{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T05:51:48Z","timestamp":1781934708281,"version":"3.54.5"},"reference-count":88,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T00:00:00Z","timestamp":1781913600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T00:00:00Z","timestamp":1781913600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s11263-026-02860-w","type":"journal-article","created":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T05:25:28Z","timestamp":1781933128000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling"],"prefix":"10.1007","volume":"134","author":[{"given":"Xudong","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghui","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuliang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9431-9247","authenticated-orcid":false,"given":"Wei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,20]]},"reference":[{"key":"2860_CR1","unstructured":"ChatGLM. https:\/\/chatglm.cn\/"},{"key":"2860_CR2","unstructured":"Gemini-Pro. https:\/\/gemini.google.com\/"},{"key":"2860_CR3","unstructured":"Kimi. https:\/\/kimi.moonshot.cn\/"},{"key":"2860_CR4","unstructured":"Qwen. https:\/\/tongyi.aliyun.com\/qianwen\/"},{"key":"2860_CR5","unstructured":"Grobid. https:\/\/github.com\/kermitt2\/grobid (2008\u20132024)"},{"key":"2860_CR6","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Tang, P., Dong, Q., Sankaran, N., Zhou, Y., & Manmatha, R. (2024). Docformerv2: Local features for document understanding. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 38, pp. 709\u2013718.","DOI":"10.1609\/aaai.v38i2.27828"},{"key":"2860_CR7","unstructured":"Bai, J., Bai, S., Yang, S., Wang, S., Tan, S., Wang, P., Lin, J., Zhou, C., & Zhou, J. (2023). Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv:2308.12966"},{"key":"2860_CR8","unstructured":"Bai, S., Cai, Y., Chen, R., Chen, K., Chen, X., Cheng, Z., Deng, L., Ding, W., Gao, C., Ge, C., Ge, W., Guo, Z., Huang, Q., Huang, J., Huang, F., Hui, B., Jiang, S., Li, Z., Li, M., Li, M., Li, K., Lin, Z., Lin, J., Liu, X., Liu, J., Liu, C., Liu, Y., Liu, D., Liu, S., Lu, D., Luo, R., Lv, C., Men, R., Meng, L., Ren, X., Ren, X., Song, S., Sun, Y., Tang, J., Tu, J., Wan, J., Wang, P., Wang, P., Wang, Q., Wang, Y., Xie, T., Xu, Y., Xu, H., Xu, J., Yang, Z., Yang, M., Yang, J., Yang, A., Yu, B., Zhang, F., Zhang, H., Zhang, X., Zheng, B., Zhong, H., Zhou, J., Zhou, F., Zhou, J., Zhu, Y., & Zhu, K. (2025). Qwen3-vl technical report. arXiv:2511.21631"},{"key":"2860_CR9","unstructured":"Bai, S., Chen, K., Liu, X., Wang, J., Ge, W., Song, S., Dang, K., Wang, P., Wang, S., Tang, J., Zhong, H., Zhu, Y., Yang, M., Li, Z., Wan, J., Wang, P., Ding, W., Fu, Z., Xu, Y., Ye, J., Zhang, X., Xie, T., Cheng, Z., Zhang, H., Yang, Z., Xu, H., & Lin, J. (2025). Qwen2.5-vl technical report. arXiv:2502.13923"},{"key":"2860_CR10","unstructured":"Beltagy, I., Peters, M.E., & Cohan, A. (2020). Longformer: The long-document transformer. arXiv:2004.05150"},{"key":"2860_CR11","doi-asserted-by":"crossref","unstructured":"Blau, T., Fogel, S., Ronen, R., Golts, A., Ganz, R., Ben\u00a0Avraham, E., Aberdam, A., Tsiper, S., & Litman, R. (2024). Gram: Global reasoning for multi-page vqa. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15598\u201315607.","DOI":"10.1109\/CVPR52733.2024.01477"},{"key":"2860_CR12","unstructured":"Chen, A., Giovannini, S., Gemelli, A., Coppini, F., & Marinai, S. (2025). Towards reliable and interpretable document question answering via vlms. arXiv:2509.10129"},{"key":"2860_CR13","unstructured":"Chen, J., Zhang, R., Zhou, Y., Yu, T., Dernoncourt, F., Gu, J., Rossi, R.A., Chen, C., & Sun, T. (2025) SV-RAG: LoRA-contextualizing adaptation of MLLMs for long document understanding. In: The Thirteenth International Conference on Learning Representations https:\/\/openreview.net\/forum?id=FDaHjwInXO"},{"key":"2860_CR14","doi-asserted-by":"crossref","unstructured":"Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., & Liu, Z. (2024) Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv:2402.03216","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"2860_CR15","unstructured":"Chen, W., Wang, Q., Long, Z., Zhang, X., Lu, Z., Li, B., Wang, S., Xu, J., Bai, X., & Huang, X., et\u00a0al. (2023). Disc-finllm: A chinese financial large language model based on multiple experts fine-tuning. arXiv:2310.15205"},{"key":"2860_CR16","unstructured":"Chen, Y., Qian, S., Tang, H., Lai, X., Liu, Z., Han, S., Jia, J. (2024). LongloRA: Efficient fine-tuning of long-context large language models. In: The Twelfth International Conference on Learning Representations."},{"key":"2860_CR17","unstructured":"Chen, Z., Wang, W., Cao, Y., Liu, Y., Gao, Z., Cui, E., Zhu, J., Ye, S., Tian, H., & Liu, Z., et\u00a0al. (2024) Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv:2412.05271"},{"key":"2860_CR18","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, W., Tian, H., Ye, S., Gao, Z., Cui, E., Tong, W., Hu, K., Luo, J., & Ma, Z., et\u00a0al. (2024) How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites. arXiv:2404.16821","DOI":"10.1007\/s11432-024-4231-5"},{"key":"2860_CR19","doi-asserted-by":"crossref","unstructured":"Dasigi, P., Lo, K., Beltagy, I., Cohan, A., Smith, N.A., & Gardner, M. (2021). A dataset of information-seeking questions and answers anchored in research papers. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. pp. 4599\u20134610.","DOI":"10.18653\/v1\/2021.naacl-main.365"},{"key":"2860_CR20","unstructured":"Dong, X., Zhang, P., Zang, Y., Cao, Y., Wang, B., Ouyang, L., Wei, X., Zhang, S., Duan, H., Cao, M., Zhang, W., Li, Y., Yan, H., Gao, Y., Zhang, X., Li, W., Li, J., Chen, K., He, C., Zhang, X., Qiao, Y., Lin, D., & Wang, J. (2024a). Internlm-xcomposer2: Mastering free-form text-image composition and comprehension in vision-language large model. arXiv:2401.16420"},{"key":"2860_CR21","doi-asserted-by":"crossref","unstructured":"Dong, X., Zhang, P., Zang, Y., Cao, Y., Wang, B., Ouyang, L., Zhang, S., Duan, H., Zhang, W., Li, Y., Yan, H., Gao, Y., Chen, Z., Zhang, X., Li, W., Li, J., Wang, W., Chen, K., He, C., Zhang, X., Dai, J., Qiao, Y., Lin, D., & Wang, J. (2024b) Internlm-xcomposer2-4khd: A pioneering large vision-language model handling resolutions from 336 pixels to 4k hd. arXiv:2404.06512","DOI":"10.52202\/079017-1348"},{"key":"2860_CR22","unstructured":"Edge, D., Trinh, H., Cheng, N., Bradley, J., Chao, A., Mody, A., Truitt, S., & Larson, J. (2024). From local to global: A graph rag approach to query-focused summarization. arXiv:2404.16130"},{"key":"2860_CR23","unstructured":"Faysse, M., Sibille, H., Wu, T., Omrani, B., Viaud, G., HUDELOT, C., Colombo, P. (2025). Colpali: Efficient document retrieval with vision language models. In: The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ogjBpZ8uSi"},{"key":"2860_CR24","doi-asserted-by":"crossref","unstructured":"Feng, H., Liu, Q., Liu, H., Zhou, W., Li, H., & Huang, C. (2023) Docpedia: Unleashing the power of large multimodal model in the frequency domain for versatile document understanding. arXiv:2311.11810","DOI":"10.1007\/s11432-024-4250-y"},{"key":"2860_CR25","unstructured":"Feng, H., Wang, Z., Tang, J., Lu, J., Zhou, W., Li, H., & Huang, C. (2023) Unidoc: A universal large multimodal model for simultaneous text detection, recognition, spotting and understanding. arXiv:2308.11592"},{"key":"2860_CR26","doi-asserted-by":"crossref","unstructured":"Hong, W., Wang, W., Ding, M., Yu, W., Lv, Q., Wang, Y., Cheng, Y., Huang, S., Ji, J., & Xue, Z., et\u00a0al. (2024) Cogvlm2: Visual language models for image and video understanding. arXiv:2408.16500","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"2860_CR27","doi-asserted-by":"crossref","unstructured":"Hu, A., Xu, H., Zhang, L., Ye, J., Yan, M., Zhang, J., Jin, Q., Huang, F., & Zhou, J. (2024). mplug-docowl2: High-resolution compressing for ocr-free multi-page document understanding. arXiv:2409.03420","DOI":"10.18653\/v1\/2025.acl-long.291"},{"key":"2860_CR28","unstructured":"Hu, S., Tu, Y., Han, X., He, C., Cui, G., Long, X., Zheng, Z., Fang, Y., Huang, Y., Zhao, W., et\u00a0al. (2024). Minicpm: Unveiling the potential of small language models with scalable training strategies. arXiv:2404.06395"},{"key":"2860_CR29","doi-asserted-by":"crossref","unstructured":"Huang, L., Cao, S., Parulian, N., Ji, H., & Wang, L. (2021). Efficient attentions for long document summarization. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. pp. 1419\u20131436.","DOI":"10.18653\/v1\/2021.naacl-main.112"},{"key":"2860_CR30","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., & Wei, F. (2022). Layoutlmv3: Pre-training for document ai with unified text and image masking. In: Proceedings of the 30th ACM International Conference on Multimedia. pp. 4083\u20134091.","DOI":"10.1145\/3503161.3548112"},{"key":"2860_CR31","doi-asserted-by":"crossref","unstructured":"Huang, Z., Chen, K., He, J., Bai, X., Karatzas, D., Lu, S., & Jawahar, C. (2019) Icdar2019 competition on scanned receipt ocr and information extraction. In: ICDAR. pp. 1516\u20131520.","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"2860_CR32","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et\u00a0al. (2023). Segment anything. arXiv:2304.02643","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2860_CR33","doi-asserted-by":"crossref","unstructured":"Lauren\u00e7on, H., Saulnier, L., Tronchon, L., Bekman, S., Singh, A., Lozhkov, A., Wang, T., Karamcheti, S., Rush, A., Kiela, D., et\u00a0al. (2024). Obelics: An open web-scale filtered dataset of interleaved image-text documents. Advances in Neural Information Processing Systems 36.","DOI":"10.52202\/075280-3138"},{"key":"2860_CR34","doi-asserted-by":"crossref","unstructured":"Li, L., Wang, Y., Xu, R., Wang, P., Feng, X., Kong, L., & Liu, Q. (2024). Multimodal arxiv: A dataset for improving scientific comprehension of large vision-language models. arXiv:2403.00231","DOI":"10.18653\/v1\/2024.acl-long.775"},{"key":"2860_CR35","doi-asserted-by":"crossref","unstructured":"Li, M., Xu, Y., Cui, L., Huang, S., Wei, F., Li, Z., & Zhou, M. (2020). Docbank: A benchmark dataset for document layout analysis. arXiv:2006.01038","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"2860_CR36","doi-asserted-by":"crossref","unstructured":"Li, Z., Yang, B., Liu, Q., Ma, Z., Zhang, S., Yang, J., Sun, Y., Liu, Y., & Bai, X. (2023). Monkey: Image resolution and text label are important things for large multi-modal models. arXiv:2311.06607","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"2860_CR37","doi-asserted-by":"crossref","unstructured":"Lin, J., Yin, H., Ping, W., Molchanov, P., Shoeybi, M., & Han, S. (2024). Vila: On pre-training for visual language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 26689\u201326699.","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"2860_CR38","unstructured":"Liu, C., Wei, H., Chen, J., Kong, L., Ge, Z., Zhu, Z., Zhao, L., Sun, J., Han, C., & Zhang, X. (2024). Focus anywhere for fine-grained multi-page document understanding. arXiv:2405.14295"},{"key":"2860_CR39","unstructured":"Liu, H., Li, C., Li, Y., Li, B., Zhang, Y., Shen, S., & Lee, Y.J. (2024). Llava-next: Improved reasoning, ocr, and world knowledge. https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"2860_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Y., Xie, X., Liu, Y., & Bai, X. (2025). Multi-scenario overlapping text segmentation with depth awareness. In: Proceedings of the IEEE\/CVF international conference on computer vision (pp. 17454\u201317463).","DOI":"10.1109\/ICCV51701.2025.01621"},{"key":"2860_CR41","unstructured":"Liu, Y., Yang, B., Liu, Q., Li, Z., Ma, Z., Zhang, S., & Bai, X. (2024). Textmonkey: An ocr-free large multimodal model for understanding document. arXiv:2403.04473"},{"key":"2860_CR42","unstructured":"Lyu, P., Li, Y., Zhou, H., Ma, W., Wan, X., Xie, Q., Wu, L., Zhang, C., Yao, K., Ding, E., et\u00a0al. (2024). Structextv3: An efficient vision-language model for text-rich image perception, comprehension, and beyond. arXiv:2405.21013"},{"key":"2860_CR43","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S., & Hoque, E. (2022). Chartqa: A benchmark for question answering about charts with visual and logical reasoning. arXiv:2203.10244","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"2860_CR44","doi-asserted-by":"crossref","unstructured":"Mathew, M., Bagal, V., Tito, R., Karatzas, D., Valveny, E., & Jawahar, C. (2022). Infographicvqa. In: WACV. pp. 1697\u20131706.","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"2860_CR45","unstructured":"Mathew, M., Karatzas, D., & Jawahar, C.V. (2011). Docvqa: A dataset for vqa on document images. In: WACV. pp. 2200\u20132209."},{"key":"2860_CR46","doi-asserted-by":"crossref","unstructured":"Mishra, A., Shekhar, S., Singh, A.K., & Chakraborty, A. (2019). Ocr-vqa: Visual question answering by reading text in images. In: ICDAR. pp. 947\u2013952.","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"2860_CR47","unstructured":"OpenAI: Gpt-4v(ision) system card. https:\/\/openai.com\/contributions\/gpt-4v (2023)"},{"key":"2860_CR48","unstructured":"Park, S., Shin, S., Lee, B., Lee, J., Surh, J., Seo, M., & Lee, H. (2019). Cord: A consolidated receipt dataset for post-ocr parsing. In: Workshop on Document Intelligence at NeurIPS."},{"key":"2860_CR49","unstructured":"Peng, B., Quesnelle, J., Fan, H., & Shippole, E. (2024). YaRN: Efficient context window extension of large language models. In: The Twelfth International Conference on Learning Representations."},{"key":"2860_CR50","doi-asserted-by":"crossref","unstructured":"Pfitzmann, B., Auer, C., Dolfi, M., Nassar, A.S., & Staar, P. (2022). Doclaynet: a large human-annotated dataset for document-layout segmentation. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. pp. 3743\u20133751.","DOI":"10.1145\/3534678.3539043"},{"key":"2860_CR51","doi-asserted-by":"crossref","unstructured":"Prem\u00a0Jacob, T., Bizotto, B.L.S., & Sathiyanarayanan, M. (2024). Constructing the chatgpt for pdf files with langchain \u2013 ai. In: 2024 International Conference on Inventive Computation Technologies (ICICT). pp. 835\u2013839.","DOI":"10.1109\/ICICT60155.2024.10544643"},{"key":"2860_CR52","unstructured":"Reid, M., Savinov, N., Teplyashin, D., Lepikhin, D., Lillicrap, T., Alayrac, J.B., Soricut, R., Lazaridou, A., Firat, O., Schrittwieser, J., et\u00a0al. (2024). Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv:2403.05530"},{"key":"2860_CR53","doi-asserted-by":"crossref","unstructured":"Saad-Falcon, J., Barrow, J., Siu, A., Nenkova, A., Yoon, D.S., Rossi, R.A., & Dernoncourt, F. (2023). Pdftriage: Question answering over long, structured documents. arXiv:2309.08872","DOI":"10.18653\/v1\/2024.emnlp-industry.13"},{"key":"2860_CR54","unstructured":"Sarthi, P., Abdullah, S., Tuli, A., Khanna, S., Goldie, A., & Manning, C.D. (2024). RAPTOR: Recursive abstractive processing for tree-organized retrieval. In: The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=GN921JHCRw"},{"key":"2860_CR55","doi-asserted-by":"crossref","unstructured":"\u0160imsa, \u0160., \u0160ulc, M., U\u0159i\u010d\u00e1\u0159, M., Patel, Y., Hamdi, A., Koci\u00e1n, M., Skalick\u1ef3, M., Matas, J., Doucet, A., Coustaty, M., et\u00a0al. (2023). Docile benchmark for document information localization and extraction pp. 147\u2013166","DOI":"10.1007\/978-3-031-41679-8_9"},{"key":"2860_CR56","unstructured":"Souibgui, M.A., Choi, C., Barsky, A., Jung, K., Valveny, E., & Karatzas, D. (2025). Docvxqa: Context-aware visual explanations for document question answering. arXiv:2505.07496"},{"key":"2860_CR57","doi-asserted-by":"crossref","unstructured":"Sun, Q., Cui, Y., Zhang, X., Zhang, F., Yu, Q., Wang, Y., Rao, Y., Liu, J., Huang, T., & Wang, X. (2024). Generative multimodal models are in-context learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14398\u201314409.","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"2860_CR58","doi-asserted-by":"crossref","unstructured":"Tanaka, R., Nishida, K., Nishida, K., Hasegawa, T., Saito, I., & Saito, K. (2023). Slidevqa: A dataset for document visual question answering on multiple images. In: AAAI. pp. 13636\u201313645.","DOI":"10.1609\/aaai.v37i11.26598"},{"key":"2860_CR59","unstructured":"Tang, Y., & Yang, Y. (2024). Multihop-rag: Benchmarking retrieval-augmented generation for multi-hop queries. arXiv:2401.15391"},{"key":"2860_CR60","unstructured":"Team, G.V., Karlinsky, L., Arbelle, A., Daniels, A., Nassar, A., Alfassi, A., Wu, B., Schwartz, E., Joshi, D., Kondic, J., et\u00a0al. (2025). Granite vision: a lightweight, open-source multimodal model for enterprise intelligence. arXiv:2502.09927"},{"key":"2860_CR61","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109834","volume":"144","author":"R Tito","year":"2023","unstructured":"Tito, R., Karatzas, D., & Valveny, E. (2023). Hierarchical multimodal transformers for multipage docvqa. Pattern Recognition, 144, Article 109834.","journal-title":"Pattern Recognition"},{"key":"2860_CR62","doi-asserted-by":"crossref","unstructured":"Tworkowski, S., Staniszewski, K., Pacek, M.a., Wu, Y., Michalewski, H., & Mi\u0142\u00a0o\u015b, P. (2023). Focused transformer: Contrastive training for context scaling. In: Advances in Neural Information Processing Systems. (Vol. 36, pp. 42661\u201342688).","DOI":"10.52202\/075280-1849"},{"key":"2860_CR63","doi-asserted-by":"crossref","unstructured":"Van\u00a0Landeghem, J., Tito, R., Borchmann, \u0141., Pietruszka, M., Joziak, P., Powalski, R., Jurkiewicz, D., Coustaty, M., Anckaert, B., Valveny, E., et\u00a0al. (2023). Document understanding dataset and evaluation (dude). In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 19528\u201319540.","DOI":"10.1109\/ICCV51070.2023.01789"},{"key":"2860_CR64","unstructured":"Wang, B., Xu, C., Zhao, X., Ouyang, L., Wu, F., Zhao, Z., Xu, R., Liu, K., Qu, Y., Shang, F., Zhang, B., Wei, L., Sui, Z., Li, W., Shi, B., Qiao, Y., Lin, D., & He, C. (2024a). Mineru: An open-source solution for precise document content extraction. arXiv:2409.18839"},{"key":"2860_CR65","unstructured":"Wang, P., Bai, S., Tan, S., Wang, S., Fan, Z., Bai, J., Chen, K., Liu, X., Wang, J., Ge, W., Fan, Y., Dang, K., Du, M., Ren, X., Men, R., Liu, D., Zhou, C., Zhou, J., & Lin, J. (2024b). Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution. arXiv:2409.12191"},{"key":"2860_CR66","unstructured":"Wang, W., Gao, Z., Gu, L., Pu, H., Cui, L., Wei, X., Liu, Z., Jing, L., Ye, S., Shao, J., et\u00a0al. (2025). Internvl3.5: Advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv:2508.18265"},{"key":"2860_CR67","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhang, S., Ren, Y., Duan, Y., Li, T., Liu, S., Hu, M., Chen, Z., Zhang, K., Lu, L., et\u00a0al. (2024). Needle in a multimodal haystack. arXiv:2406.07230","DOI":"10.52202\/079017-0649"},{"key":"2860_CR68","doi-asserted-by":"crossref","unstructured":"Wei, H., Kong, L., Chen, J., Zhao, L., Ge, Z., Yang, J., Sun, J., Han, C., & Zhang, X. (2024) Vary: Scaling up the vision vocabulary for large vision-language model. In: European Conference on Computer Vision. (pp. 408\u2013424). Springer.","DOI":"10.1007\/978-3-031-73235-5_23"},{"issue":"9","key":"2860_CR69","doi-asserted-by":"publisher","first-page":"4019","DOI":"10.1007\/s11263-024-02063-1","volume":"132","author":"W Wu","year":"2024","unstructured":"Wu, W., Cai, Y., Shen, C., Zhang, D., Fu, Y., Zhou, H., & Luo, P. (2024). End-to-end video text spotting with transformer. International Journal of Computer Vision, 132(9), 4019\u20134035.","journal-title":"International Journal of Computer Vision"},{"key":"2860_CR70","unstructured":"Xia, R., Mao, S., Yan, X., Zhou, H., Zhang, B., Peng, H., Pi, J., Fu, D., Wu, W., Ye, H., et\u00a0al. (2024a). Docgenome: An open large-scale scientific document benchmark for training and testing multi-modal large language models. arXiv:2406.11633"},{"key":"2860_CR71","unstructured":"Yan, H., Liu, Y., Liu, X., Zhang, Y., Liao, M., Wu, J., Chen, W., & Bai, X. (2026). DocSeeker: Structured visual reasoning with evidence grounding for long document understanding. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition."},{"key":"2860_CR72","doi-asserted-by":"crossref","unstructured":"Xia, R., Zhang, B., Ye, H., Yan, X., Liu, Q., Zhou, H., Chen, Z., Dou, M., Shi, B., Yan, J., et\u00a0al. (2024b). Chartx & chartvlm: A versatile benchmark and foundation model for complicated chart reasoning. arXiv:2402.12185","DOI":"10.1109\/TIP.2025.3607618"},{"key":"2860_CR73","unstructured":"Yao, Y., Yu, T., Zhang, A., Wang, C., Cui, J., Zhu, H., Cai, T., Li, H., Zhao, W., He, Z., et\u00a0al. (2024). Minicpm-v: A gpt-4v level mllm on your phone. arXiv:2408.01800"},{"key":"2860_CR74","unstructured":"Ye, J., Hu, A., Xu, H., Ye, Q., Yan, M., Dan, Y., Zhao, C., Xu, G., Li, C., Tian, J., et\u00a0al. (2023). mplug-docowl: Modularized multimodal large language model for document understanding. arXiv:2307.02499"},{"key":"2860_CR75","doi-asserted-by":"crossref","unstructured":"Ye, J., Hu, A., Xu, H., Ye, Q., Yan, M., Xu, G., Li, C., Tian, J., Qian, Q., Zhang, J., et\u00a0al. (2023). Ureader: Universal ocr-free visually-situated language understanding with multimodal large language model. arXiv:2310.05126","DOI":"10.18653\/v1\/2023.findings-emnlp.187"},{"key":"2860_CR76","unstructured":"Yin, L., Xie, X., Li, Z., Bai, X., and Liu, Y. (2025). MSTAR: Box-free multi-query scene text retrieval with attention recycling. In: The thirty-ninth annual conference on neural information processing systems."},{"key":"2860_CR77","unstructured":"Yu, S., Tang, C., Xu, B., Cui, J., Ran, J., Yan, Y., Liu, Z., Wang, S., Han, X., Liu, Z., et\u00a0al. (2024). Visrag: Vision-based retrieval-augmented generation on multi-modality documents. arXiv:2410.10594"},{"key":"2860_CR78","unstructured":"Yu, T., Wang, Z., Wang, C., Huang, F., Ma, W., He, Z., Cai, T., Chen, W., Huang, Y., Zhao, Y., et\u00a0al. (2025). Minicpm-v 4.5: Cooking efficient mllms via architecture, data, and training recipe. arXiv:2509.18154"},{"key":"2860_CR79","unstructured":"Yu, Y.Q., Liao, M., Wu, J., Liao, Y., Zheng, X., & Zeng, W. (2024). Texthawk: Exploring efficient fine-grained perception of multimodal large language models arXiv:2404.09204"},{"key":"2860_CR80","doi-asserted-by":"crossref","unstructured":"Yu, W., Yang, Z., Liu, Y., and Bai, X. (2025). Docthinker: Explainable multimodal large language models with rule-basedreinforcement learning for document understanding. In: Proceedings of the IEEE\/CVF international conference on computer vision (pp. 837\u2013847).","DOI":"10.1109\/ICCV51701.2025.00086"},{"key":"2860_CR81","unstructured":"Yue, S., Chen, W., Wang, S., Li, B., Shen, C., Liu, S., Zhou, Y., Xiao, Y., Yun, S., Huang, X., et\u00a0al. (2023). Disc-lawllm: Fine-tuning large language models for intelligent legal services arXiv:2309.11325"},{"key":"2860_CR82","unstructured":"Zaheer, M., Guruganesh, G., Dubey, K. A., Ainslie, J., Alberti, C., Ontanon, S., Pham, P., Ravula, A., Wang, Q., Yang, L., et al. (2020). Big bird: Transformers for longer sequences. Advances in neural information processing systems,33, 17283\u201317297."},{"key":"2860_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, E., Li, Y., Liu, Y., Zhu, Y., & Bai, X. (2025). Towards comprehensive lecture slides understanding: Large-scale dataset and effective method. In: Proceedings of the IEEE\/CVF international conference on computer vision (pp. 4455\u20134464).","DOI":"10.1109\/ICCV51701.2025.00424"},{"key":"2860_CR84","doi-asserted-by":"crossref","unstructured":"Zhang, J., Yu, Y., & Zhang, Y. (2024). Cream: Coarse-to-fine retrieval and multi-modal efficient tuning for document vqa. In: Proceedings of the 32nd ACM International Conference on Multimedia. (pp. 925\u2013934).","DOI":"10.1145\/3664647.3680750"},{"key":"2860_CR85","doi-asserted-by":"crossref","unstructured":"Zhang, P., Zhang, J., Cao, J., Li, H., & Jin, L. (2025). Smaller but better: Unifying layout generation with smaller large language models. International Journal of Computer Vision. (pp. 1\u201327).","DOI":"10.1007\/s11263-025-02353-2"},{"issue":"8","key":"2860_CR86","doi-asserted-by":"publisher","first-page":"3119","DOI":"10.1007\/s11263-024-02022-w","volume":"132","author":"X Zhao","year":"2024","unstructured":"Zhao, X., Feng, W., Zhang, Z., Lv, J., Zhu, X., Lin, Z., Hu, J., & Shao, J. (2024). Cbnet: A plug-and-play network for segmentation-based scene text detection. International Journal of Computer Vision, 132(8), 3119\u20133138.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"2860_CR87","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/s11263-023-01880-0","volume":"132","author":"T Zheng","year":"2024","unstructured":"Zheng, T., Chen, Z., Fang, S., Xie, H., & Jiang, Y. G. (2024). Cdistnet: Perceiving multi-domain character distance for robust text recognition. International Journal of Computer Vision, 132(2), 300\u2013318.","journal-title":"International Journal of Computer Vision"},{"key":"2860_CR88","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., & Yepes, A.J. (2019). Publaynet: Largest dataset ever for document layout analysis. In: 2019 International conference on document analysis and recognition (ICDAR). (pp. 1015\u20131022). IEEE.","DOI":"10.1109\/ICDAR.2019.00166"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02860-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02860-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02860-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T05:25:52Z","timestamp":1781933152000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02860-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,20]]},"references-count":88,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["2860"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02860-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,20]]},"assertion":[{"value":"2 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}],"article-number":"324"}}