Incoming Ph.D. Student
Department of Computer Science and Engineering
The Chinese University of Hong Kong
Email: zl3202 [at] columbia.edu
GitHub: ArthasL1
LinkedIn: zeqili
I am an incoming Ph.D. student in the Department of Computer Science and Engineering at The Chinese University of Hong Kong. My research background spans machine learning, reinforcement learning, robotics, embedded systems, and hardware acceleration for intelligent systems.
Previously, I received an M.S. in Computer Engineering from Columbia University and an M.Sc. in Artificial Intelligence for Sustainable Development with Distinction from University College London. I received my B.S. in Computer Science and Engineering from the University of California, Irvine.
My interests include reinforcement learning, adaptive robotic systems, machine learning for embedded and edge devices, hardware acceleration, and trustworthy AI systems for real-world physical environments.
| Ph.D. in Computer Science and Engineering | The Chinese University of Hong Kong | Incoming |
| M.S. in Computer Engineering | Columbia University | 2022–2025 |
| M.Sc. in Artificial Intelligence for Sustainable Development | University College London | 2023–2024 |
| B.S. in Computer Science and Engineering | University of California, Irvine | 2018–2022 |
Developed a reinforcement learning framework for dynamically selecting model width in UAV-based weed detection with Slimmable Neural Networks. Implemented Proximal Policy Optimization to balance segmentation accuracy and energy consumption, improving cumulative reward under constrained UAV settings.
Led a team project integrating model-agnostic meta-learning with GPT-2 for few-shot text style transfer. The work focused on syntactic and semantic transformations under limited data, using STYLEPTB for training and evaluation.
Designed and built custom legged robots using 3D printing, servo motors, and Raspberry Pi 4 control systems. Combined self-modeling and reinforcement learning to improve robot navigation and turning in both simulation and real-world experiments.
Developed machine learning models to determine control parameters for manipulating qubits, in collaboration with Fermilab. Implemented models on FPGAs close to quantum hardware to support ultra-low-latency quantum control.
Led a team of four to build camera-equipped glasses that generate audio descriptions of the surrounding scene for visually impaired users. The system combined image captioning, text-to-speech, Raspberry Pi 4 hardware integration, and custom circuit assembly. The project received the Dean's Choice Award at UC Irvine.
| Dean's Choice Award | University of California, Irvine | 2022 |
| Engineering Dean's Excellence Scholarship | University of California, Irvine | 2018–2022 |
| Dean's Honor List | University of California, Irvine | 2018–2022 |
| Cum Laude | University of California, Irvine | 2022 |
Python, C++, Verilog, SystemC, C, Java, MATLAB, PyTorch, TensorFlow, Vivado, embedded systems, FPGA design, robotics prototyping, and Linux-based development.