Minglan Liang

Guilin University of Electronic Technology

Papers

Total Citations

H-Index

About

Minglan Liang is a researcher at the forefront of hardware acceleration for artificial intelligence, with a primary focus on deep learning inference engines and energy-efficient computing architectures. Liang’s most notable contribution is the design of a coarse-grained reconfigurable array (CGRA)-based neural network inference engine tailored for deep reinforcement learning, a critical innovation that bridges the gap between high-performance AI algorithms and resource-constrained edge devices. This work, published in 2018 and garnering 12 citations, addresses the pressing demand for dedicated accelerators that deliver both exceptional computing throughput and low power consumption, enabling real-time AI deployment on edge computing nodes. By tackling the challenges of state-of-the-art deep learning engines, Liang’s research advances the practical implementation of intelligent systems in applications ranging from robotics to autonomous navigation. Though early in their career, Liang’s contributions highlight a commitment to optimizing neural network hardware, making AI more accessible and efficient for real-world use. Their work stands as a valuable reference for researchers exploring reconfigurable architectures and edge AI, promising continued impact as the field evolves.