GU, Hongyaoxing; HU, Lijuan; NIU, Shuzi; LIU, Fangfang. FLRQ: Faster LLM Quantization with Flexible Low-Rank Matrix Sketching. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 26, p. 21369–21377, 2026. DOI: 10.1609/aaai.v40i26.39283. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/39283. Acesso em: 19 may. 2026.