{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T07:01:13Z","timestamp":1771743673011,"version":"3.50.1"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049704","type":"print"},{"value":"9783032049711","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"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\/978-3-032-04971-1_6","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T17:10:28Z","timestamp":1758301828000},"page":"57-66","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CARE-VL: A Domain-Specialized Vision-Language Model for\u00a0Early ASD Screening"],"prefix":"10.1007","author":[{"given":"Cheol-Hwan","family":"Yoo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jang-Hee","family":"Yoo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaeyoon","family":"Jang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"American Psychiatric\u00a0Association, D., American Psychiatric\u00a0Association, D., et\u00a0al.: Diagnostic and statistical manual of mental disorders: DSM-5, vol.\u00a05. American psychiatric association Washington, DC (2013)","DOI":"10.1176\/appi.books.9780890425596"},{"issue":"6","key":"6_CR2","doi-asserted-by":"publisher","first-page":"1891","DOI":"10.1046\/j.1460-9568.1999.00621.x","volume":"11","author":"S Baron-Cohen","year":"1999","unstructured":"Baron-Cohen, S., et al.: Social intelligence in the normal and autistic brain: an FMRI study. Eur. J. Neurosci. 11(6), 1891\u20131898 (1999)","journal-title":"Eur. J. Neurosci."},{"key":"6_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR4","unstructured":"Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to algorithms. MIT press (2022)"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Deng, S., et\u00a0al.: Hear me, see me, understand me: Audio-visual autism behavior recognition (2024). arXiv preprint arXiv:2406.02554","DOI":"10.1109\/TMM.2024.3521838"},{"key":"6_CR6","unstructured":"Dubey, A., et\u00a0al.: The llama 3 herd of models (2024). arXiv preprint arXiv:2407.21783"},{"issue":"21","key":"6_CR7","first-page":"591","volume":"21","author":"F Edition","year":"2013","unstructured":"Edition, F., et al.: Diagnostic and statistical manual of mental disorders. Am Psychiatric Assoc 21(21), 591\u2013643 (2013)","journal-title":"Am Psychiatric Assoc"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"He, B., et al.: Ma-LMM: Memory-augmented large multimodal model for long-term video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13504\u201313514 (2024)","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Jin, P., Takanobu, R., Zhang, W., Cao, X., Yuan, L.: Chat-univi: Unified visual representation empowers large language models with image and video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13700\u201313710 (2024)","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"6_CR10","unstructured":"Kumar, A., et\u00a0al.: Training language models to self-correct via reinforcement learning (2024). arXiv preprint arXiv:2409.12917"},{"key":"6_CR11","unstructured":"Li, B., et\u00a0al.: Llava-onevision: Easy visual task transfer (2024). arXiv preprint arXiv:2408.03326"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Llava-med: Training a large language-and-vision assistant for biomedicine in one day. Adv. Neural Inf. Process. Syst. 36 (2024)","DOI":"10.32388\/VLXB6M"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Lin, B., et al.: Video-llava: Learning united visual representation by alignment before projection (2023). arXiv preprint arXiv:2311.10122","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"6_CR14","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1023\/A:1005592401947","volume":"30","author":"C Lord","year":"2000","unstructured":"Lord, C., et al.: The autism diagnostic observation schedule\u2013generic: a standard measure of social and communication deficits associated with the spectrum of autism. J. Autism Dev. Disord. 30, 205\u2013223 (2000)","journal-title":"J. Autism Dev. Disord."},{"key":"6_CR15","unstructured":"Madaan, A., et\u00a0al.: Self-refine: Iterative refinement with self-feedback. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"6_CR16","unstructured":"Min, S., .: Rethinking the role of demonstrations: what makes in-context learning work? (2022). https:\/\/arxiv.org\/abs\/2202.12837"},{"key":"6_CR17","unstructured":"Moor, M., et al.: Med-flamingo: a multimodal medical few-shot learner. In: Machine Learning for Health (ML4H), pp. 353\u2013367. PMLR (2023)"},{"key":"6_CR18","unstructured":"Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., Yao, S.: Reflexion: Language agents with verbal reinforcement learning. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"issue":"7972","key":"6_CR19","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K., et al.: Large language models encode clinical knowledge. Nature 620(7972), 172\u2013180 (2023)","journal-title":"Nature"},{"key":"6_CR20","unstructured":"Singhal, K., et\u00a0al.: Toward expert-level medical question answering with large language models. Nat. Med. pp.\u00a01\u20138 (2025)"},{"key":"6_CR21","unstructured":"Wang, P., et\u00a0al.: Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution (2024). arXiv preprint arXiv:2409.12191"},{"key":"6_CR22","unstructured":"Xiong, T., .: Llava-critic: Learning to evaluate multimodal models (2024). arXiv preprint arXiv:2410.02712"},{"key":"6_CR23","unstructured":"Zhang, Y., et al.: Llava-next: A strong zero-shot video understanding model (2024). https:\/\/llava-vl.github.io\/blog\/2024-04-30-llava-next-video\/"},{"key":"6_CR24","unstructured":"Zhang, Y., et al.: Video instruction tuning with synthetic data (2024). arXiv preprint arXiv:2410.02713"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: Chatcad+: Towards a universal and reliable interactive cad using llms. IEEE Trans. Med. Imaging (2024)","DOI":"10.1109\/TMI.2024.3398350"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04971-1_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T06:46:18Z","timestamp":1771742778000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04971-1_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032049704","9783032049711"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04971-1_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,20]]},"assertion":[{"value":"20 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}