QIN, Zongyue; HE, Zifan; PRAKRIYA, Neha; CONG, Jason; SUN, Yizhou. Dynamic-Width Speculative Beam Decoding for LLM Inference. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 39, n. 23, p. 25056–25064, 2025. DOI: 10.1609/aaai.v39i23.34690. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/34690. Acesso em: 25 may. 2026.