{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T23:03:13Z","timestamp":1789686193575,"version":"4.0.1"},"publisher-location":"Cham","reference-count":91,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370310","type":"print"},{"value":"9783032370327","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\/978-3-032-37032-7_28","type":"book-chapter","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T22:16:02Z","timestamp":1789683362000},"page":"515-534","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AdaThinking- : One-Token Entropy Regulation for Adaptive Thinking"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3847-6396","authenticated-orcid":false,"given":"Zining","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3346-8315","authenticated-orcid":false,"given":"Tongkun","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1248-2430","authenticated-orcid":false,"given":"Boming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0242-4059","authenticated-orcid":false,"given":"Zhentao","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"28_CR1","unstructured":"Aggarwal, P., Welleck, S.: L1: Controlling how long a reasoning model thinks with reinforcement learning. arXiv preprint arXiv:2503.04697 (2025)"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Aytes, S.A., Baek, J., Hwang, S.J.: Sketch-of-thought: Efficient LLM reasoning with adaptive cognitive-inspired sketching. arXiv preprint arXiv:2503.05179 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.1236"},{"key":"28_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"28_CR4","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report (2025). https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"28_CR5","unstructured":"Bercovich, A., et al.: Llama-Nemotron: Efficient reasoning models. arXiv preprint arXiv:2505.00949 (2025)"},{"key":"28_CR6","unstructured":"Chen, H., et al.: SFT or RL? An early investigation into training R1-like reasoning large vision-language models (2025). https:\/\/arxiv.org\/abs\/2504.11468"},{"key":"28_CR7","unstructured":"Chen, S., et al.: ARES: Multimodal adaptive reasoning via difficulty-aware token-level entropy shaping. arXiv preprint arXiv:2510.08457 (2025)"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Chen, W., et al.: The overthinker\u2019s diet: Cutting token calories with difficulty-aware training. arXiv preprint arXiv:2505.19217 (2025)","DOI":"10.52202\/085713-0911"},{"key":"28_CR9","unstructured":"Chen, X., et\u00a0al.: Do not think that much for 2+ 3=? On the overthinking of o1-like LLMs. arXiv preprint arXiv:2412.21187 (2024)"},{"key":"28_CR10","unstructured":"Chen, Z., et\u00a0al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, X., et al.: Incentivizing dual process thinking for efficient large language model reasoning. arXiv preprint arXiv:2505.16315 (2025)","DOI":"10.52202\/085713-5108"},{"key":"28_CR13","unstructured":"Cuadron, A., et\u00a0al.: The danger of overthinking: Examining the reasoning-action dilemma in agentic tasks. arXiv preprint arXiv:2502.08235 (2025)"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Deng, Y., Bansal, H., Yin, F., Peng, N., Wang, W., Chang, K.W.: OpenVLThinker: An early exploration to complex vision-language reasoning via iterative self-improvement. arXiv preprint arXiv:2503.17352 (2025)","DOI":"10.52202\/085713-4126"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Duan, H., et al.: VLMEvalKit: an open-source toolkit for evaluating large multi-modality models. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 11198\u201311201 (2024)","DOI":"10.1145\/3664647.3685520"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Duan, Y., et\u00a0al.: Docopilot: improving multimodal models for document-level understanding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 4026\u20134037 (2025)","DOI":"10.1109\/CVPR52734.2025.00381"},{"issue":"12","key":"28_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4250-y","volume":"67","author":"H Feng","year":"2024","unstructured":"Feng, H., et al.: DocPedia: unleashing the power of large multimodal model in the frequency domain for versatile document understanding. Sci. China Inf. Sci. 67(12), 220106 (2024)","journal-title":"Sci. China Inf. Sci."},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Ghosal, S.S., et al.: Does thinking more always help? Understanding test-time scaling in reasoning models. arXiv preprint arXiv:2506.04210 (2025)","DOI":"10.52202\/085713-5747"},{"issue":"9","key":"28_CR19","doi-asserted-by":"publisher","first-page":"6073","DOI":"10.1109\/TCSVT.2022.3156390","volume":"32","author":"T Guan","year":"2022","unstructured":"Guan, T., et al.: Industrial scene text detection with refined feature-attentive network. IEEE Trans. Circuits Syst. Video Technol. 32(9), 6073\u20136085 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Guan, T., et al.: Self-supervised implicit glyph attention for text recognition. In: CVPR, pp. 15285\u201315294 (2023)","DOI":"10.1109\/CVPR52729.2023.01467"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Guan, T., Lin, C., Shen, W., Yang, X.: PosFormer: recognizing complex handwritten mathematical expression with position forest transformer. In: European Conference on Computer Vision, pp. 130\u2013147. Springer (2025)","DOI":"10.1007\/978-3-031-72670-5_8"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Guan, T., Shen, W., Yang, X.: CCDPlus: towards accurate character to character distillation for text recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3533737"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Guan, T., Shen, W., Yang, X., Feng, Q., Jiang, Z., Yang, X.: Self-supervised character-to-character distillation for text recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19473\u201319484 (2023)","DOI":"10.1109\/ICCV51070.2023.01784"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Guan, T., Shen, W., Yang, X., Wang, X., Yang, X.: Bridging synthetic and real worlds for pre-training scene text detectors. In: European Conference on Computer Vision, pp. 428\u2013446. Springer (2024)","DOI":"10.1007\/978-3-031-72784-9_24"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Guan, T., et al.: A token-level text image foundation model for document understanding. arXiv preprint arXiv:2503.02304 (2025)","DOI":"10.1109\/ICCV51701.2025.02155"},{"key":"28_CR26","unstructured":"Guan, T., et\u00a0al.: CodePercept: code-grounded visual stem perception for MLLMs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 33542\u201333552 (2026)"},{"key":"28_CR27","unstructured":"Guo, D., et\u00a0al.: Seed1. 5-VL technical report. arXiv preprint arXiv:2505.07062 (2025)"},{"key":"28_CR28","unstructured":"Guo, Z., Duan, C., Guan, T., Wang, Z., Zhou, K., Yan, P.: ViTexQA: A multi-frame temporal perception dataset for video text question answering. https:\/\/arxiv.org\/abs\/2606.24602 (2026)"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Hu, A., et al.: mPLUG-DocOwl 1.5: unified structure learning for OCR-free document understanding. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 3096\u20133120 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"key":"28_CR30","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":"28_CR31","unstructured":"Huang, M., Liu, Y., Liang, D., Jin, L., Bai, X.: Mini-Monkey: Alleviate the sawtooth effect by multi-scale adaptive cropping. arXiv e-prints pp. arXiv\u20132408 (2024)"},{"key":"28_CR32","unstructured":"Huang, M., Shi, Y., Peng, D., Lai, S., Xie, Z., Jin, L.: OCR-reasoning benchmark: Unveiling the true capabilities of MLLMs in complex text-rich image reasoning. arXiv preprint arXiv:2505.17163 (2025)"},{"key":"28_CR33","unstructured":"Huang, S., et al.: AdaCtrl: Towards adaptive and controllable reasoning via difficulty-aware budgeting. arXiv preprint arXiv:2505.18822 (2025)"},{"key":"28_CR34","unstructured":"Hurst, A., et al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"28_CR35","unstructured":"Jaech, A., et al.: OpenAI o1 system card. arXiv preprint arXiv:2412.16720 (2024)"},{"key":"28_CR36","doi-asserted-by":"crossref","unstructured":"Jiang, L., et al.: Think only when you need with large hybrid-reasoning models (2025). https:\/\/arxiv.org\/abs\/2505.14631","DOI":"10.52202\/085713-5323"},{"key":"28_CR37","doi-asserted-by":"crossref","unstructured":"Jin, Z., et al.: ReCUT: Balancing reasoning length and accuracy in LLMs via stepwise trails and preference optimization. arXiv preprint arXiv:2506.10822 (2025)","DOI":"10.18653\/v1\/2025.findings-emnlp.770"},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Kim, G., et al.: Visually-situated natural language understanding with contrastive reading model and frozen large language models. arXiv preprint arXiv:2305.15080 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.735"},{"key":"28_CR39","doi-asserted-by":"crossref","unstructured":"Lee, B.K., Park, B., Won\u00a0Kim, C., Man\u00a0Ro, Y.: MoAI: mixture of all intelligence for large language and vision models. In: European Conference on Computer Vision, pp. 273\u2013302. Springer (2024)","DOI":"10.1007\/978-3-031-72967-6_16"},{"key":"28_CR40","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Monkey: image resolution and text label are important things for large multi-modal models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26763\u201326773 (2024)","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Li, Z., Dong, Q., Ma, J., Zhang, D., Jia, K., Sui, Z.: SelfBudgeter: Adaptive token allocation for efficient LLM reasoning. arXiv preprint arXiv:2505.11274 (2025)","DOI":"10.18653\/v1\/2026.findings-acl.1063"},{"key":"28_CR42","doi-asserted-by":"crossref","unstructured":"Liao, W., Wang, J., Li, H., Wang, C., Huang, J., Jin, L.: DocLayLLM: an efficient multi-modal extension of large language models for text-rich document understanding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 4038\u20134049 (2025)","DOI":"10.1109\/CVPR52734.2025.00382"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: HRVDA: high-resolution visual document assistant. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15534\u201315545 (2024)","DOI":"10.1109\/CVPR52733.2024.01471"},{"key":"28_CR44","unstructured":"Liu, Y., et al.: On the hidden mystery of OCR in large multimodal models. arXiv preprint arXiv:2305.07895 (2023)"},{"key":"28_CR45","unstructured":"Liu, Y., et al.: TextMonkey: An OCR-free large multimodal model for understanding document. arXiv preprint arXiv:2403.04473 (2024)"},{"key":"28_CR46","unstructured":"Lou, C., et al.: AdaCoT: Pareto-optimal adaptive chain-of-thought triggering via reinforcement learning. arXiv preprint arXiv:2505.11896 (2025)"},{"key":"28_CR47","doi-asserted-by":"crossref","unstructured":"Lu, J., et\u00a0al.: A bounding box is worth one token-interleaving layout and text in a large language model for document understanding. In: Findings of the Association for Computational Linguistics: ACL 2025, pp. 7252\u20137273 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.379"},{"key":"28_CR48","doi-asserted-by":"crossref","unstructured":"Luo, C., Shen, Y., Zhu, Z., Zheng, Q., Yu, Z., Yao, C.: LayoutLLM: layout instruction tuning with large language models for document understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15630\u201315640 (2024)","DOI":"10.1109\/CVPR52733.2024.01480"},{"key":"28_CR49","doi-asserted-by":"crossref","unstructured":"Luo, H., et al.: O1-pruner: Length-harmonizing fine-tuning for O1-like reasoning pruning. arXiv preprint arXiv:2501.12570 (2025)","DOI":"10.18653\/v1\/2026.findings-acl.697"},{"key":"28_CR50","doi-asserted-by":"crossref","unstructured":"Ma, X., Wan, G., Yu, R., Fang, G., Wang, X.: CoT-valve: Length-compressible chain-of-thought tuning. arXiv preprint arXiv:2502.09601 (2025)","DOI":"10.18653\/v1\/2025.acl-long.300"},{"key":"28_CR51","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S., Hoque, E.: ChartQA: A benchmark for question answering about charts with visual and logical reasoning. arXiv preprint arXiv:2203.10244 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"28_CR52","first-page":"145684","volume":"38","author":"A Masry","year":"2026","unstructured":"Masry, A., et al.: AlignVLM: bridging vision and language latent spaces for multimodal document understanding. Adv. Neural. Inf. Process. Syst. 38, 145684\u2013145710 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR53","doi-asserted-by":"crossref","unstructured":"Mathew, M., Bagal, V., Tito, R., Karatzas, D., Valveny, E., Jawahar, C.: InfographicVQA. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1697\u20131706 (2022)","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"28_CR54","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: DocVQA: a dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"28_CR55","unstructured":"OpenAI: ChatGPT (2023). https:\/\/openai.com\/chatgpt"},{"key":"28_CR56","unstructured":"OpenAI: GPT-4 (2023). https:\/\/openai.com\/gpt-4"},{"key":"28_CR57","unstructured":"OpenAI: GPT-4V(ision) system card (2023). https:\/\/cdn.openai.com\/papers\/GPTV_System_Card.pdf"},{"key":"28_CR58","unstructured":"Shao, H., et al.: Visual CoT: Unleashing chain-of-thought reasoning in multi-modal language models. CoRR (2024)"},{"key":"28_CR59","unstructured":"Shao, Z., et al.: DeepSeekMath: Pushing the limits of mathematical reasoning in open language models (2024). https:\/\/arxiv.org\/abs\/2402.03300"},{"key":"28_CR60","doi-asserted-by":"crossref","unstructured":"Shen, Y., et al.: DAST: Difficulty-adaptive slow-thinking for large reasoning models. arXiv preprint arXiv:2503.04472 (2025)","DOI":"10.18653\/v1\/2025.emnlp-industry.160"},{"key":"28_CR61","unstructured":"Sheng, G., et al.: HybridFlow: A flexible and efficient RLHF framework. arXiv preprint arXiv: 2409.19256 (2024)"},{"key":"28_CR62","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"28_CR63","unstructured":"Sui, Y., et\u00a0al.: Stop overthinking: A survey on efficient reasoning for large language models. arXiv preprint arXiv:2503.16419 (2025)"},{"key":"28_CR64","doi-asserted-by":"crossref","unstructured":"Tanaka, R., Iki, T., Nishida, K., Saito, K., Suzuki, J.: InstructDoc: a dataset for zero-shot generalization of visual document understanding with instructions. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 19071\u201319079 (2024)","DOI":"10.1609\/aaai.v38i17.29874"},{"key":"28_CR65","unstructured":"Team, K., et\u00a0al.: Kimi-VL technical report. arXiv preprint arXiv:2504.07491 (2025)"},{"key":"28_CR66","unstructured":"Team, K.K.: Kwai Keye-VL technical report (2025). https:\/\/arxiv.org\/abs\/2507.01949"},{"key":"28_CR67","doi-asserted-by":"crossref","unstructured":"Tu, S., et al.: Learning when to think. In: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL. arXiv preprint arXiv:2505.10832 (2025)","DOI":"10.52202\/085713-0510"},{"key":"28_CR68","doi-asserted-by":"crossref","unstructured":"Wang, D., et al.: DocLLM: a layout-aware generative language model for multimodal document understanding. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (volume 1: long papers), pp. 8529\u20138548 (2024)","DOI":"10.18653\/v1\/2024.acl-long.463"},{"key":"28_CR69","doi-asserted-by":"crossref","unstructured":"Wang, H., Qu, C., Huang, Z., Chu, W., Lin, F., Chen, W.: VL-rethinker: Incentivizing self-reflection of vision-language models with reinforcement learning. arXiv preprint arXiv:2504.08837 (2025)","DOI":"10.52202\/085713-1037"},{"key":"28_CR70","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Marten: Visual question answering with mask generation for multi-modal document understanding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 14460\u201314471 (2025)","DOI":"10.1109\/CVPR52734.2025.01348"},{"key":"28_CR71","doi-asserted-by":"publisher","first-page":"113569","DOI":"10.52202\/079017-3609","volume":"37","author":"Z Wang","year":"2024","unstructured":"Wang, Z., et al.: CharXiv: charting gaps in realistic chart understanding in multimodal LLMs. Adv. Neural. Inf. Process. Syst. 37, 113569\u2013113697 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR72","doi-asserted-by":"publisher","first-page":"24824","DOI":"10.52202\/068431-1800","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR73","unstructured":"Wu, Y., Wang, Y., Ye, Z., Du, T., Jegelka, S., Wang, Y.: When more is less: Understanding chain-of-thought length in LLMs. arXiv preprint arXiv:2502.07266 (2025)"},{"key":"28_CR74","unstructured":"Xiang, V., et al.: Just enough thinking: Efficient reasoning with adaptive length penalties reinforcement learning. arXiv preprint arXiv:2506.05256 (2025)"},{"key":"28_CR75","doi-asserted-by":"crossref","unstructured":"Xiao, H., et al.: Adaptive markup language generation for contextually-grounded visual document understanding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 29558\u201329568 (2025)","DOI":"10.1109\/CVPR52734.2025.02752"},{"key":"28_CR76","unstructured":"Xiaomi, L.C.T.: MiMo-VL technical report (2025). https:\/\/arxiv.org\/abs\/2506.03569"},{"key":"28_CR77","unstructured":"Xu, S., Xie, W., Zhao, L., He, P.: Chain of draft: Thinking faster by writing less. arXiv preprint arXiv:2502.18600 (2025)"},{"key":"28_CR78","unstructured":"Yang, Q., Ni, B., Xiang, S., Hu, H., Peng, H., Jiang, J.: R-4B: Incentivizing general-purpose auto-thinking capability in MLLMs via Bi-mode annealing and reinforce learning. arXiv preprint arXiv:2508.21113 (2025)"},{"key":"28_CR79","unstructured":"Yang, Q., Ni, B., Xiang, S., Hu, H., Peng, H., Jiang, J.: R-4B: Incentivizing general-purpose auto-thinking capability in MLLMs via Bi-mode annealing and reinforce learning (2025). https:\/\/arxiv.org\/abs\/2508.21113"},{"key":"28_CR80","doi-asserted-by":"crossref","unstructured":"Yang, Y., et\u00a0al.: R1-Onevision: Advancing generalized multimodal reasoning through cross-modal formalization. arXiv preprint arXiv:2503.10615 (2025)","DOI":"10.1109\/ICCV51701.2025.00229"},{"key":"28_CR81","doi-asserted-by":"crossref","unstructured":"Ye, J., et\u00a0al.: UReader: universal OCR-free visually-situated language understanding with multimodal large language model. In: Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 2841\u20132858 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.187"},{"key":"28_CR82","unstructured":"Yu, Q., et al.: DAPO: An open-source LLM reinforcement learning system at scale (2025). https:\/\/arxiv.org\/abs\/2503.14476"},{"key":"28_CR83","doi-asserted-by":"crossref","unstructured":"Yu, W., Yang, Z., Liu, Y., Bai, X.: DocThinker: explainable multimodal large language models with rule-based reinforcement learning for document understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 837\u2013847 (2025)","DOI":"10.1109\/ICCV51701.2025.00086"},{"key":"28_CR84","unstructured":"Yu, Y.Q., Liao, M., Zhang, J., Wu, J.: TextHawk2: A large vision-language model excels in bilingual OCR and grounding with 16x fewer tokens. arXiv preprint arXiv:2410.05261 (2024)"},{"key":"28_CR85","unstructured":"Zeng, Z., Huang, X., Li, B., Zhang, H., Deng, Z.: Done is better than perfect: Unlocking efficient reasoning by structured multi-turn decomposition. arXiv preprint arXiv:2505.19788 (2025)"},{"key":"28_CR86","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lin, N., Hou, L., Feng, L., Li, J.: AdaptThink: Reasoning models can learn when to think (2025). https:\/\/arxiv.org\/abs\/2505.13417","DOI":"10.18653\/v1\/2025.emnlp-main.184"},{"key":"28_CR87","unstructured":"Zhang, R., Lyu, Y., Shao, R., Chen, G., Guan, W., Nie, L.: Token-level correlation-guided compression for efficient multimodal document understanding. arXiv preprint arXiv:2407.14439 (2024)"},{"key":"28_CR88","doi-asserted-by":"crossref","unstructured":"Zhao, W., et al.: Trade-offs in large reasoning models: An empirical analysis of deliberative and adaptive reasoning over foundational capabilities. arXiv preprint arXiv:2503.17979 (2025)","DOI":"10.1609\/aaai.v40i41.40802"},{"key":"28_CR89","unstructured":"Zhao, Y., et al.: SWIFT:A scalable lightweight infrastructure for fine-tuning (2024). https:\/\/arxiv.org\/abs\/2408.05517"},{"key":"28_CR90","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"},{"key":"28_CR91","unstructured":"Zhu, J., et al.: InternVL3: Exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"}],"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\/978-3-032-37032-7_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T22:16:23Z","timestamp":1789683383000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37032-7_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370310","9783032370327"],"references-count":91,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37032-7_28","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":"18 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"}}]}}