{"paper":{"title":"Unifying Vision, Text, and Layout for Universal Document Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cha Zhang, Chenguang Zhu, Guoxin Wang, Michael Zeng, Mohit Bansal, Yang Liu, Yuwei Fang, Zineng Tang, Ziyi Yang","submitted_at":"2022-12-05T22:14:49Z","abstract_excerpt":"We propose Universal Document Processing (UDOP), a foundation Document AI model which unifies text, image, and layout modalities together with varied task formats, including document understanding and generation. UDOP leverages the spatial correlation between textual content and document image to model image, text, and layout modalities with one uniform representation. With a novel Vision-Text-Layout Transformer, UDOP unifies pretraining and multi-domain downstream tasks into a prompt-based sequence generation scheme. UDOP is pretrained on both large-scale unlabeled document corpora using inno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.02623","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.02623/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}