{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T10:05:30Z","timestamp":1789207530106,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373342","type":"print"},{"value":"9783032373359","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37335-9_37","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:08:40Z","timestamp":1789204120000},"page":"677-695","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DARL: Efficient Document-to-Markup Generation via\u00a0Look-Ahead Diffusion Trajectory Sampling"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8738-0648","authenticated-orcid":false,"given":"Wentao","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2650-1663","authenticated-orcid":false,"given":"Yongxin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4212-9168","authenticated-orcid":false,"given":"Rui","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1857-5473","authenticated-orcid":false,"given":"Peirong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3863-047X","authenticated-orcid":false,"given":"Shihang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1419-059X","authenticated-orcid":false,"given":"Huiguo","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3263-3449","authenticated-orcid":false,"given":"Dezhi","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2583-4314","authenticated-orcid":false,"given":"Minghui","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5456-0957","authenticated-orcid":false,"given":"Lianwen","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"37_CR1","first-page":"17981","volume":"34","author":"J Austin","year":"2021","unstructured":"Austin, J., Johnson, D.D., Ho, J., Tarlow, D., Van Den Berg, R.: Structured denoising diffusion models in discrete state-spaces. Adv. Neural. Inf. Process. Syst. 34, 17981\u201317993 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"37_CR2","unstructured":"Bai, S., et al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"37_CR3","unstructured":"Bie, T., et\u00a0al.: Llada2.0: scaling up diffusion language models to 100b. arXiv preprint arXiv:2512.15745 (2025)"},{"key":"37_CR4","unstructured":"Cai, T., et al.: Medusa: simple LLM inference acceleration framework with multiple decoding heads. In: Proceedings of the 41st International Conference on Machine Learning, pp. 5209\u20135235 (2024)"},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, S., et\u00a0al.: SDAR: a synergistic diffusion-autoregression paradigm for scalable sequence generation. In: Findings of the Association for Computational Linguistics, ACL 2026, pp. 22058\u201322075 (2026)","DOI":"10.18653\/v1\/2026.findings-acl.1110"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, S., et al.: SDAR-VL: stable and efficient block-wise diffusion for vision-language understanding. In: Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 28882\u201328901 (2026)","DOI":"10.18653\/v1\/2026.acl-long.1333"},{"key":"37_CR7","unstructured":"Cui, C., et\u00a0al.: PaddleOCR-VL: boosting multilingual document parsing via a 0.9 b ultra-compact vision-language model. arXiv preprint arXiv:2510.14528 (2025)"},{"key":"37_CR8","unstructured":"Dao, T.: FlashAttention-2: faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691 (2023)"},{"key":"37_CR9","unstructured":"Fu, Y., Bailis, P., Stoica, I., Zhang, H.: Break the sequential dependency of LLM inference using lookahead decoding. In: International Conference on Machine Learning, pp. 14060\u201314079. PMLR (2024)"},{"key":"37_CR10","unstructured":"Grattafiori, A., et al.: The Llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"37_CR11","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Hu, A., et al.: mPLUG-DocOwl2: high-resolution compressing for OCR-free multi-page document understanding. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5817\u20135834 (2025)","DOI":"10.18653\/v1\/2025.acl-long.291"},{"key":"37_CR13","unstructured":"Khanna, S., et al.: Mercury: ultra-fast language models based on diffusion. arXiv preprint arXiv:2506.17298, 1 (2025)"},{"key":"37_CR14","unstructured":"Kou, S., Hu, L., He, Z., Deng, Z., Zhang, H.: CLLMs: consistency large language models. In: International Conference on Machine Learning, pp. 25426\u201325440. PMLR (2024)"},{"key":"37_CR15","unstructured":"Li, B., et\u00a0al.: LLaVA-OneVision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"37_CR16","first-page":"105101","volume":"38","author":"S Li","year":"2026","unstructured":"Li, S., et al.: LaViDa: a large diffusion language model for multimodal understanding. Adv. Neural. Inf. Process. Syst. 38, 105101\u2013105134 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., Wei, F., Zhang, C., Zhang, H.: EAGLE-3: scaling up inference acceleration of large language models via training-time test. In: Advances in Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-4562"},{"key":"37_CR18","unstructured":"Li, Y., Yang, G., Liu, H., Wang, B., Zhang, C.: dots.ocr: multilingual document layout parsing in a single vision-language model. arXiv preprint arXiv:2512.02498 (2025)"},{"key":"37_CR19","unstructured":"Liu, A., et al.: WeDLM: reconciling diffusion language models with standard causal attention for fast inference. arXiv preprint arXiv:2512.22737 (2025)"},{"key":"37_CR20","unstructured":"Liu, Y., et\u00a0al.: Sequential diffusion language models. arXiv preprint arXiv:2509.24007 (2025)"},{"key":"37_CR21","unstructured":"Ma, Y., et al.: dVLM-AD: enhance diffusion vision-language-model for driving via controllable reasoning. arXiv preprint arXiv:2512.04459 (2025)"},{"key":"37_CR22","unstructured":"Mandal, S., Talewar, A., Thakuria, S., Ahuja, P., Juvatkar, P.: Nanonets-OCR2: a model for transforming documents into structured markdown with intelligent content recognition and semantic tagging (2025). https:\/\/nanonets.com\/research\/nanonets-ocr-2\/"},{"key":"37_CR23","unstructured":"Niu, J., et al.: MinerU2.5: a decoupled vision-language model for efficient high-resolution document parsing (2025). https:\/\/arxiv.org\/abs\/2509.22186"},{"key":"37_CR24","doi-asserted-by":"crossref","unstructured":"Ouyang, L., et\u00a0al.: OmniDocBench: benchmarking diverse pdf document parsing with comprehensive annotations. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 24838\u201324848 (2025)","DOI":"10.1109\/CVPR52734.2025.02313"},{"key":"37_CR25","unstructured":"Poznanski, J., Soldaini, L., Lo, K.: olmOCR 2: unit test rewards for document OCR. arXiv preprint arXiv:2510.19817 (2025)"},{"key":"37_CR26","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)"},{"key":"37_CR27","doi-asserted-by":"crossref","unstructured":"Santilli, A., et al.: Accelerating transformer inference for translation via parallel decoding. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12336\u201312355 (2023)","DOI":"10.18653\/v1\/2023.acl-long.689"},{"key":"37_CR28","unstructured":"Shao, Z., et\u00a0al.: DeepSeekMath: pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)"},{"key":"37_CR29","unstructured":"Team, H.V., et\u00a0al.: HunyuanOCR technical report. arXiv preprint arXiv:2511.19575 (2025)"},{"key":"37_CR30","doi-asserted-by":"crossref","unstructured":"Wang, B., et al.: Image over text: transforming formula recognition evaluation with character detection matching. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 19681\u201319690 (2025)","DOI":"10.1109\/CVPR52734.2025.01833"},{"key":"37_CR31","unstructured":"Wang, W., et al.: InternVL3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"37_CR32","unstructured":"Wang, X., Xu, C., Jin, Y., Jin, J., Zhang, H., Deng, Z.: Diffusion LLMs can do faster-than-AR inference via discrete diffusion forcing. arXiv preprint arXiv:2508.09192 (2025)"},{"key":"37_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Make some noise: Unlocking language model parallel inference capability through noisy training. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 12914\u201312926 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.718"},{"key":"37_CR34","unstructured":"Wei, H., Sun, Y., Li, Y.: DeepSeek-OCR: contexts optical compression. arXiv preprint arXiv:2510.18234 (2025)"},{"key":"37_CR35","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: MMaDA: multimodal large diffusion language models. arXiv preprint arXiv:2505.15809 (2025)","DOI":"10.52202\/085713-4636"},{"key":"37_CR36","unstructured":"Ye, J., et al.: Dream 7B: diffusion large language models. arXiv preprint arXiv:2508.15487 (2025)"},{"key":"37_CR37","unstructured":"You, Z., et al.: LLaDA-V: large language diffusion models with visual instruction tuning. arXiv preprint arXiv:2505.16933 (2025)"},{"key":"37_CR38","doi-asserted-by":"crossref","unstructured":"Zeng, L., Yao, J., Liao, B., Tao, H., Liu, W., Wang, X.: DiffusionVL: translating any autoregressive models into diffusion vision language models. arXiv preprint arXiv:2512.15713 (2025)","DOI":"10.1007\/978-3-032-37369-4_18"},{"key":"37_CR39","unstructured":"Zhang, J., et al.: MonkeyOCR v1.5 technical report: Unlocking robust document parsing for complex patterns (2025). https:\/\/arxiv.org\/abs\/2511.10390"},{"key":"37_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, P., Jiang, J., Liu, Y., Jin, L.: MSDS: a large-scale Chinese signature and token digit string dataset for handwriting verification. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 35, pp. 36507\u201336519 (2022)","DOI":"10.52202\/068431-2645"},{"key":"37_CR41","unstructured":"Zhang, P., et al.: OCRGenBench: a comprehensive benchmark for evaluating OCR generative capabilities. arXiv preprint arXiv:2507.15085 (2025)"},{"key":"37_CR42","doi-asserted-by":"publisher","first-page":"3891","DOI":"10.1007\/s11263-025-02353-2","volume":"133","author":"P Zhang","year":"2025","unstructured":"Zhang, P., Zhang, J., Cao, J., Li, H., Jin, L.: Smaller but better: unifying layout generation with smaller large language models. Int. J. Comput. Vis. (IJCV) 133, 3891\u20133917 (2025)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"37_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, S., Gupta, D., Zheng, Q., Grover, A.: d1: scaling reasoning in diffusion large language models via reinforcement learning. arXiv preprint arXiv:2504.12216 (2025)","DOI":"10.52202\/085713-1898"},{"key":"37_CR44","unstructured":"Zhao, S., et\u00a0al.: Inpainting-guided policy optimization for diffusion large language models. arXiv preprint arXiv:2509.10396 (2025)"},{"key":"37_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1007\/978-3-030-58589-1_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Zhong","year":"2020","unstructured":"Zhong, X., ShafieiBavani, E., Jimeno Yepes, A.: Image-based table recognition: data, model, and evaluation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 564\u2013580. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_34"},{"key":"37_CR46","doi-asserted-by":"crossref","unstructured":"Zhu, F., et al.: LLaDA 1.5: variance-reduced preference optimization for large language diffusion models. In: Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 11425\u201311460 (2026)","DOI":"10.18653\/v1\/2026.acl-long.524"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37335-9_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:08:50Z","timestamp":1789204130000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37335-9_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373342","9783032373359"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37335-9_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}