{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T13:25:25Z","timestamp":1787405125372,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032360328","type":"print"},{"value":"9783032360335","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T00:00:00Z","timestamp":1787443200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T00:00:00Z","timestamp":1787443200000},"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":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-36033-5_25","type":"book-chapter","created":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T13:21:11Z","timestamp":1787404871000},"page":"418-434","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LiteDoc: Distilling Large Document Models into Efficient Task-Specific Encoders"],"prefix":"10.1007","author":[{"given":"Tayyab","family":"Raza","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syed Muhammad Taha","family":"Imam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adrian","family":"Ulges","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ulrich","family":"Schwanecke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9465-4678","authenticated-orcid":false,"given":"Momina","family":"Moetesum","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0922-0566","authenticated-orcid":false,"given":"Faisal","family":"Shafait","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,23]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMv3: pre-training for Document AI with unified text and image masking. In: Proceedings of the 30th ACM International Conference on Multimedia (MM 2022), Lisbon, Portugal, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: European Conference on Computer Vision (ECCV), pp. 498\u2013517. Springer, Tel Aviv (2022)","DOI":"10.1007\/978-3-031-19815-1_29"},{"issue":"120","key":"25_CR3","first-page":"1","volume":"23","author":"W Fedus","year":"2022","unstructured":"Fedus, W., Zoph, B., Shazeer, N.: Switch Transformers: scaling to trillion parameter models with simple and efficient sparsity. J. Mach. Learn. Res. (JMLR) 23(120), 1\u201339 (2022)","journal-title":"J. Mach. Learn. Res. (JMLR)"},{"key":"25_CR4","unstructured":"Du, N., et al.: GLaM: efficient scaling of language models with mixture-of-experts. In: Proceedings of the 39th International Conference on Machine Learning (ICML), vol. 162, pp. 5547\u20135569, Baltimore, MD, USA. PMLR (2022)"},{"key":"25_CR5","unstructured":"Wang, Y., et al.: BuddyMoE: exploiting expert redundancy to accelerate memory-constrained mixture-of-experts inference. In: ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming (PPoPP), Sydney, Australia (2026)"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Lo, K.M., Huang, Z., Qiu, Z., Wang, Z., Fu, J.: A closer look into mixture-of-experts in large language models. In: Findings of the Association for Computational Linguistics: NAACL 2025, pp. 4427\u20134447. Association for Computational Linguistics, Albuquerque, New Mexico (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.251"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhou, W., Zeng, Y., Zhang, X.: EfficientVLM: Fast and accurate vision-language models via knowledge distillation and modal-adaptive pruning. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 13899\u201313913. Association for Computational Linguistics, Toronto, Canada (2023)","DOI":"10.18653\/v1\/2023.findings-acl.873"},{"key":"25_CR8","unstructured":"Xie, Y., et al.: MoE-Pruner: pruning mixture-of-experts large language model using the hints from its router. Preprint at https:\/\/arxiv.org\/abs\/2410.12013 (2024)"},{"key":"25_CR9","unstructured":"Liu, E., et al.: Efficient expert pruning for sparse mixture-of-experts language models: enhancing performance and reducing inference costs. Preprint at https:\/\/arxiv.org\/abs\/2407.00945 (2024)"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, Q., et al.: Beyond text-visual attention: exploiting visual cues for effective token pruning in VLMs. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2025)","DOI":"10.1109\/ICCV51701.2025.01939"},{"key":"25_CR11","unstructured":"Kornblith, S., Norouzi, M., Lee, H., Hinton, G.: Similarity of neural network representations revisited. In: Proceedings of the 36th International Conference on Machine Learning (ICML), vol. 97, pp. 3519\u20133529, Long Beach, CA, USA. PMLR (2019)"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Do, G., Le, H., Tran, T.: SimSMoE: toward efficient training mixture of experts via solving representational collapse. In: Findings of the Association for Computational Linguistics: NAACL 2025, pp. 2012\u20132025. Association for Computational Linguistics, Albuquerque, New Mexico (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.107"},{"key":"25_CR13","unstructured":"Wu, Z., et al.: DeepSeek-VL2: mixture-of-experts vision-language models for advanced multimodal understanding. Preprint at https:\/\/arxiv.org\/abs\/2412.10302 (2024)"},{"key":"25_CR14","unstructured":"Zhao, B., Walters, R., Yu, R.: Symmetry in neural network parameter spaces. Preprint at https:\/\/arxiv.org\/abs\/2506.13018 (2025)"},{"key":"25_CR15","unstructured":"Komatsuzaki, A., et al.: Sparse upcycling: training mixture-of-experts from dense checkpoints. In: International Conference on Learning Representations (ICLR), Kigali, Rwanda (2023)"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Kudugunta, S., et al.: Beyond distillation: task-level mixture-of-experts for efficient inference. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 3577\u20133599. Association for Computational Linguistics, Punta Cana, Dominican Republic (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.304"},{"key":"25_CR17","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. Preprint at https:\/\/arxiv.org\/abs\/1503.02531 (2015)"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.V.: DocVQA: a dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.-P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: 2nd International Workshop on Open Services and Tools for Document Analysis (OST@ICDAR), pp. 1\u20136. IEEE, Sydney, Australia (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"25_CR20","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s10032-025-00542-w","volume":"28","author":"M Lamott","year":"2025","unstructured":"Lamott, M., Shakir, M.A., Ulges, A., Weweler, Y.N., Shafait, F.: SlimDoc: lightweight distillation of document transformer models. Int. J. Document Anal. Recogn. (IJDAR) 28, 457\u2013473 (2025)","journal-title":"Int. J. Document Anal. Recogn. (IJDAR)"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Kim, S., et al.: DocKD: knowledge distillation from LLMs for open-world document understanding models. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3167\u20133193. Association for Computational Linguistics, Miami, Florida, USA (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.185"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Ben Mansour, A., Karine, A., Naccache, D.: Interpret, prune and distill Donut: towards lightweight VLMs for VQA on documents. In: Document Analysis and Recognition - ICDAR 2025 Workshops, Part I, pp. 260\u2013278 (2025)","DOI":"10.1007\/978-3-032-09368-4_16"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Ye, X., Gan, Y., Ge, Y., Zhang, X.-P., Tang, Y.: ATP-LLaVA: adaptive token pruning for large vision language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 24972\u201324982 (2025)","DOI":"10.1109\/CVPR52734.2025.02325"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: SmartTrim: adaptive tokens and attention pruning for efficient vision-language models. In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING), pp. 14937\u201314953. ELRA and ICCL, Torino, Italia (2024)","DOI":"10.63317\/23hifgwadz5j"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"25_CR26","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/11564089_7","volume-title":"Algorithmic Learning Theory","author":"A Gretton","year":"2005","unstructured":"Gretton, A., Bousquet, O., Smola, A., Sch\u00f6lkopf, B.: Measuring statistical dependence with Hilbert-Schmidt norms. In: Jain, S., Simon, H.U., Tomita, E. (eds.) ALT 2005. LNCS (LNAI), vol. 3734, pp. 63\u201377. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11564089_7"},{"key":"25_CR27","unstructured":"Park, S., et al.: CORD: a consolidated receipt dataset for post-OCR parsing. In: Workshop on Document Intelligence at NeurIPS (2019)"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: ICDAR2019 competition on scanned receipt OCR and information extraction. In: Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), pp. 1516\u20131520. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Mathew, M., Bagal, V., Tito, R., Karatzas, D., Valveny, E., Jawahar, C.V.: InfographicVQA. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2582\u20132591. IEEE, Waikoloa, HI, USA (2022)","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Pasupat, P., Liang, P.: Compositional semantic parsing on semi-structured tables. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics (ACL), pp. 1470\u20131480 (2015)","DOI":"10.3115\/v1\/P15-1142"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval. In: Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), pp. 991\u2013995 (2015)","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Larson, S., Lim, G., Leach, K.: On evaluation of document classification with RVL-CDIP. In: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.eacl-main.195"},{"key":"25_CR33","unstructured":"Biten, A.F., et al.: ICDAR 2019 competition on scene text visual question answering. In: 2019 International Conference on Document Analysis and Recognition (ICDAR). IEEE (2019)"},{"key":"25_CR34","unstructured":"Lin, B., et al.: MoE-LLaVA: mixture of experts for large vision-language models. Preprint at https:\/\/arxiv.org\/abs\/2401.15947 (2024)"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: QLoRA: efficient finetuning of quantized LLMs. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 36 (2023)","DOI":"10.52202\/075280-0441"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Ma, X., Fang, G., Wang, X.: LLM-Pruner: on the structural pruning of large language models. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 36 (2023)","DOI":"10.52202\/075280-0950"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-36033-5_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T13:21:14Z","timestamp":1787404874000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36033-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,23]]},"ISBN":["9783032360328","9783032360335"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36033-5_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,23]]},"assertion":[{"value":"23 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vienna","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Austria","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}