{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:38:00Z","timestamp":1776883080184,"version":"3.51.2"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730030","type":"print"},{"value":"9783031730047","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73004-7_26","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:07:25Z","timestamp":1730394445000},"page":"446-462","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Instruction Tuning-Free Visual Token Complement for\u00a0Multimodal LLMs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3380-5337","authenticated-orcid":false,"given":"Dongsheng","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-7851","authenticated-orcid":false,"given":"Jiequan","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9531-3254","authenticated-orcid":false,"given":"Miaoge","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8353-2392","authenticated-orcid":false,"given":"Wang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5151-9388","authenticated-orcid":false,"given":"Bo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7374-8739","authenticated-orcid":false,"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"26_CR1","unstructured":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality (March 2023)"},{"key":"26_CR2","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"26_CR3","unstructured":"Anil, R., et\u00a0al.: Palm 2 technical report. arXiv preprint arXiv:2305.10403 (2023)"},{"key":"26_CR4","unstructured":"Awadalla, A., et\u00a0al.: Openflamingo: an open-source framework for training large autoregressive vision-language models. arXiv preprint arXiv:2308.01390 (2023)"},{"key":"26_CR5","unstructured":"Chen, X., et\u00a0al.: Pali: a jointly-scaled multilingual language-image model. arXiv preprint arXiv:2209.06794 (2022)"},{"key":"26_CR6","unstructured":"Dai, W., et\u00a0al.: Instructblip: towards general-purpose vision-language models with instruction tuning. CoRR abs\/2305.06500 (2023)"},{"key":"26_CR7","unstructured":"Driess, D., et\u00a0al.: Palm-e: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"key":"26_CR8","unstructured":"Fu, C., ., et\u00a0al.: Mme: a comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394 (2023)"},{"key":"26_CR9","unstructured":"Gao, P., et\u00a0al.: Llama-adapter v2: parameter-efficient visual instruction model. arXiv preprint arXiv:2304.15010 (2023)"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"26_CR11","unstructured":"Hu, E.J., et\u00a0al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Huiskes, M.J., Lew, M.S.: The MIR flickr retrieval evaluation. In: Proceedings of the 1st ACM International Conference on Multimedia Information Retrieval, pp. 39\u201343 (2008)","DOI":"10.1145\/1460096.1460104"},{"key":"26_CR13","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":"26_CR14","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., et al.: Text2video-zero: text-to-image diffusion models are zero-shot video generators. arXiv preprint arXiv:2303.13439 (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"26_CR15","unstructured":"Li, B., et al.: Mimic-it: multi-modal in-context instruction tuning (2023)"},{"key":"26_CR16","unstructured":"Li, B., Zhang, Y., Chen, L., Wang, J., Yang, J., Liu, Z.: Otter: a multi-modal model with in-context instruction tuning. arXiv preprint arXiv:2305.03726 (2023)"},{"key":"26_CR17","unstructured":"Li, J., et al.: Fine-tuning multimodal llms to follow zero-shot demonstrative instructions. arXiv preprint arXiv:2308.04152 (2023)"},{"key":"26_CR18","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.C.H.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, ICML 2023, 23\u201329 July 2023, Honolulu, Hawaii, USA, vol.\u00a0202, pp. 19730\u201319742. PMLR (2023)"},{"key":"26_CR19","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)"},{"key":"26_CR20","unstructured":"OpenAI: GPT-4 technical report. CoRR abs\/2303.08774 (2023)"},{"key":"26_CR21","unstructured":"OpenAI: GPT-4V(ision) system card (2023)"},{"key":"26_CR22","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback 2022, 13 (2022)"},{"key":"26_CR23","unstructured":"Paischer, F., Adler, T., Hofmarcher, M., Hochreiter, S.: Sitta: a semantic image-text alignment for image captioning. arXiv preprint arXiv:2307.05591 (2023)"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"26_CR25","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural Inf. Process. Syst. 35, 36479\u201336494 (2022)"},{"issue":"1","key":"26_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/BF02289451","volume":"31","author":"PH Sch\u00f6nemann","year":"1966","unstructured":"Sch\u00f6nemann, P.H.: A generalized solution of the orthogonal procrustes problem. Psychometrika 31(1), 1\u201310 (1966)","journal-title":"Psychometrika"},{"key":"26_CR27","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"26_CR28","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: International Conference on Learning Representations (2021)"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Sur\u00eds, D., Menon, S., Vondrick, C.: Vipergpt: visual inference via python execution for reasoning. arXiv preprint arXiv:2303.08128 (2023)","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"26_CR30","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"26_CR31","first-page":"200","volume":"34","author":"M Tsimpoukelli","year":"2021","unstructured":"Tsimpoukelli, M., Menick, J.L., Cabi, S., Eslami, S., Vinyals, O., Hill, F.: Multimodal few-shot learning with frozen language models. Adv. Neural Inf. Process. Syst. 34, 200\u2013212 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"26_CR32","unstructured":"Wang, J., et al.: Git: a generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100 (2022)"},{"key":"26_CR33","unstructured":"Wang, Z., Yu, J., Yu, A.W., Dai, Z., Tsvetkov, Y., Cao, Y.: Simvlm: simple visual language model pretraining with weak supervision. arXiv preprint arXiv:2108.10904 (2021)"},{"key":"26_CR34","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)"},{"key":"26_CR35","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural Inf. Process. Syst. 35, 24824\u201324837 (2022)"},{"key":"26_CR36","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":"26_CR37","doi-asserted-by":"crossref","unstructured":"Xu, P., et al.: LVLM-eHub: a comprehensive evaluation benchmark for large vision-language models. arXiv preprint arXiv:2306.09265 (2023)","DOI":"10.1109\/TPAMI.2024.3507000"},{"key":"26_CR38","unstructured":"Ye, Q., et\u00a0al.: Mplug-owl: modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)"},{"key":"26_CR39","unstructured":"Yin, S., et al.: A survey on multimodal large language models. arXiv preprint arXiv:2306.13549 (2023)"},{"key":"26_CR40","unstructured":"Zhang, A., et al.: Transfer visual prompt generator across llms. arXiv preprint arXiv:2305.01278 (2023)"},{"key":"26_CR41","unstructured":"Zhang, C., Zhang, C., Zhang, M., Kweon, I.S.: Text-to-image diffusion model in generative AI: a survey. arXiv preprint arXiv:2303.07909 (2023)"},{"key":"26_CR42","unstructured":"Zhang, S., et\u00a0al.: Instruction tuning for large language models: a survey. arXiv preprint arXiv:2308.10792 (2023)"},{"key":"26_CR43","unstructured":"Zhang, S., et\u00a0al.: OPT: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"26_CR44","unstructured":"Zhao, H., et al.: Mmicl: empowering vision-language model with multi-modal in-context learning. arXiv preprint arXiv:2309.07915 (2023)"},{"key":"26_CR45","unstructured":"Zhao, X., Liu, B., Liu, Q., Shi, G., Wu, X.M.: Making multimodal generation easier: when diffusion models meet llms. arXiv preprint arXiv:2310.08949 (2023)"},{"key":"26_CR46","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (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\/978-3-031-73004-7_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T16:17:14Z","timestamp":1732983434000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73004-7_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031730030","9783031730047"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73004-7_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}