SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression

Open Webpage

Xinhao Huang, You-Liang Huang, Zeyi Wen

Published: 01 Jan 2025, Last Modified: 31 Jul 2025AAAI 2025EveryoneRevisionsBibTeXCC BY-SA 4.0