The National Science Foundation (NSF) awarded a $450,064 Project Grant under the Computer and Information Science and Engineering (CISE) program to the University of California, Davis (UC Davis) for the project "SHF: SMALL: IMPROVING EFFICIENCY OF VISION TRANSFORMERS VIA SOFTWARE-HARDWARE CO-DESIGN AND ACCELERATION". The grant, awarded on October 1, 2023, supports research to develop new energy-efficient transformer models and specialized hardware for their efficient execution. Key focus areas include creating transformer models that can be dynamically pruned to improve efficiency, and designing specialized hardware with advanced solutions for dynamic precision tuning and scheduling. The project aims to advance scientific knowledge on attention mechanisms in transformer models, extend hardware design expertise, and improve the accessibility of superior transformer models across various applications. The grant is expected to be completed by September 30, 2026. No federal grant sub-awards are planned for this project.