AI RESEARCH
Energy Efficient Software Hardware CoDesign for Machine Learning: From TinyML to Large Language Models
arXiv CS.LG
•
ArXi:2603.23668v1 Announce Type: cross The rapid deployment of machine learning across platforms from milliwatt-class TinyML devices to large language models has made energy efficiency a primary constraint for sustainable AI. Across these scales, performance and energy are increasingly limited by data movement and memory-system behavior rather than by arithmetic throughput alone. This work reviews energy efficient software hardware codesign methods spanning edge inference and