{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T17:44:14Z","timestamp":1789494254315,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":71,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373588","type":"print"},{"value":"9783032373595","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\/978-3-032-37359-5_25","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:07:29Z","timestamp":1788934049000},"page":"445-462","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Chain-of-Visual-Thought: Teaching VLMs to\u00a0See and\u00a0Think Better with\u00a0Continuous Visual Tokens"],"prefix":"10.1007","author":[{"given":"Yiming","family":"Qin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bomin","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxin","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Konstantinos","family":"Kallidromitis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephanie","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"XuDong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Acharya, M., Kafle, K., Kanan, C.: Tallyqa: answering complex counting questions. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8076\u20138084 (2019)","DOI":"10.1609\/aaai.v33i01.33018076"},{"key":"25_CR2","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"25_CR3","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Bigverdi, M., et al.: Perception tokens enhance visual reasoning in multimodal language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 3836\u20133845 (2025)","DOI":"10.1109\/CVPR52734.2025.00363"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Biran, E., Gottesman, D., Yang, S., Geva, M., Globerson, A.: Hopping too late: exploring the limitations of large language models on multi-hop queries. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 14113\u201314130 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.781"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"25_CR7","unstructured":"Chen, H., et al.: Language models are hidden reasoners: unlocking latent reasoning capabilities via self-rewarding. arXiv preprint arXiv:2411.04282 (2024)"},{"key":"25_CR8","doi-asserted-by":"publisher","first-page":"27056","DOI":"10.52202\/079017-0850","volume":"37","author":"L Chen","year":"2024","unstructured":"Chen, L., et al.: Are we on the right way for evaluating large vision-language models? Adv. Neural. Inf. Process. Syst. 37, 27056\u201327087 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR9","unstructured":"Cheng, J., Van Durme, B.: Compressed chain of thought: efficient reasoning through dense representations. arXiv preprint arXiv:2412.13171 (2024)"},{"key":"25_CR10","unstructured":"Cheng, Z., et al.: Visual thoughts: a unified perspective of understanding multimodal chain-of-thought. arXiv abs\/2505.15510 (2025)"},{"key":"25_CR11","unstructured":"DeepSeek-AI, Guo, D., et al.: Deepseek-r1: incentivizing reasoning capability in LLMs via reinforcement learning (2025). arXiv preprint arXiv:2501.12948"},{"key":"25_CR12","unstructured":"Deng, C., et\u00a0al.: Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683 (2025)"},{"key":"25_CR13","unstructured":"Deng, Y., Prasad, K., Fernandez, R., Smolensky, P., Chaudhary, V., Shieber, S.: Implicit chain of thought reasoning via knowledge distillation. arXiv preprint arXiv:2311.01460 (2023)"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Duan, H., et al.: Vlmevalkit: an open-source toolkit for evaluating large multi-modality models. Proceedings of the 32nd ACM International Conference on Multimedia (2024)","DOI":"10.1145\/3664647.3685520"},{"key":"25_CR15","unstructured":"Dubey, A., et\u00a0al.: The llama 3 herd of models. arXiv e-prints, pp. arXiv\u20132407 (2024)"},{"key":"25_CR16","unstructured":"Fu, C., et al.: MME: a comprehensive evaluation benchmark for multimodal large language models. arXiv abs\/2306.13394 (2023)"},{"key":"25_CR17","unstructured":"Fu, S., Bonnen, T., Guillory, D., Darrell, T.: Hidden in plain sight: VLMs overlook their visual representations. arXiv preprint arXiv:2506.08008 (2025)"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Fu, X., et al.: Blink: multimodal large language models can see but not perceive. In: European Conference on Computer Vision, pp. 148\u2013166. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"25_CR19","unstructured":"Goyal, S., Ji, Z., Rawat, A.S., Menon, A.K., Kumar, S., Nagarajan, V.: Think before you speak: training language models with pause tokens. arXiv preprint arXiv:2310.02226 (2023)"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Guan, T., et al.: Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14375\u201314385 (2023)","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Gupta, T., Kembhavi, A.: Visual programming: compositional visual reasoning without training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14953\u201314962 (2023)","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"25_CR22","unstructured":"Hao, S., et al.: Training large language models to reason in a continuous latent space. arXiv preprint arXiv:2412.06769 (2024)"},{"key":"25_CR23","unstructured":"Hu, J.E., et al.: Lora: low-rank adaptation of large language models. arXiv abs\/2106.09685 (2021)"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Huang, Z., Yu, N., Chen, G., Qiu, H., Debevec, P., Liu, Z.: Vchain: chain-of-visual-thought for reasoning in video generation. arXiv preprint arXiv:2510.05094 (2025)","DOI":"10.18653\/v1\/2026.findings-acl.12"},{"key":"25_CR25","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)"},{"key":"25_CR26","doi-asserted-by":"publisher","first-page":"22199","DOI":"10.52202\/068431-1613","volume":"35","author":"T Kojima","year":"2022","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. Adv. Neural. Inf. Process. Syst. 35, 22199\u201322213 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: Lisa: reasoning segmentation via large language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9579\u20139589 (2024)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"25_CR28","unstructured":"Li, B., et al.: Latent visual reasoning. arXiv preprint arXiv:2509.24251 (2025)"},{"key":"25_CR29","unstructured":"Li, B., et\u00a0al.: Llava-onevision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"25_CR30","unstructured":"Li, C., et al.: Imagine while reasoning in space: multimodal visualization-of-thought. arXiv preprint arXiv:2501.07542 (2025)"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: OCRBench: on the hidden mystery of OCR in large multimodal models. Sci. China Inf. Sci. 67 (2023)","DOI":"10.1007\/s11432-024-4235-6"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. arXiv preprint arXiv:2209.09513 (2022)","DOI":"10.52202\/068431-0182"},{"key":"25_CR34","doi-asserted-by":"publisher","first-page":"43447","DOI":"10.52202\/075280-1882","volume":"36","author":"P Lu","year":"2023","unstructured":"Lu, P., et al.: Chameleon: Plug-and-play compositional reasoning with large language models. Adv. Neural. Inf. Process. Syst. 36, 43447\u201343478 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Madaan, A., et al.: Self-refine: iterative refinement with self-feedback (2023). arXiv preprint arXiv:2303.17651","DOI":"10.52202\/075280-2019"},{"key":"25_CR36","unstructured":"Matos, J., et al.: Worldmedqa-v: a multilingual, multimodal medical examination dataset for multimodal language models evaluation. arXiv abs\/2410.12722 (2024)"},{"key":"25_CR37","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"25_CR38","unstructured":"Qiao, R., et al.: We-math: does your large multimodal model achieve human-like mathematical reasoning? arXiv abs\/2407.01284 (2024)"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Rahmanzadehgervi, P., Bolton, L., Taesiri, M.R., Nguyen, A.T.: Vision language models are blind: Failing to translate detailed visual features into words. arXiv preprint arXiv:2407.06581 (2025)","DOI":"10.1007\/978-981-96-0917-8_17"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Schwenk, D., Khandelwal, A., Clark, C., Marino, K., Mottaghi, R.: A-okvqa: a benchmark for visual question answering using world knowledge. In: European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"25_CR41","doi-asserted-by":"crossref","unstructured":"Shao, H., et al.: Visual cot: advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning. In: Advances in Neural Information Processing Systems, vol. 37 (2024)","DOI":"10.52202\/079017-0275"},{"key":"25_CR42","doi-asserted-by":"crossref","unstructured":"Su, Z., et al.: Pixel difference networks for efficient edge detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5117\u20135127 (2021)","DOI":"10.1109\/ICCV48922.2021.00507"},{"key":"25_CR43","doi-asserted-by":"crossref","unstructured":"Sur\u00eds, D., Menon, S., Vondrick, C.: ViperGPT: visual inference via python execution for reasoning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11888\u201311898 (2023)","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"25_CR44","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"25_CR45","unstructured":"Team, G., et al.: Gemma 3 technical report. arXiv preprint arXiv:2503.19786 (2025)"},{"key":"25_CR46","doi-asserted-by":"publisher","first-page":"87310","DOI":"10.52202\/079017-2771","volume":"37","author":"P Tong","year":"2024","unstructured":"Tong, P., et al.: Cambrian-1: a fully open, vision-centric exploration of multimodal LLMs. Adv. Neural. Inf. Process. Syst. 37, 87310\u201387356 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR47","doi-asserted-by":"crossref","unstructured":"Tong, S., Liu, Z., Zhai, Y., Ma, Y., LeCun, Y., Xie, S.: Eyes wide shut? Exploring the visual shortcomings of multimodal LLMs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9568\u20139578 (2024)","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"25_CR48","unstructured":"Wang, F., et al.: Muirbench: a comprehensive benchmark for robust multi-image understanding. arXiv abs\/2406.09411 (2024)"},{"key":"25_CR49","unstructured":"Wang, Q., et al.: Monet: reasoning in latent visual space beyond images and language. arXiv preprint arXiv:2511.21395 (2025)"},{"key":"25_CR50","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Divide, conquer and combine: a training-free framework for high-resolution image perception in multimodal large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 7907\u20137915 (2025)","DOI":"10.1609\/aaai.v39i8.32852"},{"key":"25_CR51","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhou, X., Fathi, A., Darrell, T., Schmid, C.: Visual lexicon: rich image features in language space. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 19736\u201319747 (2025)","DOI":"10.1109\/CVPR52734.2025.01838"},{"key":"25_CR52","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2023)"},{"key":"25_CR53","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhou, D.: Chain-of-thought reasoning without prompting. arXiv preprint arXiv:2402.10200 (2024)","DOI":"10.52202\/079017-2123"},{"key":"25_CR54","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":"25_CR55","unstructured":"Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., Duan, N.: Visual chatGPT: talking, drawing and editing with visual foundation models. arXiv preprint arXiv:2303.04671 (2023)"},{"key":"25_CR56","doi-asserted-by":"crossref","unstructured":"Wu, P., Xie, S.: V?: guided visual search as a core mechanism in multimodal LLMs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13084\u201313094 (2024)","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"25_CR57","doi-asserted-by":"crossref","unstructured":"XAI: Grok-1.5 vision preview (2024). https:\/\/x.ai\/news\/grok-1.5v. Accessed 27 June 2026","DOI":"10.32996\/jpda.2026.5.2.3"},{"key":"25_CR58","unstructured":"Xie, J., Darrell, T., Zettlemoyer, L., Wang, X.: Reconstruction alignment improves unified multimodal models. arXiv preprint arXiv:2509.07295 (2025)"},{"key":"25_CR59","unstructured":"Yang, A., et al.: Qwen3 technical report. arXiv abs\/2505.09388 (2025)"},{"key":"25_CR60","doi-asserted-by":"crossref","unstructured":"Yang, J., Yang, S., Gupta, A.W., Han, R., Fei-Fei, L., Xie, S.: Thinking in space: how multimodal large language models see, remember, and recall spaces. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10632\u201310643 (2025)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"25_CR61","doi-asserted-by":"publisher","first-page":"21875","DOI":"10.52202\/079017-0688","volume":"37","author":"L Yang","year":"2024","unstructured":"Yang, L., et al.: Depth anything v2. Adv. Neural. Inf. Process. Syst. 37, 21875\u201321911 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR62","unstructured":"Yang, Z., Yu, X., Chen, D., Shen, M., Gan, C.: Machine mental imagery: empower multimodal reasoning with latent visual tokens. arXiv preprint arXiv:2506.17218 (2025)"},{"key":"25_CR63","doi-asserted-by":"crossref","unstructured":"Yin, S., Lei, T., Liu, Y.: ToolVQA: a dataset for multi-step reasoning VQA with external tools. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4424\u20134433 (2025)","DOI":"10.1109\/ICCV51701.2025.00421"},{"key":"25_CR64","unstructured":"Ying, K., et\u00a0al.: MMT-bench: a comprehensive multimodal benchmark for evaluating large vision-language models towards multitask AGI. arXiv preprint arXiv:2404.16006 (2024)"},{"key":"25_CR65","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, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"25_CR66","unstructured":"Zhang, J., et al.: Task me anything. arXiv abs\/2406.11775 (2024)"},{"key":"25_CR67","unstructured":"Zhang, Y.F., et\u00a0al.: MME-realworld: could your multimodal LLM challenge high-resolution real-world scenarios that are difficult for humans? arXiv preprint arXiv:2408.13257 (2024)"},{"key":"25_CR68","unstructured":"Zhang, Z., Zhang, A., Li, M., Karypis, G., Smola, A., et\u00a0al.: Multimodal chain-of-thought reasoning in language models. Trans. Mach. Learn. Res. (2024)"},{"key":"25_CR69","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2016","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Semantic understanding of scenes through the ade20k dataset. Int. J. Comput. Vis. 127, 302\u2013321 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"25_CR70","unstructured":"Zhou, C., et al.: From perception to cognition: A survey of vision-language interactive reasoning in multimodal large language models. arXiv abs\/2509.25373 (2025)"},{"key":"25_CR71","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\/978-3-032-37359-5_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:07:50Z","timestamp":1788934070000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37359-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373588","9783032373595"],"references-count":71,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37359-5_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 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"}}]}}