Decision-making occurs every day across domains, from logistics and transportation to energy, to make the most of our resources. The advancement of AI/ML has provided unprecedented opportunity to augment—not replace—classical operations research (OR), enabling data-driven forecasting, scheduling, optimization, and sequential decision-making. My research aims to integrate AI/ML and OR to design both efficient and sustainable decision-making pipelines, for practitioners to deploy and generalize intelligent decision systems at scale. I am particularly interested in applied AI for urban mobility and logistics systems, identifying their sustainability opportunities while maintain service efficiency.

I am currently focusing on three key areas:

1. fusing generative AI and OR to transform combinatorial optimization;
2. optimizing the on-demand operation of shared mobility systems;
3. evaluating life-cycle carbon footprint of AI systems.

Publications

• Preprint 2025 ViTSP: A Vision Language Models Guided Framework for Large-Scale Traveling Salesman Problems
  Zhuoli Yin, Yi Ding, Reem Khir, & Hua Cai 📄 Paper
• Preprint 2025 DeepBike: A Deep Reinforcement Learning Based Model for Large-scale Online Bike Share Rebalancing
  Zhuoli Yin, Zhaoyu Kou, & Hua Cai 📄 Paper
• Enhanced global oil spill dataset from 1967 to 2023 based on text-form incident information
  Yiming Liu, Zhuoli Yin, & Hua Cai
  Scientific Data, 12(1), 1-14. 2025. 📄 Paper
• Understanding the Demand Predictability of Bike Share Systems: A Station-Level Analysis
  Zhuoli Yin, Kendrick Hardaway, Yu Feng, Zhaoyu Kou, & Hua Cai
  Frontiers of Engineering Management, 1-15. 2023. 📄 Paper
• A Deep Reinforcement Learning Model for Large-Scale Dynamic Bike Share Rebalancing with Spatial-Temporal Context
  Zhuoli Yin, Zhaoyu Kou, & Hua Cai
  The 12th International Workshop on Urban Computing. 2023. 📄 Paper