Edge Platform

Edge platforms are computing systems designed to process data locally on resource-constrained devices, enabling faster, more efficient, and privacy-preserving applications. Current research focuses on optimizing deep neural networks (DNNs), including transformers and graph neural networks, for these platforms through techniques like model quantization, hardware-software co-design, and adaptive batching to improve inference speed and energy efficiency. This work is crucial for advancing applications in diverse fields such as robotics, medical imaging, and IoT, where real-time processing and limited resources are critical constraints.