Wang, Zeyuan, Da Li, Yulin Chen, Ye Shi, Liang Bai, Tianyuan Yu, and Yanwei Fu. 2026. “One-Step Generative Policies With Q-Learning: A Reformulation of MeanFlow”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (31):26751-59. https://doi.org/10.1609/aaai.v40i31.39885.