Hao Liu is a fourth year Ph.D student advised by Prof. Suhaib A.
Fahmy in the Accelerated Connected Computing Lab (ACCL) at King Abdullah University of Science and Technology (KAUST). Previously, he received his Bachelor's degree in Electronic and Information Engineering and Master's degree in Cyber Science and Technology from Beihang University (BUAA), Beijing, China in 2019 and 2021, respectively.
Research Interests
My research focuses on enabling efficient and scalable DNN inference by leveraging the collaborative capabilities of edge and near-edge computing nodes (such as base stations). The goal is to bridge the gap between advanced deep learning models and their real-world deployment, making intelligent services practical under real-world resource and latency constraints.
Topic: Work on Network Architecture Search (NAS).
Supervised by Prof. Yu Wang
Teaching Experience
Teaching Assistant for ECE 265P: AI Training
Saudi Ministry of Interior Program
April 2025 | Riyadh, Saudi Arabia
Teaching Assistant for KAUST CS256: Digital Design and Computer Architecture
KAUST
September 2022 | Jeddah, Saudi Arabia
Teaching Assistant for Digital Circuits and Systems Course
Beihang University
September 2020 | Beijing, China
Technical Projects
NNStreamer Deployment & Custom Plugin Development
DockerCode
Deployed the NNStreamer framework on NVIDIA Jetson edge platforms. Developed custom GStreamer plugins using C/C++ to
optimize DNN collaborative inference across multiple devices.
Implemented ResNet inference using the Xilinx Vitis-AI flow on Xilinx Alveo U55C. Conducted a comparative analysis against hls4ml
implementations, evaluating performance metrics and resource utilization.