Mingqiang Huang
Papers
2
Total Citations
40
H-Index
2
About
Mingqiang Huang is a rising researcher at the forefront of efficient AI deployment, specializing in hardware-software co-design for large language models (LLMs) on resource-constrained edge devices. His major contribution is the development of **EdgeLLM**, a pioneering CPU-FPGA heterogeneous edge accelerator that addresses the critical challenge of running computationally intensive LLMs on platforms like robots and IoT devices. By intelligently partitioning model computation between the CPU and FPGA fabric, his work dramatically reduces latency and energy consumption while maintaining model accuracy—a breakthrough for real-time edge AI applications. With his most-cited paper (2025) already accumulating 38 citations and a 2024 version adding 2 more, Huang’s research is rapidly gaining traction in the systems and machine learning communities. His work not only pushes the boundaries of edge computing but also democratizes access to advanced AI, enabling smarter, autonomous systems in manufacturing, healthcare, and smart cities. As an early-career scholar, Huang’s innovative accelerator design positions him as a key contributor to the next generation of efficient, on-device intelligence.
Research Focus
Key Achievements
Top Papers
- 1
- 2