Ma, Zhibin, Pengwen Dai, Wei Zhuo, and Xugong Qin. “One2Seq: One-Token Wise Decoder for Efficient Scene Text Recognition”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 10 (March 14, 2026): 7883-7891. Accessed April 29, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/37732.