{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T08:10:29Z","timestamp":1783930229009,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":18,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234318","type":"print"},{"value":"9789819234325","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"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\/978-981-92-3432-5_11","type":"book-chapter","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:41:35Z","timestamp":1783928495000},"page":"124-136","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VBIR: Visual Brain-Inspired Inference-Time Structured Reasoning for Multimodal Large Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1210-5179","authenticated-orcid":false,"given":"Yu","family":"Ni","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanqiu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahe","family":"Chai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"issue":"13","key":"11_CR1","doi-asserted-by":"publisher","first-page":"1588","DOI":"10.1016\/j.visres.2011.02.018","volume":"51","author":"O Braddick","year":"2011","unstructured":"Braddick, O., Atkinson, J.: Development of human visual function. Vis. Res. 51(13), 1588\u20131609 (2011)","journal-title":"Vis. Res."},{"key":"11_CR2","doi-asserted-by":"publisher","unstructured":"Chen, L., et al.: BabyVision: visual reasoning beyond language. http:\/\/arxiv.org\/abs\/2601.06521,  https:\/\/doi.org\/10.48550\/arXiv.2601.06521 (2026)","DOI":"10.48550\/arXiv.2601.06521"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Felleman, D.J., Van Essen, D.C.: Distributed hierarchical processing in the primate cerebral cortex. Cereb. Cortex 1(1), 1\u201347 (1991)","DOI":"10.1093\/cercor\/1.1.1"},{"key":"11_CR4","doi-asserted-by":"publisher","unstructured":"Ghosh, S., et al.: The percept-V challenge: can multimodal LLMs crack simple perception problems? http:\/\/arxiv.org\/abs\/2508.21143, https:\/\/doi.org\/10.48550\/arXiv.2508.21143 (2026)","DOI":"10.48550\/arXiv.2508.21143"},{"key":"11_CR5","doi-asserted-by":"publisher","unstructured":"Huang, J.-T., et al.: human cognitive benchmarks reveal foundational visual gaps in MLLMs. http:\/\/arxiv.org\/abs\/2502.16435, https:\/\/doi.org\/10.48550\/arXiv.2502.16435 (2026)","DOI":"10.48550\/arXiv.2502.16435"},{"issue":"7","key":"11_CR6","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1111\/j.1551-6709.2010.01127.x","volume":"34","author":"SP Johnson","year":"2010","unstructured":"Johnson, S.P.: How infants learn about the visual world. Cogn. Sci. 34(7), 1158\u20131184 (2010). https:\/\/doi.org\/10.1111\/j.1551-6709.2010.01127.x","journal-title":"Cogn. Sci."},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Kanade, A.S., Ganu, T.: Do you see me: a multidimensional benchmark for evaluating visual perception in multimodal LLMs. In: Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 7285\u20137326 (2026)","DOI":"10.18653\/v1\/2026.eacl-long.343"},{"issue":"1","key":"11_CR8","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.tics.2012.10.011","volume":"17","author":"DJ Kravitz","year":"2013","unstructured":"Kravitz, D.J., et al.: The ventral visual pathway: an expanded neural framework for the processing of object quality. Trends Cogn. Sci. 17(1), 26\u201349 (2013)","journal-title":"Trends Cogn. Sci."},{"key":"11_CR9","unstructured":"Liu, H., et al.: LLaVANeXT: Improved reasoning, OCR, and world knowledge (2024). https:\/\/hliu.cc\/publications\/"},{"issue":"3","key":"11_CR10","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1016\/j.neuropsychologia.2007.10.005","volume":"46","author":"AD Milner","year":"2008","unstructured":"Milner, A.D., Goodale, M.A.: Two visual systems re-viewed. Neuropsychologia 46(3), 774\u2013785 (2008)","journal-title":"Neuropsychologia"},{"key":"11_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2024.105650","volume":"160","author":"ET Rolls","year":"2024","unstructured":"Rolls, E.T.: Two what, two where, visual cortical streams in humans. Neurosci. Biobehav. Rev. 160, 105650 (2024)","journal-title":"Neurosci. Biobehav. Rev."},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Sur\u00eds, D., et al.: 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":"11_CR13","doi-asserted-by":"publisher","first-page":"87310","DOI":"10.52202\/079017-2771","volume":"37","author":"S Tong","year":"2024","unstructured":"Tong, S., 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":"11_CR14","doi-asserted-by":"publisher","unstructured":"Wang, W., et al.: InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Zhou, K., Liu, Z., Gao, P. (eds.) Large Vision-Language Models. ACVPR, pp. 23\u201357. Springer, Cham (2026). https:\/\/doi.org\/10.1007\/978-3-031-94969-2_2","DOI":"10.1007\/978-3-031-94969-2_2"},{"key":"11_CR15","unstructured":"Wang, X., et al.: KidVis: do multimodal large language models possess the visual perceptual capabilities of a 6-year-old? http:\/\/arxiv.org\/abs\/2601.08292, https:\/\/doi.org\/10.48550\/arXiv.2601.08292 (2026)"},{"key":"11_CR16","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. http:\/\/arxiv.org\/abs\/2203.11171, https:\/\/doi.org\/10.48550\/arXiv.2203.11171 (2023)"},{"key":"11_CR17","unstructured":"Wu, C., et al.: Visual ChatGPT: talking, drawing and editing with visual foundation models. http:\/\/arxiv.org\/abs\/2303.04671, https:\/\/doi.org\/10.48550\/arXiv.2303.04671 (2023)"},{"key":"11_CR18","doi-asserted-by":"publisher","first-page":"11809","DOI":"10.52202\/075280-0517","volume":"36","author":"S Yao","year":"2023","unstructured":"Yao, S., et al.: Tree of thoughts: deliberate problem solving with large language models. Adv. Neural. Inf. Process. Syst. 36, 11809\u201311822 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3432-5_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:41:37Z","timestamp":1783928497000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3432-5_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"ISBN":["9789819234318","9789819234325"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3432-5_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"14 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}