The field of multilingual document intelligence is rapidly advancing, with a focus on developing unified, end-to-end frameworks that can jointly learn multiple tasks, such as document layout parsing, text recognition, and relational understanding. This allows for more robust and efficient processing of multilingual documents, enabling applications such as semantic search and cross-lingual retrieval. Notable papers in this area include: dots.ocr, which introduces a single Vision-Language Model that achieves state-of-the-art performance on multilingual document layout parsing. M3DR, which presents a framework for universal multilingual multimodal document retrieval that generalizes across different vision-language architectures and model sizes. HieroGlyphTranslator, which proposes a method for automatic recognition and translation of Egyptian hieroglyphs to English, achieving a significant BLEU score of 42.2.