陆奕衡 Yiheng Lu

CUHKSZ UG'27

About Me

Hi I’m Yiheng Lu, a Music lover, Gym bro, also an Aspiring AI researcher. I’m a 3rd Year Undergraduate student at The Chinese University of Hong Kong, Shenzhen, majoring in Electric Engineering. My experience lies in Deep Learning & Signal Processing, and I have a strong interest in the field of Swarm Intelligence, Robotics and Networking.

Projects

In this project, I led my team to leverage the latest AI technologies to build a system that helps novice academic researchers with paper finding, summarization, and retrieval.

We critically analyzed the limitations of current academic search engines and conventional RAG systems.
I proposed an improved architecture and coordinated the division of tasks among team members.
My role focused on backend development, including model fine-tuning, and the integration of MCP, large language models (LLMs), and database systems to ensure seamless functionality.

Experience

Amphion

Research Assistant

October 2024 - Present

Amphion GitHub Page

Amphion is the lab led by Prof. Zhizheng Wu, focusing on the research of AI Audio, Music, and Speech Generation.

As a research assistant in the Amphion Lab, I explored state-of-the-art methods in Text-to-Speech and Text-to-Audio generation. This experience deepened my understanding of speech synthesis pipelines and the latest advancements in generative audio technologies.

NCEL

Research Assistant

May 2025 - Present

NCEL website

Network Communications and Economics Lab (NCEL) is the lab led by Prof. Jianwei Huang, focusing on the research of Network Economics, Wireless Communications, swarm Intelligence and Smart Grid.

As a research assistant in the NCEL, I contributed to the Smart Grid project collaborated with Guangdong Power Grid. This project aims to develop a smart grid system that can predict the electric price through the analysis of historical data and real-time information.

Tech Stack

  • Languages: Python, PyTorch, HTML, Bash, VHDL
  • Tools: Linux, Git&GitHub, Docker, Huggingface, Slurm, Vivado, MultiSim
  • Experience: Deep Learning, Signal Processing & System, Digital Circuit Design