{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T14:18:50Z","timestamp":1788445130133,"version":"build-2803163510"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T00:00:00Z","timestamp":1785974400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2026AFB700"],"award-info":[{"award-number":["2026AFB700"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["XJ2026000901"],"award-info":[{"award-number":["XJ2026000901"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005234","name":"Central China Normal University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005234","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M781597"],"award-info":[{"award-number":["2025M781597"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114570","type":"journal-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T16:21:49Z","timestamp":1786033309000},"page":"114570","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PF","title":["Boosting Multimodal Chain of Thought Reasoning by Selective Mixture of Experts"],"prefix":"10.1016","volume":"180","author":[{"given":"Qilei","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shitong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Da","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timothy","family":"Hospedales","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaogang","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114570_b1","series-title":"Proc. of NeurIPS","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"10.1016\/j.patcog.2026.114570_b2","series-title":"Proc. of NeurIPS","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022"},{"key":"10.1016\/j.patcog.2026.114570_b3","series-title":"Proc. of NeurIPS","article-title":"Large language models are zero-shot reasoners","author":"Kojima","year":"2022"},{"key":"10.1016\/j.patcog.2026.114570_b4","series-title":"Proc. of NeurIPS","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","author":"Lu","year":"2022"},{"key":"10.1016\/j.patcog.2026.114570_b5","series-title":"Proc. of ECCV","article-title":"A-OKVQA: A benchmark for visual question answering using world knowledge","author":"Schwenk","year":"2022"},{"key":"10.1016\/j.patcog.2026.114570_b6","article-title":"Multimodal chain-of-thought reasoning in language models","author":"Zhang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.114570_b7","series-title":"Proc. of NeruIPS","article-title":"DDCOT: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models","author":"Zheng","year":"2024"},{"key":"10.1016\/j.patcog.2026.114570_b8","series-title":"Proc. of AAAI","article-title":"KAM-COT: Knowledge augmented multimodal chain-of-thoughts reasoning","author":"Mondal","year":"2024"},{"key":"10.1016\/j.patcog.2026.114570_b9","series-title":"Proc. of AAAI","article-title":"T-SciQ: Teaching multimodal chain-of-thought reasoning via large language model signals for science question answering","author":"Wang","year":"2024"},{"key":"10.1016\/j.patcog.2026.114570_b10","series-title":"Proc. of AAAI","article-title":"Multi-modal latent space learning for chain-of-thought reasoning in language models","author":"He","year":"2024"},{"key":"10.1016\/j.patcog.2026.114570_b11","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3034","article-title":"Corvid: Improving multimodal large language models towards chain-of-thought reasoning","author":"Jiang","year":"2025"},{"key":"10.1016\/j.patcog.2026.114570_b12","series-title":"2025 International Joint Conference on Neural Networks","first-page":"1","article-title":"Retrieval-augmented multi-modal chain-of-thoughts reasoning for large language models","author":"Liu","year":"2025"},{"key":"10.1016\/j.patcog.2026.114570_b13","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"17371","article-title":"Medcot: Medical chain of thought via hierarchical expert","author":"Liu","year":"2024"},{"key":"10.1016\/j.patcog.2026.114570_b14","unstructured":"Q. Wu, Z. Ke, Y. Zhou, X. Sun, R. Ji, Routing experts: Learning to route dynamic experts in existing multi-modal large language models, in: The Thirteenth International Conference on Learning Representations, 2025."},{"key":"10.1016\/j.patcog.2026.114570_b15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3571730","article-title":"Survey of hallucination in natural language generation","volume":"55","author":"Ji","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.patcog.2026.114570_b16","series-title":"Proc. of NeurIPS","article-title":"Object-centric learning with slot attention","author":"Locatello","year":"2020"},{"key":"10.1016\/j.patcog.2026.114570_b17","series-title":"Proc. of ICLR","article-title":"Decomposed prompting: A modular approach for solving complex tasks","author":"Khot","year":"2023"},{"key":"10.1016\/j.patcog.2026.114570_b18","series-title":"Proc. of EMNLP","article-title":"UnifiedQA: Crossing format boundaries with a single QA system","author":"Khashabi","year":"2020"},{"key":"10.1016\/j.patcog.2026.114570_b19","series-title":"Proc. of ICML","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.114570_b20","series-title":"Proc. of NeurIPS","article-title":"Visual instruction tuning","author":"Liu","year":"2024"},{"key":"10.1016\/j.patcog.2026.114570_b21","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.1109\/TNNLS.2012.2200299","article-title":"Twenty years of mixture of experts","volume":"23","author":"Yuksel","year":"2012","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.114570_b22","series-title":"Proc. of EMNLP","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"10.1016\/j.patcog.2026.114570_b23","series-title":"Proc. of ICLR","article-title":"Neural machine translation with universal visual representation","author":"Zhang","year":"2019"},{"key":"10.1016\/j.patcog.2026.114570_b24","series-title":"Proc. of NeurIPS","article-title":"IconQA: A new benchmark for abstract diagram understanding and visual language reasoning","author":"Lu","year":"2021"},{"key":"10.1016\/j.patcog.2026.114570_b25","series-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"10.1016\/j.patcog.2026.114570_b26","series-title":"Proc. of LCML","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021"},{"key":"10.1016\/j.patcog.2026.114570_b27","series-title":"Proc. of ICLR","article-title":"LLaMA-Adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2024"},{"key":"10.1016\/j.patcog.2026.114570_b28","series-title":"Proc. of NeruIPS","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"10.1016\/j.patcog.2026.114570_b29","series-title":"Proc. of NeurIPS","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","author":"Lu","year":"2024"},{"key":"10.1016\/j.patcog.2026.114570_b30","series-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"10.1016\/j.patcog.2026.114570_b31","series-title":"Proc. of NeurIPS","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019"},{"key":"10.1016\/j.patcog.2026.114570_b32","first-page":"7","article-title":"Alpaca: A strong, replicable instruction-following model","volume":"3","author":"Taori","year":"2023","journal-title":"Stanf. Cent. Res. Found. Model."},{"key":"10.1016\/j.patcog.2026.114570_b33","series-title":"OPT: Open pre-trained transformer language models, 2022","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114570_b34","series-title":"ICLR","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.patcog.2026.114570_b35","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2020","journal-title":"J. Mach. Learn. Res."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326015347?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326015347?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T13:59:35Z","timestamp":1788443975000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326015347"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":35,"alternative-id":["S0031320326015347"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114570","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Boosting Multimodal Chain of Thought Reasoning by Selective Mixture of Experts","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114570","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"114570"}}