[1]
Liao, H. et al. 2026. SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 38 (Mar. 2026), 31961–31969. DOI:https://doi.org/10.1609/aaai.v40i38.40466.