Ma, Z., P. Dai, W. Zhuo, and X. Qin. “One2Seq: One-Token Wise Decoder for Efficient Scene Text Recognition”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 10, Mar. 2026, pp. 7883-91, doi:10.1609/aaai.v40i10.37732.