{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:00:46Z","timestamp":1776888046115,"version":"3.51.2"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031736605","type":"print"},{"value":"9783031736612","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73661-2_17","type":"book-chapter","created":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T11:09:54Z","timestamp":1731150594000},"page":"305-322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Boosting the\u00a0Power of\u00a0Small Multimodal Reasoning Models to\u00a0Match Larger Models with\u00a0Self-consistency Training"],"prefix":"10.1007","author":[{"given":"Cheng","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingxuan","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhangyang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linzhuang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruifeng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bihui","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2961-8096","authenticated-orcid":false,"given":"Stan Z.","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,10]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"17_CR2","unstructured":"Anil, R., et\u00a0al.: Palm 2 technical report. arXiv preprint arXiv:2305.10403 (2023)"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"17_CR4","unstructured":"Askell, A., et\u00a0al.: A general language assistant as a laboratory for alignment. arXiv preprint arXiv:2112.00861 (2021)"},{"key":"17_CR5","unstructured":"Bai, J., et al.: Qwen-vl: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"17_CR6","unstructured":"Besta, M., et\u00a0al.: Graph of thoughts: solving elaborate problems with large language models. arXiv preprint arXiv:2308.09687 (2023)"},{"key":"17_CR7","unstructured":"Biderman, S., et\u00a0al.: Pythia: a suite for analyzing large language models across training and scaling. In: International Conference on Machine Learning, pp. 2397\u20132430. PMLR (2023)"},{"key":"17_CR8","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advance in Neural Information Processing System, vol. 33, pp. 1877\u20131901 (2020)"},{"key":"17_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"17_CR10","unstructured":"Chen, Z., Zhou, Q., Shen, Y., Hong, Y., Zhang, H., Gan, C.: See, think, confirm: interactive prompting between vision and language models for knowledge-based visual reasoning. arXiv preprint arXiv:2301.05226 (2023)"},{"key":"17_CR11","unstructured":"Chowdhery, A., et\u00a0al.: Palm: scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022)"},{"key":"17_CR12","unstructured":"Chung, H.W., et\u00a0al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)"},{"key":"17_CR13","unstructured":"Fu, C., et\u00a0al.: MME: a comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394 (2023)"},{"key":"17_CR14","unstructured":"Gao, P., et\u00a0al.: Llama-adapter v2: parameter-efficient visual instruction model. arXiv preprint arXiv:2304.15010 (2023)"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Gao, P., et al.: Dynamic fusion with intra-and inter-modality attention flow for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6639\u20136648 (2019)","DOI":"10.1109\/CVPR.2019.00680"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Horawalavithana, S., Munikoti, S., Stewart, I., Kvinge, H.: Scitune: aligning large language models with scientific multimodal instructions. arXiv preprint arXiv:2307.01139 (2023)","DOI":"10.18653\/v1\/2024.nlp4science-1.7"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Huang, J., Chang, K.C.C.: Towards reasoning in large language models: a survey. arXiv preprint arXiv:2212.10403 (2022)","DOI":"10.18653\/v1\/2023.findings-acl.67"},{"key":"17_CR19","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1007\/978-3-031-20059-5_38","volume-title":"ECCV 2022","author":"A Kamath","year":"2022","unstructured":"Kamath, A., Clark, C., Gupta, T., Kolve, E., Hoiem, D., Kembhavi, A.: Webly supervised concept expansion for general purpose vision models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13696, pp. 662\u2013681. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_38"},{"key":"17_CR20","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of naacL-HLT, vol.\u00a01, p.\u00a02 (2019)"},{"key":"17_CR21","doi-asserted-by":"publisher","unstructured":"Khashabi, D., et al.: UNIFIEDQA: crossing format boundaries with a single QA system. In: Cohn, T., He, Y., Liu, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 1896\u20131907. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.171, https:\/\/aclanthology.org\/2020.findings-emnlp.171","DOI":"10.18653\/v1\/2020.findings-emnlp.171"},{"key":"17_CR22","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"17_CR23","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594. PMLR (2021)"},{"key":"17_CR24","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: What does Bert with vision look at? In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 5265\u20135275 (2020)","DOI":"10.18653\/v1\/2020.acl-main.469"},{"key":"17_CR26","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: Mmbench: is your multi-modal model an all-around player? arXiv preprint arXiv:2307.06281 (2023)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"17_CR28","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"17_CR29","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. In: Advances in Neural Information Processing Systems, vol. 35, pp. 2507\u20132521 (2022)"},{"key":"17_CR30","unstructured":"Lu, P., et al.: Chameleon: plug-and-play compositional reasoning with large language models. arXiv preprint arXiv:2304.09842 (2023)"},{"key":"17_CR31","unstructured":"Lu, P., et al.: IconQA: a new benchmark for abstract diagram understanding and visual language reasoning. arXiv preprint arXiv:2110.13214 (2021)"},{"key":"17_CR32","unstructured":"Luo, G., Zhou, Y., Ren, T., Chen, S., Sun, X., Ji, R.: Cheap and quick: efficient vision-language instruction tuning for large language models. arXiv preprint arXiv:2305.15023 (2023)"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Marino, K., Chen, X., Parikh, D., Gupta, A., Rohrbach, M.: KRISP: integrating implicit and symbolic knowledge for open-domain knowledge-based VQA. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14111\u201314121 (2021)","DOI":"10.1109\/CVPR46437.2021.01389"},{"key":"17_CR34","unstructured":"Ning, X., Lin, Z., Zhou, Z., Yang, H., Wang, Y.: Skeleton-of-thought: large language models can do parallel decoding. arXiv preprint arXiv:2307.15337 (2023)"},{"key":"17_CR35","unstructured":"OpenAI: Gpt-4 technical report (2023)"},{"key":"17_CR36","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: Advance in Neural Information Processing System, vol. 35, pp. 27730\u201327744 (2022)"},{"key":"17_CR37","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"1","key":"17_CR38","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"17_CR39","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., Liu, P.J.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"17_CR40","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"17_CR41","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1007\/978-3-031-20074-8_9","volume-title":"ECCV 2022","author":"D Schwenk","year":"2022","unstructured":"Schwenk, D., Khandelwal, A., Clark, C., Marino, K., Mottaghi, R.: A-OKVQA: a benchmark for visual question answering using world knowledge. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13668, pp. 146\u2013162. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20074-8_9"},{"key":"17_CR42","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: Lxmert: learning cross-modality encoder representations from transformers. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"17_CR43","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"17_CR44","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"17_CR45","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"17_CR46","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"17_CR47","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advance in Neural Information Processing System, vol. 35, pp. 24824\u201324837 (2022)"},{"key":"17_CR48","unstructured":"Wu, C., Liu, J., Wang, X., Dong, X.: Chain of reasoning for visual question answering. In: Advances in Neural Information Processing Systems 31 (2018)"},{"key":"17_CR49","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":"17_CR50","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: An empirical study of GPT-3 for few-shot knowledge-based VQA. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 3081\u20133089 (2022)","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"17_CR51","unstructured":"Yang, Z., et al.: Mm-react: prompting chatgpt for multimodal reasoning and action. arXiv preprint arXiv:2303.11381 (2023)"},{"key":"17_CR52","unstructured":"Yao, S., et al.: Tree of thoughts: deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601 (2023)"},{"key":"17_CR53","unstructured":"Yin, S., et al.: A survey on multimodal large language models. arXiv preprint arXiv:2306.13549 (2023)"},{"key":"17_CR54","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., Tao, D., Tian, Q.: Deep modular co-attention networks for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6281\u20136290 (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"17_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: VinVL: revisiting visual representations in vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5579\u20135588 (2021)","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"17_CR56","unstructured":"Zhang, R., et al.: Llama-adapter: efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199 (2023)"},{"key":"17_CR57","unstructured":"Zhang, S., et\u00a0al.: OPT: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"17_CR58","unstructured":"Zhang, Z., Zhang, A., Li, M., Zhao, H., Karypis, G., Smola, A.: Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73661-2_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T02:20:38Z","timestamp":1733019638000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73661-2_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,10]]},"ISBN":["9783031736605","9783031736612"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73661-2_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,10]]},"assertion":[{"value":"10 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}