github.com/microsoft/unilm/tree/master/layoutlm
LayoutLM is a multimodal pre-training method for visually rich document understanding that combines text, layout, and image information. It achieves state-of-the-art results on tasks like form and receipt understanding, with extensions for multilingual support.
AI named LayoutLM from January 2026 to July 2026.
Brand page for github-com-2776