Research
Embedded Files
Our research focuses on building intelligent and efficient computing systems that support modern applications such as artificial intelligence, mobile computing, and large-scale machine learning. We develop system software and architecture-aware optimization techniques to improve performance, energy efficiency, and sustainability across edge devices, servers, and distributed AI platforms.
Our work spans multiple layers of the computing stack —from hardware to operating systems — and aims to bridge the gap between emerging workloads and efficient system design.
Research topics in our lab include:
System Design and Optimization for AI and Machine Learning Workloads
Efficient Edge Computing for Mobile and Embedded Systems
Energy- and Thermal-Aware Computing Systems
Distributed AI Systems and LLM Inference Optimization
Architecture-Aware System Software and Resource Management
Sustainable and Energy-Efficient Computing Systems
Sustainable and Energy-Efficient Computing Systems
We develops system-level optimization techniques that enable sustained and energy-efficient computing under real-world workloads. We balance performance, power, and thermal constraints across edge devices and data centers.
Intelligent Resource Management
for Modern AI Workloads
Intelligent Resource Management
for Modern AI Workloads
We develop intelligent scheduling, allocation, and optimization techniques for emerging AI workloads, including multi-DNN and large language model (LLM) inference.
Architecture-Aware
System Software and Modeling
Architecture-Aware
System Software and Modeling
We bridge computer architecture and system software to build adaptive, lightweight, and deployable optimization techniques. By combining hardware characterization with data-driven modeling, we enable smarter system control across heterogeneous platforms.
Page updated
Google Sites
Report abuse