018), and a BS in Computer Science from Shanghai Jiao Tong University (2016). Her research focuses on deep learning, meta-learning, imitation learning, and spatial-temporal data mining, with applications to smart cities and public safety. She has advised PhD students Xinbo Zhao and Yuhang Liu, and an MS student Junjie Xu. Her work includes developing generative adversarial networks (GANs) for urban traffic prediction and spatial-temporal data analysis, as well as large-scale solar energy forecasting. She serves on technical program committees for top conferences like KDD, NeurIPS, and ICLR. She teaches courses in data mining, machine learning, and information systems.

Education

• PhD in Data Science, Worcester Polytechnic Institute (2022)
• MS in Financial Engineering, Stevens Institute of Technology (2018)
• BS in Computer Science, Shanghai Jiao Tong University (2016)

Research Interests

• Deep learning and AI techniques for spatial-temporal big data
• Urban dynamics prediction using large language models
• Generative adversarial networks (GANs) for traffic estimation
• Human behavior analysis and decision-making modeling
• Meta-learning and multi-task reinforcement learning

Recent Publications

Her research highlights include UrbanMind (KDD 2025), C3-GAN+ (TKDD 2024), and SolarCube (NeurIPS 2024), which demonstrate innovations in spatio-temporal modeling, urban systems analysis, and energy forecasting. Her work often bridges theory and real-world applications in smart cities.

Collaborations & Leadership

Dr. Zhang actively participates in organizing top-tier conferences, including serving as a TPC member for KDD 2025, NeurIPS 2025, ICLR 2025, and others. She leads a research group at Binghamton focused on advancing AI-driven solutions for urban and environmental challenges.