DOTS-MOCR

DOTS-MOCR is a 3-billion-parameter multimodal OCR model developed by rednote-hilab, designed for parsing text and structure from documents, webpages, and images with state-of-the-art performance.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.