Gao, Lishuai, et al. “ViType: High-Fidelity Visual Text Rendering via Glyph-Aware Multimodal Diffusion”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 6, Mar. 2026, pp. 4131-9, doi:10.1609/aaai.v40i6.42408.