WANG, Zeyuan; LI, Da; CHEN, Yulin; SHI, Ye; BAI, Liang; YU, Tianyuan; FU, Yanwei. One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 31, p. 26751–26759, 2026. DOI: 10.1609/aaai.v40i31.39885. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/39885. Acesso em: 16 may. 2026.