Liao, Huanxuan, et al. “SparK: Query-Aware Unstructured Sparsity With Recoverable KV Cache Channel Pruning”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 38, Mar. 2026, pp. 31961-9, doi:10.1609/aaai.v40i38.40466.