Huang, Xinhao, You-Liang Huang, and Zeyi Wen. 2025. “SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression”. Proceedings of the AAAI Conference on Artificial Intelligence 39 (16):17494-502. https://doi.org/10.1609/aaai.v39i16.33923.