{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/document-understanding","name":"document understanding","slug":"document-understanding","description_markdown":"Document understanding involves document classification, layout analysis, information extraction, and DocQA.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":309,"papers_with_code":140,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":1,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/pdfvqa","name":"PDFVQA","full_name":"","num_papers_in_archive":3},{"url":"/dataset/u-diads-bib","name":"U-DIADS-Bib","full_name":"","num_papers_in_archive":2}],"subtasks":[{"url":"/task/line-items-extraction","name":"Line Items Extraction"}],"parent_tasks":[{"url":"/task/document-ai","name":"Document AI"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":4,"rows_per_page":100,"shown":100,"of":309,"of_with_code":140,"tagged_in_all":309,"counts":{"archive_papers_tagged":309,"with_a_code_link":140,"where_syntology_ran_a_sample":39,"not_listed_spam_title":0,"listed":309,"listed_where_code_ran":39,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":30,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":30,"listed_every_run_a_failure_of_syntologys_instrument":9,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/layoutlmv2-multi-modal-pre-training-for","slug":"layoutlmv2-multi-modal-pre-training-for","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","date":"2020-12-29","arxiv_id":"2012.14740","repositories_listed":9,"syntology":null},{"url":"/paper/layoutxlm-multimodal-pre-training-for","slug":"layoutxlm-multimodal-pre-training-for","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","date":"2021-04-18","arxiv_id":"2104.08836","repositories_listed":6,"syntology":null},{"url":"/paper/colpali-efficient-document-retrieval-with","slug":"colpali-efficient-document-retrieval-with","title":"ColPali: Efficient Document Retrieval with Vision Language Models","date":"2024-06-27","arxiv_id":"2407.01449","repositories_listed":5,"syntology":{"n":4,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/colpali-efficient-document-retrieval-with#ran","syntology_url":"https://syntology.ai/paper/2407.01449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01449"}},"official":null}},{"url":"/paper/unifying-vision-text-and-layout-for-universal","slug":"unifying-vision-text-and-layout-for-universal","title":"Unifying Vision, Text, and Layout for Universal Document Processing","date":"2022-12-05","arxiv_id":"2212.02623","repositories_listed":5,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":2,"n_no_contract":12,"n_pointer_only":4,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 2 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unifying-vision-text-and-layout-for-universal#ran","syntology_url":"https://syntology.ai/paper/2212.02623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.02623"}},"official":{"repos":["microsoft/i-code","microsoft/udop"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/lilt-a-simple-yet-effective-language","slug":"lilt-a-simple-yet-effective-language","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","date":"2022-02-28","arxiv_id":"2202.13669","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lilt-a-simple-yet-effective-language#ran","syntology_url":"https://syntology.ai/paper/2202.13669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13669"}},"official":{"repos":["jpwang/lilt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/donut-document-understanding-transformer","slug":"donut-document-understanding-transformer","title":"OCR-free Document Understanding Transformer","date":"2021-11-30","arxiv_id":"2111.15664","repositories_listed":5,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/donut-document-understanding-transformer#ran","syntology_url":"https://syntology.ai/paper/2111.15664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.15664"}},"official":{"repos":["clovaai/donut"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/chargrid-towards-understanding-2d-documents","slug":"chargrid-towards-understanding-2d-documents","title":"Chargrid: Towards Understanding 2D Documents","date":"2018-09-24","arxiv_id":"1809.08799","repositories_listed":5,"syntology":null},{"url":"/paper/qwen2-5-vl-technical-report","slug":"qwen2-5-vl-technical-report","title":"Qwen2.5-VL Technical Report","date":"2025-02-19","arxiv_id":"2502.13923","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/qwen2-5-vl-technical-report#ran","syntology_url":"https://syntology.ai/paper/2502.13923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13923"}},"official":null}},{"url":"/paper/icdar-2021-competition-on-scientific","slug":"icdar-2021-competition-on-scientific","title":"ICDAR 2021 Competition on Scientific Literature Parsing","date":"2021-06-08","arxiv_id":"2106.14616","repositories_listed":3,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/icdar-2021-competition-on-scientific#ran","syntology_url":"https://syntology.ai/paper/2106.14616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14616"}},"official":{"repos":["ibm-aur-nlp/PubLayNet","ibm-aur-nlp/PubTabNet","wenwenyu/MASTER-pytorch"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learned-compression-for-compressed-learning","slug":"learned-compression-for-compressed-learning","title":"Learned Compression for Compressed Learning","date":"2024-12-12","arxiv_id":"2412.09405","repositories_listed":2,"syntology":null},{"url":"/paper/doclayout-yolo-enhancing-document-layout","slug":"doclayout-yolo-enhancing-document-layout","title":"DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception","date":"2024-10-16","arxiv_id":"2410.12628","repositories_listed":2,"syntology":null},{"url":"/paper/layoutllm-layout-instruction-tuning-with","slug":"layoutllm-layout-instruction-tuning-with","title":"LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding","date":"2024-04-08","arxiv_id":"2404.05225","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/layoutllm-layout-instruction-tuning-with#ran","syntology_url":"https://syntology.ai/paper/2404.05225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05225"}},"official":{"repos":["alibabaresearch/advancedliteratemachinery"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-affinity-rationality-and-diversity-of","slug":"on-the-affinity-rationality-and-diversity-of","title":"On the Affinity, Rationality, and Diversity of Hierarchical Topic Modeling","date":"2024-01-25","arxiv_id":"2401.14113","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_constructed":5,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"7 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/on-the-affinity-rationality-and-diversity-of#ran","syntology_url":"https://syntology.ai/paper/2401.14113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14113"}},"official":{"repos":["bobxwu/traco"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/pali-x-on-scaling-up-a-multilingual-vision","slug":"pali-x-on-scaling-up-a-multilingual-vision","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","date":"2023-05-29","arxiv_id":"2305.18565","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":4,"n_no_contract":1,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 4 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pali-x-on-scaling-up-a-multilingual-vision#ran","syntology_url":"https://syntology.ai/paper/2305.18565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18565"}},"official":null}},{"url":"/paper/ernie-layout-layout-knowledge-enhanced-pre","slug":"ernie-layout-layout-knowledge-enhanced-pre","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","date":"2022-10-12","arxiv_id":"2210.06155","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ernie-layout-layout-knowledge-enhanced-pre#ran","syntology_url":"https://syntology.ai/paper/2210.06155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06155"}},"official":{"repos":["PaddlePaddle/PaddleNLP"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/end-to-end-document-recognition-and","slug":"end-to-end-document-recognition-and","title":"End-to-end Document Recognition and Understanding with Dessurt","date":"2022-03-30","arxiv_id":"2203.16618","repositories_listed":2,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-document-recognition-and#ran","syntology_url":"https://syntology.ai/paper/2203.16618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16618"}},"official":{"repos":["herobd/dessurt"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/markuplm-pre-training-of-text-and-markup","slug":"markuplm-pre-training-of-text-and-markup","title":"MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding","date":"2021-10-16","arxiv_id":"2110.08518","repositories_listed":2,"syntology":null},{"url":"/paper/message-passing-attention-networks-for","slug":"message-passing-attention-networks-for","title":"Message Passing Attention Networks for Document Understanding","date":"2019-08-17","arxiv_id":"1908.06267","repositories_listed":2,"syntology":null},{"url":"/paper/paddleocr-3-0-technical-report","slug":"paddleocr-3-0-technical-report","title":"PaddleOCR 3.0 Technical Report","date":"2025-07-08","arxiv_id":"2507.05595","repositories_listed":1,"syntology":null},{"url":"/paper/glm-4-1v-thinking-towards-versatile","slug":"glm-4-1v-thinking-towards-versatile","title":"GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","date":"2025-07-01","arxiv_id":"2507.01006","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":1,"n_instrument":10,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glm-4-1v-thinking-towards-versatile#ran","syntology_url":"https://syntology.ai/paper/2507.01006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.01006"}},"official":{"repos":["thudm/glm-4.1v-thinking"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/class-agnostic-region-of-interest-matching-in","slug":"class-agnostic-region-of-interest-matching-in","title":"Class-Agnostic Region-of-Interest Matching in Document Images","date":"2025-06-26","arxiv_id":"2506.21055","repositories_listed":1,"syntology":null},{"url":"/paper/drishtikon-multi-granular-visual-grounding","slug":"drishtikon-multi-granular-visual-grounding","title":"DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images","date":"2025-06-26","arxiv_id":"2506.21316","repositories_listed":1,"syntology":null},{"url":"/paper/pp-docbee2-improved-baselines-with-efficient","slug":"pp-docbee2-improved-baselines-with-efficient","title":"PP-DocBee2: Improved Baselines with Efficient Data for Multimodal Document Understanding","date":"2025-06-22","arxiv_id":"2506.18023","repositories_listed":1,"syntology":null},{"url":"/paper/simpledoc-multi-modal-document-understanding","slug":"simpledoc-multi-modal-document-understanding","title":"SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement","date":"2025-06-16","arxiv_id":"2506.14035","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simpledoc-multi-modal-document-understanding#ran","syntology_url":"https://syntology.ai/paper/2506.14035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.14035"}},"official":{"repos":["ag2ai/simpledoc"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/infinity-parser-layout-aware-reinforcement","slug":"infinity-parser-layout-aware-reinforcement","title":"Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing","date":"2025-06-01","arxiv_id":"2506.03197","repositories_listed":1,"syntology":null},{"url":"/paper/lemonade-a-large-multilingual-expert","slug":"lemonade-a-large-multilingual-expert","title":"LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World","date":"2025-06-01","arxiv_id":"2506.00980","repositories_listed":1,"syntology":null},{"url":"/paper/arb-a-comprehensive-arabic-multimodal","slug":"arb-a-comprehensive-arabic-multimodal","title":"ARB: A Comprehensive Arabic Multimodal Reasoning Benchmark","date":"2025-05-22","arxiv_id":"2505.17021","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-markup-language-generation-for","slug":"adaptive-markup-language-generation-for","title":"Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding","date":"2025-05-08","arxiv_id":"2505.05446","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/adaptive-markup-language-generation-for#ran","syntology_url":"https://syntology.ai/paper/2505.05446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.05446"}},"official":{"repos":["Euphoria16/DocMark"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/frag-frame-selection-augmented-generation-for","slug":"frag-frame-selection-augmented-generation-for","title":"FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding","date":"2025-04-24","arxiv_id":"2504.17447","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-menu-ocr-and-translation-a","slug":"evaluating-menu-ocr-and-translation-a","title":"Evaluating Menu OCR and Translation: A Benchmark for Aligning Human and Automated Evaluations in Large Vision-Language Models","date":"2025-04-16","arxiv_id":"2504.13945","repositories_listed":1,"syntology":null},{"url":"/paper/relation-rich-visual-document-generator-for","slug":"relation-rich-visual-document-generator-for","title":"Relation-Rich Visual Document Generator for Visual Information Extraction","date":"2025-04-14","arxiv_id":"2504.10659","repositories_listed":1,"syntology":null},{"url":"/paper/bibliopage-a-dataset-of-scanned-title-pages","slug":"bibliopage-a-dataset-of-scanned-title-pages","title":"BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction","date":"2025-03-25","arxiv_id":"2503.19658","repositories_listed":1,"syntology":null},{"url":"/paper/sfdla-source-free-document-layout-analysis","slug":"sfdla-source-free-document-layout-analysis","title":"SFDLA: Source-Free Document Layout Analysis","date":"2025-03-24","arxiv_id":"2503.18742","repositories_listed":1,"syntology":null},{"url":"/paper/mdocagent-a-multi-modal-multi-agent-framework","slug":"mdocagent-a-multi-modal-multi-agent-framework","title":"MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding","date":"2025-03-18","arxiv_id":"2503.13964","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mdocagent-a-multi-modal-multi-agent-framework#ran","syntology_url":"https://syntology.ai/paper/2503.13964","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13964"}},"official":{"repos":["aiming-lab/mdocagent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pp-docbee-improving-multimodal-document","slug":"pp-docbee-improving-multimodal-document","title":"PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks","date":"2025-03-06","arxiv_id":"2503.04065","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-complex-question-answering-on-long","slug":"zero-shot-complex-question-answering-on-long","title":"Zero-Shot Complex Question-Answering on Long Scientific Documents","date":"2025-03-04","arxiv_id":"2503.02695","repositories_listed":1,"syntology":null},{"url":"/paper/omniparser-v2-structured-points-of-thought","slug":"omniparser-v2-structured-points-of-thought","title":"OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models","date":"2025-02-22","arxiv_id":"2502.16161","repositories_listed":1,"syntology":null},{"url":"/paper/docmia-document-level-membership-inference","slug":"docmia-document-level-membership-inference","title":"DocMIA: Document-Level Membership Inference Attacks against DocVQA Models","date":"2025-02-06","arxiv_id":"2502.03692","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/docmia-document-level-membership-inference#ran","syntology_url":"https://syntology.ai/paper/2502.03692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.03692"}},"official":{"repos":["khanhnguyen21006/mia_docvqa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ain-the-arabic-inclusive-large-multimodal","slug":"ain-the-arabic-inclusive-large-multimodal","title":"AIN: The Arabic INclusive Large Multimodal Model","date":"2025-01-31","arxiv_id":"2502.00094","repositories_listed":1,"syntology":null},{"url":"/paper/ocean-ocr-towards-general-ocr-application-via","slug":"ocean-ocr-towards-general-ocr-application-via","title":"Ocean-OCR: Towards General OCR Application via a Vision-Language Model","date":"2025-01-26","arxiv_id":"2501.15558","repositories_listed":1,"syntology":null},{"url":"/paper/heritage-an-end-to-end-web-platform-for","slug":"heritage-an-end-to-end-web-platform-for","title":"HERITAGE: An End-to-End Web Platform for Processing Korean Historical Documents in Hanja","date":"2025-01-21","arxiv_id":"2501.11951","repositories_listed":1,"syntology":null},{"url":"/paper/doclayllm-an-efficient-multi-modal-extension","slug":"doclayllm-an-efficient-multi-modal-extension","title":"DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/docopilot-improving-multimodal-models-for","slug":"docopilot-improving-multimodal-models-for","title":"Docopilot: Improving Multimodal Models for Document-Level Understanding","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/longdocurl-a-comprehensive-multimodal-long","slug":"longdocurl-a-comprehensive-multimodal-long","title":"LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating","date":"2024-12-24","arxiv_id":"2412.18424","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/longdocurl-a-comprehensive-multimodal-long#ran","syntology_url":"https://syntology.ai/paper/2412.18424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18424"}},"official":{"repos":["dengc2023/longdocurl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/typhoon-2-a-family-of-open-text-and","slug":"typhoon-2-a-family-of-open-text-and","title":"Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models","date":"2024-12-18","arxiv_id":"2412.13702","repositories_listed":1,"syntology":null},{"url":"/paper/expanding-performance-boundaries-of-open","slug":"expanding-performance-boundaries-of-open","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","date":"2024-12-06","arxiv_id":"2412.05271","repositories_listed":1,"syntology":{"n":9,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/expanding-performance-boundaries-of-open#ran","syntology_url":"https://syntology.ai/paper/2412.05271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05271"}},"official":{"repos":["opengvlab/internvl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/arabic-nougat-fine-tuning-vision-transformers","slug":"arabic-nougat-fine-tuning-vision-transformers","title":"Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction","date":"2024-11-19","arxiv_id":"2411.17835","repositories_listed":1,"syntology":null},{"url":"/paper/camel-bench-a-comprehensive-arabic-lmm","slug":"camel-bench-a-comprehensive-arabic-lmm","title":"CAMEL-Bench: A Comprehensive Arabic LMM Benchmark","date":"2024-10-24","arxiv_id":"2410.18976","repositories_listed":1,"syntology":null},{"url":"/paper/data-driven-coreference-based-ontology","slug":"data-driven-coreference-based-ontology","title":"Data-driven Coreference-based Ontology Building","date":"2024-10-22","arxiv_id":"2410.17051","repositories_listed":1,"syntology":null},{"url":"/paper/chulo-chunk-level-key-information","slug":"chulo-chunk-level-key-information","title":"ChuLo: Chunk-Level Key Information Representation for Long Document Processing","date":"2024-10-14","arxiv_id":"2410.11119","repositories_listed":1,"syntology":null},{"url":"/paper/llm-times-mapreduce-simplified-long-sequence","slug":"llm-times-mapreduce-simplified-long-sequence","title":"LLM$\\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models","date":"2024-10-12","arxiv_id":"2410.09342","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llm-times-mapreduce-simplified-long-sequence#ran","syntology_url":"https://syntology.ai/paper/2410.09342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09342"}},"official":{"repos":["thunlp/llmxmapreduce"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/pdf-wukong-a-large-multimodal-model-for","slug":"pdf-wukong-a-large-multimodal-model-for","title":"PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling","date":"2024-10-08","arxiv_id":"2410.05970","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-layout-reading-order-as-ordering","slug":"modeling-layout-reading-order-as-ordering","title":"Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding","date":"2024-09-29","arxiv_id":"2409.19672","repositories_listed":1,"syntology":null},{"url":"/paper/oryx-mllm-on-demand-spatial-temporal","slug":"oryx-mllm-on-demand-spatial-temporal","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","date":"2024-09-19","arxiv_id":"2409.12961","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/oryx-mllm-on-demand-spatial-temporal#ran","syntology_url":"https://syntology.ai/paper/2409.12961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12961"}},"official":{"repos":["oryx-mllm/oryx"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/one-missing-piece-in-vision-and-language-a","slug":"one-missing-piece-in-vision-and-language-a","title":"One missing piece in Vision and Language: A Survey on Comics Understanding","date":"2024-09-14","arxiv_id":"2409.09502","repositories_listed":1,"syntology":null},{"url":"/paper/information-extraction-from-visually-rich-1","slug":"information-extraction-from-visually-rich-1","title":"Information Extraction from Visually Rich Documents Using Directed Weighted Graph Neural Network","date":"2024-09-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mplug-docowl2-high-resolution-compressing-for","slug":"mplug-docowl2-high-resolution-compressing-for","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","date":"2024-09-05","arxiv_id":"2409.03420","repositories_listed":1,"syntology":null},{"url":"/paper/doclayllm-an-efficient-and-effective-multi","slug":"doclayllm-an-efficient-and-effective-multi","title":"DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document Understanding","date":"2024-08-27","arxiv_id":"2408.15045","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/doclayllm-an-efficient-and-effective-multi#ran","syntology_url":"https://syntology.ai/paper/2408.15045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15045"}},"official":{"repos":["whlscut/DocLayLLM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-02034","slug":"2408-02034","title":"Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid","date":"2024-08-04","arxiv_id":"2408.02034","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-02034#ran","syntology_url":"https://syntology.ai/paper/2408.02034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.02034"}},"official":{"repos":["yuliang-liu/monkey"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/token-level-correlation-guided-compression","slug":"token-level-correlation-guided-compression","title":"Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding","date":"2024-07-19","arxiv_id":"2407.14439","repositories_listed":1,"syntology":null},{"url":"/paper/visfocus-prompt-guided-vision-encoders-for","slug":"visfocus-prompt-guided-vision-encoders-for","title":"VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding","date":"2024-07-17","arxiv_id":"2407.12594","repositories_listed":1,"syntology":null},{"url":"/paper/daniel-a-fast-document-attention-network-for","slug":"daniel-a-fast-document-attention-network-for","title":"DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documents","date":"2024-07-12","arxiv_id":"2407.09103","repositories_listed":1,"syntology":null},{"url":"/paper/hypergraph-based-understanding-for-document","slug":"hypergraph-based-understanding-for-document","title":"Hypergraph based Understanding for Document Semantic Entity Recognition","date":"2024-07-09","arxiv_id":"2407.06904","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hypergraph-based-understanding-for-document#ran","syntology_url":"https://syntology.ai/paper/2407.06904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06904"}},"official":{"repos":["Line-Kite/HGALayoutLM"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-bounding-box-is-worth-one-token","slug":"a-bounding-box-is-worth-one-token","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","date":"2024-07-02","arxiv_id":"2407.01976","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-bounding-box-is-worth-one-token#ran","syntology_url":"https://syntology.ai/paper/2407.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01976"}},"official":{"repos":["laytextllm/laytextllm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mmlongbench-doc-benchmarking-long-context","slug":"mmlongbench-doc-benchmarking-long-context","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","date":"2024-07-01","arxiv_id":"2407.01523","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mmlongbench-doc-benchmarking-long-context#ran","syntology_url":"https://syntology.ai/paper/2407.01523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01523"}},"official":null}},{"url":"/paper/multimodal-structured-generation-cvpr-s-2nd","slug":"multimodal-structured-generation-cvpr-s-2nd","title":"Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report","date":"2024-06-17","arxiv_id":"2406.11403","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-visual-tokens-for-extended-text","slug":"leveraging-visual-tokens-for-extended-text","title":"Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning","date":"2024-06-04","arxiv_id":"2406.02547","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":5,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":14,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/leveraging-visual-tokens-for-extended-text#ran","syntology_url":"https://syntology.ai/paper/2406.02547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02547"}},"official":{"repos":["showlab/VisInContext"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/focus-anywhere-for-fine-grained-multi-page","slug":"focus-anywhere-for-fine-grained-multi-page","title":"Focus Anywhere for Fine-grained Multi-page Document Understanding","date":"2024-05-23","arxiv_id":"2405.14295","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/focus-anywhere-for-fine-grained-multi-page#ran","syntology_url":"https://syntology.ai/paper/2405.14295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14295"}},"official":null}},{"url":"/paper/multimodal-adaptive-inference-for-document","slug":"multimodal-adaptive-inference-for-document","title":"Multimodal Adaptive Inference for Document Image Classification with Anytime Early Exiting","date":"2024-05-21","arxiv_id":"2405.12705","repositories_listed":1,"syntology":null},{"url":"/paper/geocontrastnet-contrastive-key-value-edge","slug":"geocontrastnet-contrastive-key-value-edge","title":"GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document Understanding","date":"2024-05-06","arxiv_id":"2405.03104","repositories_listed":1,"syntology":null},{"url":"/paper/machine-unlearning-for-document","slug":"machine-unlearning-for-document","title":"Machine Unlearning for Document Classification","date":"2024-04-29","arxiv_id":"2404.19031","repositories_listed":1,"syntology":null},{"url":"/paper/multi-page-document-visual-question-answering","slug":"multi-page-document-visual-question-answering","title":"Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism","date":"2024-04-29","arxiv_id":"2404.19024","repositories_listed":1,"syntology":null},{"url":"/paper/omniparser-a-unified-framework-for-text","slug":"omniparser-a-unified-framework-for-text","title":"OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition","date":"2024-03-28","arxiv_id":"2403.19128","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/omniparser-a-unified-framework-for-text#ran","syntology_url":"https://syntology.ai/paper/2403.19128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19128"}},"official":{"repos":["alibabaresearch/advancedliteratemachinery"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/visually-guided-generative-text-layout-pre","slug":"visually-guided-generative-text-layout-pre","title":"Visually Guided Generative Text-Layout Pre-training for Document Intelligence","date":"2024-03-25","arxiv_id":"2403.16516","repositories_listed":1,"syntology":null},{"url":"/paper/mplug-docowl-1-5-unified-structure-learning","slug":"mplug-docowl-1-5-unified-structure-learning","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","date":"2024-03-19","arxiv_id":"2403.12895","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mplug-docowl-1-5-unified-structure-learning#ran","syntology_url":"https://syntology.ai/paper/2403.12895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12895"}},"official":{"repos":["x-plug/mplug-docowl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/textmonkey-an-ocr-free-large-multimodal-model","slug":"textmonkey-an-ocr-free-large-multimodal-model","title":"TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document","date":"2024-03-07","arxiv_id":"2403.04473","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/textmonkey-an-ocr-free-large-multimodal-model#ran","syntology_url":"https://syntology.ai/paper/2403.04473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04473"}},"official":{"repos":["yuliang-liu/monkey"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-multimodal-pre-training-for","slug":"hierarchical-multimodal-pre-training-for","title":"Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding","date":"2024-02-28","arxiv_id":"2402.18262","repositories_listed":1,"syntology":null},{"url":"/paper/m3-vrd-multimodal-multi-task-multi-teacher","slug":"m3-vrd-multimodal-multi-task-multi-teacher","title":"3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding","date":"2024-02-28","arxiv_id":"2402.17983","repositories_listed":1,"syntology":null},{"url":"/paper/financial-report-chunking-for-effective","slug":"financial-report-chunking-for-effective","title":"Financial Report Chunking for Effective Retrieval Augmented Generation","date":"2024-02-05","arxiv_id":"2402.05131","repositories_listed":1,"syntology":null},{"url":"/paper/instructdoc-a-dataset-for-zero-shot","slug":"instructdoc-a-dataset-for-zero-shot","title":"InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions","date":"2024-01-24","arxiv_id":"2401.13313","repositories_listed":1,"syntology":null},{"url":"/paper/inters-unlocking-the-power-of-large-language","slug":"inters-unlocking-the-power-of-large-language","title":"INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning","date":"2024-01-12","arxiv_id":"2401.06532","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/inters-unlocking-the-power-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2401.06532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06532"}},"official":{"repos":["daod/inters"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/soaring-from-4k-to-400k-extending-llm-s","slug":"soaring-from-4k-to-400k-extending-llm-s","title":"Long Context Compression with Activation Beacon","date":"2024-01-07","arxiv_id":"2401.03462","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-weighted-graph-representation-for","slug":"multimodal-weighted-graph-representation-for","title":"Multimodal weighted graph representation for information extraction from visually rich documents.","date":"2024-01-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/omniparser-a-unified-framework-for-text-1","slug":"omniparser-a-unified-framework-for-text-1","title":"OmniParser: A Unified Framework for Text Spotting Key Information Extraction and Table Recognition","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/privacy-aware-document-visual-question","slug":"privacy-aware-document-visual-question","title":"Privacy-Aware Document Visual Question Answering","date":"2023-12-15","arxiv_id":"2312.10108","repositories_listed":1,"syntology":null},{"url":"/paper/wordscape-a-pipeline-to-extract-multilingual-1","slug":"wordscape-a-pipeline-to-extract-multilingual-1","title":"WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data","date":"2023-12-15","arxiv_id":"2312.10188","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wordscape-a-pipeline-to-extract-multilingual-1#ran","syntology_url":"https://syntology.ai/paper/2312.10188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10188"}},"official":{"repos":["DS3Lab/WordScape"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-improving-document-understanding-an","slug":"towards-improving-document-understanding-an","title":"Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs","date":"2023-11-22","arxiv_id":"2311.13194","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-improving-document-understanding-an#ran","syntology_url":"https://syntology.ai/paper/2311.13194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13194"}},"official":{"repos":["harrytea/tgdoc"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/doctrack-a-visually-rich-document-dataset","slug":"doctrack-a-visually-rich-document-dataset","title":"DocTrack: A Visually-Rich Document Dataset Really Aligned with Human Eye Movement for Machine Reading","date":"2023-10-23","arxiv_id":"2310.14802","repositories_listed":1,"syntology":null},{"url":"/paper/docxchain-a-powerful-open-source-toolchain","slug":"docxchain-a-powerful-open-source-toolchain","title":"DocXChain: A Powerful Open-Source Toolchain for Document Parsing and Beyond","date":"2023-10-19","arxiv_id":"2310.12430","repositories_listed":1,"syntology":null},{"url":"/paper/long-range-transformer-architectures-for","slug":"long-range-transformer-architectures-for","title":"Long-Range Transformer Architectures for Document Understanding","date":"2023-09-11","arxiv_id":"2309.05503","repositories_listed":1,"syntology":null},{"url":"/paper/vision-grid-transformer-for-document-layout","slug":"vision-grid-transformer-for-document-layout","title":"Vision Grid Transformer for Document Layout Analysis","date":"2023-08-29","arxiv_id":"2308.14978","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-visually-rich-document","slug":"enhancing-visually-rich-document","title":"Enhancing Visually-Rich Document Understanding via Layout Structure Modeling","date":"2023-08-15","arxiv_id":"2308.07777","repositories_listed":1,"syntology":null},{"url":"/paper/mplug-docowl-modularized-multimodal-large","slug":"mplug-docowl-modularized-multimodal-large","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","date":"2023-07-04","arxiv_id":"2307.02499","repositories_listed":1,"syntology":null},{"url":"/paper/documentclip-linking-figures-and-main-body","slug":"documentclip-linking-figures-and-main-body","title":"DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documents","date":"2023-06-09","arxiv_id":"2306.06306","repositories_listed":1,"syntology":null},{"url":"/paper/do-good-towards-distribution-shift-evaluation","slug":"do-good-towards-distribution-shift-evaluation","title":"Do-GOOD: Towards Distribution Shift Evaluation for Pre-Trained Visual Document Understanding Models","date":"2023-06-05","arxiv_id":"2306.02623","repositories_listed":1,"syntology":null},{"url":"/paper/docformerv2-local-features-for-document","slug":"docformerv2-local-features-for-document","title":"DocFormerv2: Local Features for Document Understanding","date":"2023-06-02","arxiv_id":"2306.01733","repositories_listed":1,"syntology":null},{"url":"/paper/table-detection-for-visually-rich-document","slug":"table-detection-for-visually-rich-document","title":"Table Detection for Visually Rich Document Images","date":"2023-05-30","arxiv_id":"2305.19181","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-meets-clustering-a-hybrid","slug":"pre-training-meets-clustering-a-hybrid","title":"Pre-training Meets Clustering: A Hybrid Extractive Multi-document Summarization Model","date":"2023-05-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cream-visually-situated-natural-language","slug":"cream-visually-situated-natural-language","title":"Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models","date":"2023-05-24","arxiv_id":"2305.15080","repositories_listed":1,"syntology":null},{"url":"/paper/document-understanding-dataset-and-evaluation","slug":"document-understanding-dataset-and-evaluation","title":"Document Understanding Dataset and Evaluation (DUDE)","date":"2023-05-15","arxiv_id":"2305.08455","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/document-understanding-dataset-and-evaluation#ran","syntology_url":"https://syntology.ai/paper/2305.08455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.08455"}},"official":{"repos":["rubenpt91/MP-DocVQA-Framework"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}}],"syntology_records":34,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":39,"papers_where_code_ran_first_page":"/task/document-understanding/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":4,"url":"/task/document-understanding/papers/2","json":"/task/document-understanding/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/document-understanding/papers/3","json":"/task/document-understanding/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/document-understanding/papers/4","json":"/task/document-understanding/papers/4.json","rows":9},{"order":"ran","page":1,"of":1,"url":"/task/document-understanding/papers/ran/1","json":"/task/document-understanding/papers/ran/1.json","rows":39}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"faa40bceedf1278ac3dd48cf646ca81e7976c2121c8c53d4297eb4dec8e09231","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}