@inproceedings{b27e030120dc47eeb9aec4aa59bd1ba6,
title = "Research on personalized compression algorithm for pre-trained models based on homomorphic entropy increase",
abstract = "This paper investigates the deployment challenges of Vision Transformer (ViT) and Large Language Models (LLMs). Vision Transformer captures global information through multi-head attention mechanisms, but its high computational cost limits its application on mobile devices. Although LLMs have achieved breakthroughs in natural language processing, they also face significant deployment challenges. To address these issues, we propose a hierarchical pruning strategy that distinguishes personalized layers from shared layers through compressed sensing and random sampling, significantly reducing model parameters. Experiments show that the hierarchical mechanism effectively balances pruning and accuracy, providing a new direction for deploying efficient and personalized AI models on mobile devices.",
keywords = "hierarchical mechanism, large language models, mobile devices, model pruning, personalized AI, Vision transformer",
author = "Xing Guo and Yicong Li and Haohua Du",
note = "Publisher Copyright: {\textcopyright} 2025 SPIE.; 2nd International Conference on Optical Communication and Optoelectronic Technology, OCOT 2025 ; Conference date: 18-07-2025 Through 20-07-2025",
year = "2025",
month = nov,
day = "13",
doi = "10.1117/12.3083641",
language = "英语",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Klimis Ntalianis",
booktitle = "Second International Conference on Optical Communication and Optoelectronic Technology, OCOT 2025",
address = "美国",
}