Zeyuan Wang, Da Li 0001, Yulin Chen, Ye Shi 0001, Liang Bai, Tianyuan Yu, Yanwei Fu 0001. One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow. In Sven Koenig, Chad Jenkins, Matthew E. Taylor, editors, Fortieth AAAI Conference on Artificial Intelligence, Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence, Sixteenth Symposium on Educational Advances in Artificial Intelligence, AAAI 2026, Singapore, January 20-27, 2026. pages 26751-26759, AAAI Press, 2026. [doi]
Abstract is missing.