% Key papers for Layout-aware document understanding (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2017_learning_12425,
  title = {{Learning to Extract Semantic Structure From Documents Using Multimodal Fully Convolutional Neural Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{aaai2023_resdsql_4464,
  title = {{RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26535},
}

@inproceedings{aaai2022_bros_1768,
  title = {{BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/10767-bros-a-pre-trained-language-model-focusing-on-text-and-layout-for-better-key-information-extraction-from-documents/},
}

@inproceedings{cvpr2021_selfdoc_17864,
  title = {{SelfDoc: Self-Supervised Document Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2023_unifying_22471,
  title = {{Unifying Vision, Text, and Layout for Universal Document Processing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21552},
}

@inproceedings{cvpr2022_xylayoutlm_20234,
  title = {{XYLayoutLM: Towards Layout-Aware Multimodal Networks for Visually-Rich Document Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2021_towards_1538,
  title = {{Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/02738-towards-robust-visual-information-extraction-in-real-world-new-dataset-and-novel-solution/},
}

@inproceedings{iclr2021_grappa_30589,
  title = {{GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3307},
}

@inproceedings{cvpr2023_geolayoutlm_21081,
  title = {{GeoLayoutLM: Geometric Pre-Training for Visual Information Extraction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21455},
}

@inproceedings{aaai2024_docformerv2_5733,
  title = {{DocFormerv2: Local Features for Document Understanding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27828},
}

@inproceedings{cvpr2023_improving_21239,
  title = {{Improving Table Structure Recognition With Visual-Alignment Sequential Coordinate Modeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22416},
}

@inproceedings{neurips2023_obelics_68178,
  title = {{OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73589},
}

@inproceedings{icml2023_pix2struct_42568,
  title = {{Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/23459},
}

@inproceedings{cvpr2024_omniparser_24334,
  title = {{OmniParser: A Unified Framework for Text Spotting Key Information Extraction and Table Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31620},
}

@inproceedings{neurips2021_unidoc_62333,
  title = {{UniDoc: Unified Pretraining Framework for Document Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28496},
}

@inproceedings{aaai2022_unims_2907,
  title = {{UniMS: A Unified Framework for Multimodal Summarization with Knowledge Distillation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/11757-unims-a-unified-framework-for-multimodal-summarization-with-knowledge-distillation/},
}

@inproceedings{aaai2021_actionbert_77,
  title = {{ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/05931-actionbert-leveraging-user-actions-for-semantic-understanding-of-user-interfaces/},
}

@inproceedings{aaai2022_doc2ppt_1917,
  title = {{DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/00634-doc2ppt-automatic-presentation-slides-generation-from-scientific-documents/},
}

@inproceedings{aaai2020_document_102967,
  title = {{Document Summarization with VHTM: Variational Hierarchical Topic-Aware Mechanism}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6277},
}

@inproceedings{cvpr2024_enhancing_23377,
  title = {{Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29620},
}

@inproceedings{iclr2024_nougat_34889,
  title = {{Nougat: Neural Optical Understanding for Academic Documents}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18185},
}

@inproceedings{aaai2024_m2doc_6557,
  title = {{M2Doc: A Multi-Modal Fusion Approach for Document Layout Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28552},
}

@inproceedings{cvpr2024_the_25006,
  title = {{The Manga Whisperer: Automatically Generating Transcriptions for Comics}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31457},
}

@inproceedings{aaai2024_improving_6295,
  title = {{Improving Faithfulness in Abstractive Text Summarization with EDUs Using BART (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30433},
}

@inproceedings{aaai2024_relational_7102,
  title = {{Relational Programming with Foundational Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28934},
}

@inproceedings{cvpr2025_markushgrapher_26923,
  title = {{MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33619},
}

@inproceedings{aaai2024_docmsu_5734,
  title = {{DocMSU: A Comprehensive Benchmark for Document-Level Multimodal Sarcasm Understanding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29748},
}

@inproceedings{aaai2025_ldp_9667,
  title = {{LDP: Generalizing to Multilingual Visual Information Extraction by Language Decoupled Pretraining}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32730},
}

@inproceedings{aaai2025_patentlmm_10277,
  title = {{PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34257},
}

@inproceedings{aaai2025_screenmark_10697,
  title = {{ScreenMark: Watermarking Arbitrary Visual Content on Screen}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34825},
}

@inproceedings{cvpr2025_relation_27424,
  title = {{Relation-Rich Visual Document Generator for Visual Information Extraction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34517},
}

@inproceedings{aaai2025_m_9889,
  title = {{M^3EL: A Multi-task Multi-topic Dataset for Multi-modal Entity Linking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33386},
}

@inproceedings{cvpr2025_vinabench_28112,
  title = {{VinaBench: Benchmark for Faithful and Consistent Visual Narratives}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33363},
}

@inproceedings{neurips2025_text_77277,
  title = {{Text-to-Code Generation for Modular Building Layouts in Building Information Modeling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=SAEBMGJegn},
}

@inproceedings{cvpr2026_markushgrapher_95930,
  title = {{MarkushGrapher-2: End-to-end Multimodal Recognition of Chemical Structures}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Strohmeyer_MarkushGrapher-2_End-to-end_Multimodal_Recognition_of_Chemical_Structures_CVPR_2026_paper.html},
}

@inproceedings{cvpr2026_tdatr_98860,
  title = {{TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Qin_TDATR_Improving_End-to-End_Table_Recognition_via_Table_Detail-Aware_Learning_and_CVPR_2026_paper.html},
}

@inproceedings{aaai2025_collagenoter_8457,
  title = {{CollageNoter: Real-Time and Adaptive Collage Layout Design for Screenshot-Based E-Note-Taking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33588},
}