Gao, L. et al. 2026. ViType: High-Fidelity Visual Text Rendering via Glyph-Aware Multimodal Diffusion. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 6 (Mar. 2026), 4131–4139. DOI:https://doi.org/10.1609/aaai.v40i6.42408.