Enming Liang

Currently, I am a Research Assistant Professor at City University of Hong Kong. My research interests include Machine Learning for Constrained Optimization, and its application for Mobility, Energy, and Climate.

I received Ph.D. (2021-2024) at Department of Data Science, City University of Hong Kong, supervised by Prof. Minghua Chen. I received bachelor degree (2016-2020) at School of Intelligent Systems Engineering, Sun Yat-sen University. supervised by Prof. Renxin Zhong.

I have been a member of the DeepOPF team, working with Prof. Steven Low. I had visited department of CST, University of Cambridge, supervised by Prof. Srinivasan Keshav. I had contributed to tutorials for the Climate Change AI summer school, working with Prof. Priya L. Donti.

I had worked as a research intern in MSRA (Beijing, 2022), Huawei Noah's Ark Lab (Shenzhen, 2021), and DiDi-SYSU Research Program (Guangzhou, 2020).


Recent Highlights

AI + Optimization
Neural-Network Feasibility
Low Complexity Homeomorphic Projection to Ensure NN Solution Feasibility for Optimization over (Non-)Convex Set.
Enming Liang, Minghua Chen, and Steven Low.
ICML 2023
Homeomorphic Projection to Ensure NN Solution Feasibility for Constrained Optimization.
Enming Liang, Minghua Chen, and Steven Low.
JMLR 2024
Generative Learning
Generative Learning for Solving Non-Convex Problem with Multi-Valued Input-Solution Mapping.
Enming Liang and Minghua Chen.
ICLR 2024
Gauge Flow Matching for Efficient Constrained Generative Modeling over General Convex Set.
Xinpeng Li*, Enming Liang*, and Minghua Chen.
ICLR 2025 DeLTa Workshop. Oral.
Decision-Focused Learning
DFF: Decision-Focused Fine-tuning for Smarter Predict-then-Optimize with Limited Data.
Jiaqi Yang*, Enming Liang*, Zicheng Su, Zhichao Zou, Peng Zhen, Jiecheng Guo, Kun An, Wanjing Ma.
AAAI 2025. Oral.
NN Approximation Theory
Characterizing ResNet's Universal Approximation Capability.
Chenghao Liu, Enming Liang, and Minghua Chen.
ICML 2024
AI for Mobility, Energy, and Climate
Ride-Sourcing Optimization
Learning to Dispatch and Reposition on a Mobility-on-Demand Platform
Enming Liang.
KDD CUP 2020. 2nd Place.
An Integrated Reinforcement Learning and Centralized Programming Approach for Online Taxi Dispatching.
Enming Liang, Kexin Wen, William Lam, Agachai Sumalee, and Renxin Zhong.
IEEE TNNLS 2021
Traffic Signal Control
OAM: An Option-Action Reinforcement Learning Framework for Universal Multi-Intersection Control
Enming Liang, Zicheng Su, Chilin Fang, and Renxin Zhong.
AAAI 2022. Oral.
Power Grid Operation
AI for Optimal Power Flow Tutorial
Enming Liang, Priya L. Donti, and Minghua Chen.
Climate Change AI Summer School 2024

Visitor Map