LIANG, Xun et al. SEAP: Sparse Expert Activation Pruning Unlocks the Brainpower of Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 38, p. 31934–31942, 2026. DOI: 10.1609/aaai.v40i38.40463. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40463. Acesso em: 26 may. 2026.