{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:51:56Z","timestamp":1781589116926,"version":"3.54.5"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2024"],"award-info":[{"award-number":["U21B2024"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62425307"],"award-info":[{"award-number":["62425307"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472303"],"award-info":[{"award-number":["62472303"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402334"],"award-info":[{"award-number":["62402334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3654463","type":"journal-article","created":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:50:42Z","timestamp":1768510242000},"page":"4460-4474","source":"Crossref","is-referenced-by-count":0,"title":["MMToT: Multi-Modal Token-of-Thought Reasoning for Large Models"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7526-4356","authenticated-orcid":false,"given":"Ning","family":"Xu","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8479-2807","authenticated-orcid":false,"given":"Zimu","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7635-0961","authenticated-orcid":false,"given":"Hongshuo","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8788-1725","authenticated-orcid":false,"given":"Bolun","family":"Zheng","sequence":"additional","affiliation":[{"name":"Institute of Information and Control, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5037-6989","authenticated-orcid":false,"given":"Jinbo","family":"Cao","sequence":"additional","affiliation":[{"name":"30th Research Institute of China Electronics Technology Corporation, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5755-9145","authenticated-orcid":false,"given":"An-An","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref4","article-title":"Llemma: An open language model for mathematics","author":"Azerbayev","year":"2024","journal-title":"Int. Conf. Learn. Representations"},{"key":"ref5","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","volume":"33","author":"Brown","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref8","article-title":"Shikra: Unleashing multimodal LLMs referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27888"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3345172"},{"key":"ref11","first-page":"11324","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref14","article-title":"Learning confidence for out-of-distribution detection in neural networks","author":"DeVries","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00503"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00503"},{"key":"ref17","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Driess","year":"2023"},{"key":"ref18","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3172588"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"ref22","article-title":"Measuring mathematical problem solving with the MATH dataset","volume-title":"Proc. NeurIPS","author":"Hendrycks","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.830"},{"key":"ref24","first-page":"72096","article-title":"Language is not all you need: Aligning perception with language models","volume-title":"Proc. NeurIPS","volume":"36","author":"Huang","year":"2023"},{"key":"ref25","article-title":"MANTIS: Interleaved multi-image instruction tuning","author":"Jiang","year":"2024","journal-title":"TMLR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref27","article-title":"Pythia v0. 1: The winning entry to the VQA challenge 2018","author":"Jiang","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3295098"},{"key":"ref29","article-title":"Bilinear attention networks","volume-title":"Proc. NeurIPS","volume":"31","author":"Kim","year":"2018"},{"key":"ref30","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref32","first-page":"87874","article-title":"What matters when building vision-language models?","volume-title":"Proc. NeurIPS","volume":"37","author":"Laurenon","year":"2024"},{"key":"ref33","article-title":"Solving quantitative reasoning problems with language models","volume-title":"Proc. NeurIPS","author":"Lewkowycz","year":"2022"},{"key":"ref34","article-title":"Common 7b language models already possess strong math capabilities","author":"Li","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127052"},{"key":"ref36","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML PMLR","author":"Li","year":"2023"},{"key":"ref37","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3322329"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref41","first-page":"10560","article-title":"Revive: Regional visual representation matters in knowledge-based visual question answering","volume-title":"Proc. NeurIPS","volume":"35","author":"Lin","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref44","first-page":"38","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Liu","year":"2024"},{"key":"ref45","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. NeurIPS","volume":"35","author":"Lu","year":"2022"},{"key":"ref46","first-page":"43447","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","volume-title":"Proc. NeurIPS","volume":"36","author":"Lu","year":"2023"},{"key":"ref47","article-title":"Iconqa: A new benchmark for abstract diagram understanding and visual language reasoning","volume-title":"Proc. NeurIPS","author":"Lu","year":"2021"},{"key":"ref48","article-title":"Feast your eyes: Mixture-of-resolution adaptation for multimodal large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Luo","year":"2025"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.20"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_18"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3230979"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3323878"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00181"},{"key":"ref55","article-title":"Code llama: Open foundation models for code","author":"Rozire","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01002"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3369863"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00209"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3380259"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32855"},{"key":"ref63","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref66","article-title":"Internlm-math: Open math large language models toward verifiable reasoning","author":"Ying","year":"2024"},{"key":"ref67","article-title":"Metamath: Bootstrap your own mathematical questions for large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2024"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref69","article-title":"Mammoth: Building math generalist models through hybrid instruction tuning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yue","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3336371"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02013-x"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02077"},{"key":"ref73","article-title":"Multimodal chain-of-thought reasoning in language models","author":"Zhang","year":"2024","journal-title":"TMLR"},{"key":"ref74","first-page":"5168","article-title":"DDCOT: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models","volume-title":"Proc. NeurIPS","volume":"36","author":"Zheng","year":"2023"},{"key":"ref75","article-title":"Least-to-most prompting enables complex reasoning in large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2023"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00208"},{"key":"ref77","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2024"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11353924.pdf?arnumber=11353924","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:58:30Z","timestamp":1781585910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11353924\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3654463","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}