Huang, X. et al. 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 (Apr. 2025), 17494–17502. DOI:https://doi.org/10.1609/aaai.v39i16.33923.