Papers › Unifying Vision, Text, and Layout for Universal Document Processing

Unifying Vision, Text, and Layout for Universal Document Processing

5 Dec 2022CVPR 2023 1arXiv:2212.02623archive 2025-07-28

Zineng Tang, ZiYi Yang, Guoxin Wang, Yuwei Fang, Yang Liu, Chenguang Zhu, Michael Zeng, Cha Zhang, Mohit Bansal

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 innovative self-supervised objectives and diverse labeled data. UDOP also learns to generate document images from text and layout modalities via masked image reconstruction. To the best of our knowledge, this is the first time in the field of document AI that one model simultaneously achieves high-quality neural document editing and content customization. Our method sets the state-of-the-art on 8 Document AI tasks, e.g., document understanding and QA, across diverse data domains like finance reports, academic papers, and websites. UDOP ranks first on the leaderboard of the Document Understanding Benchmark.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2212.02623")

Code

Syntology Ran 14 of 17 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 2 ran · violated contract; 1 ran · our draft was wrong; 11 ran with no contract checked.

By repository: community (archive-listed): 14 samples from 1 repository, 11 ran; 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

microsoft/i-code officialmentioned in papermentioned on GitHubjaxMIT report
microsoft/udop officialmentioned in papermentioned on GitHubMIT report
DS4SD/MarkushGrapher mentioned on GitHubpytorchMIT report
pwc-1/Paper-10 mindsporeApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested; 14 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · violated contract
1ran · our draft was wrong
11ran
3unverified

Licence: 3 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from DS4SD/MarkushGrapher. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

custom_huber DS4SD/MarkushGrapher/markushgrapher/core/trainers/losses.py community (archive-listed) ran MIT (permissive) · f587be8f27266175 · report
custom_huber2 DS4SD/MarkushGrapher/markushgrapher/core/trainers/losses.py community (archive-listed) ran MIT (permissive) · 8ad08bf63e399fe5 · report
estimate_word_width DS4SD/MarkushGrapher/markushgrapher/core/common/data_preprocessing.py community (archive-listed) ran MIT (permissive) · 68402efebc760365 · report
get_last_checkpoint DS4SD/MarkushGrapher/markushgrapher/core/common/utils.py community (archive-listed) ran MIT (permissive) · 9f1130d32c6430f8 · report
get_linear_with_fact_schedule_with_warmup DS4SD/MarkushGrapher/markushgrapher/core/trainers/optimization.py community (archive-listed) ran MIT (permissive) · a3b662bbc3a23327 · report
get_scheduler DS4SD/MarkushGrapher/markushgrapher/core/trainers/optimization.py community (archive-listed) ran MIT (permissive) · e78d0e6d79459413 · report
huber_loss DS4SD/MarkushGrapher/markushgrapher/core/trainers/losses.py community (archive-listed) ran fingerprinted MIT (permissive) · a83a110a9551382d · report
pad_sequence_native DS4SD/MarkushGrapher/markushgrapher/core/trainers/data_collator.py community (archive-listed) ran MIT (permissive) · 4d78a796062fd89b · report
setup_logging DS4SD/MarkushGrapher/markushgrapher/core/common/begin.py community (archive-listed) ran MIT (permissive) · fbd45e87bae891a7 · report
split_bounding_box_for_words DS4SD/MarkushGrapher/markushgrapher/core/common/data_preprocessing.py community (archive-listed) ran MIT (permissive) · 084ee3628fc5d124 · report
split_sentence_into_words DS4SD/MarkushGrapher/markushgrapher/core/common/data_preprocessing.py community (archive-listed) ran MIT (permissive) · 32b4122ad5350b54 · report
calculate_iou DS4SD/MarkushGrapher/markushgrapher/core/common/utils.py community (archive-listed) unverified MIT (permissive) · ea1bb4ac7f48a7b5 · report
clamp DS4SD/MarkushGrapher/markushgrapher/core/common/utils.py community (archive-listed) unverified MIT (permissive) · 59eacee354fa7772 · report
last_checkpoint DS4SD/MarkushGrapher/markushgrapher/core/common/begin.py community (archive-listed) unverified MIT (permissive) · 5b942743f6a5251f · report
default identical code first harvested elsewhere ran · violated contract licence of this copy not recorded · 424012cb37b31172 · report
exists identical code first harvested elsewhere ran · violated contract fingerprinted licence of this copy not recorded · aa5486a3650902d8 · report
uniq identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 9a299fe5ae09e407 · report

Tasks

Document AIImage ReconstructionVisual Question Answering (VQA)document understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering (VQA) DocVQA test UDOP (aux) ANLS 0.878 #11 of 33 Archive leaderboard report
Visual Question Answering (VQA) DocVQA test UDOP ANLS 0.847 #17 of 33 Archive leaderboard report
Visual Question Answering (VQA) InfographicVQA UDOP (aux) ANLS 63.0 #5 of 21 Archive leaderboard report
Visual Question Answering (VQA) InfographicVQA UDOP ANLS 47.4 #16 of 21 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections