Huang, X., Huang, Y.-L. and Wen, Z. (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), pp. 17494–17502. doi: 10.1609/aaai.v39i16.33923.