{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:04:00Z","timestamp":1791911040832,"version":"4.3.4"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372802","type":"print"},{"value":"9783032372819","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-37281-9_9","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:50:20Z","timestamp":1789123820000},"page":"152-172","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GenRecal: Generation After Recalibration from Large to Small Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Byung-Kwan","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryo","family":"Hachiuma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Chiang Frank","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueh-Hua","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"9_CR1","unstructured":"Abdin, M., et al.: Phi-3 technical report: a highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219 (2024)"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 35, pp. 23716\u201323736 (2022)","DOI":"10.52202\/068431-1723"},{"key":"9_CR3","unstructured":"Anthropic: The claude 3 model family: Opus, sonnet, haiku. https:\/\/www.anthropic.com (2024). https:\/\/www-cdn.anthropic.com\/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627\/Model_Card_Claude_3.pdf"},{"key":"9_CR4","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization (2016). https:\/\/arxiv.org\/abs\/1607.06450"},{"key":"9_CR5","unstructured":"Bai, S., et al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"9_CR6","unstructured":"Boizard, N., Haddad, K.E., Hudelot, C., Colombo, P.: Towards cross-tokenizer distillation: the universal logit distillation loss for LLMs. Trans. Mach. Learn. Res. (2025). https:\/\/openreview.net\/forum?id=bwRxXiGO9A"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Cai, Y., et al.: LLaVA-KD: a framework of distilling multimodal large language models. arXiv preprint arXiv:2410.16236 (2024)","DOI":"10.1109\/ICCV51701.2025.00030"},{"key":"9_CR8","unstructured":"Cai, Z., et\u00a0al.: InternLM2 technical report. arXiv preprint arXiv:2403.17297 (2024)"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Cao, J., et al.: Move-KD: knowledge distillation for VLMs with mixture of visual encoders. arXiv preprint arXiv:2501.01709 (2025)","DOI":"10.1109\/CVPR52734.2025.01848"},{"key":"9_CR10","unstructured":"Chen, L., et\u00a0al.: Are we on the right way for evaluating large vision-language models? arXiv preprint arXiv:2403.20330 (2024)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Can pre-trained vision and language models answer visual information-seeking questions? arXiv preprint arXiv:2302.11713 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"9_CR12","unstructured":"Chen, Z., et al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: How far are we to GPT-4v? Closing the gap to commercial multimodal models with open-source suites. arXiv preprint arXiv:2404.16821 (2024)","DOI":"10.1007\/s11432-024-4231-5"},{"key":"9_CR14","unstructured":"Chen, Z., et\u00a0al.: InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. arXiv preprint arXiv:2312.14238 (2023)"},{"key":"9_CR15","unstructured":"Conneau, A., Lample, G., Ranzato, M., Denoyer, L., J\u00e9gou, H.: Word translation without parallel data. arXiv preprint arXiv:1710.04087 (2017)"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Cui, X., Zhu, M., Qin, Y., Xie, L., Zhou, W., Li, H.: Multi-level optimal transport for universal cross-tokenizer knowledge distillation on language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 23724\u201323732 (2025)","DOI":"10.1609\/aaai.v39i22.34543"},{"key":"9_CR17","unstructured":"Dai, W., et al.: NVLM: open frontier-class multimodal LLMs. arXiv preprint (2024)"},{"key":"9_CR18","unstructured":"Deitke, M., et al.: Molmo and PixMo: open weights and open data for state-of-the-art multimodal models. arXiv preprint arXiv:2409.17146 (2024)"},{"key":"9_CR19","unstructured":"Dubey, A., et al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Feng, Q., Li, W., Lin, T., Chen, X.: Align-KD: distilling cross-modal alignment knowledge for mobile vision-language model. arXiv preprint arXiv:2412.01282 (2024)","DOI":"10.1109\/CVPR52734.2025.00395"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Fu, X., et al.: Blink: multimodal large language models can see but not perceive. arXiv preprint arXiv:2404.12390 (2024)","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"9_CR22","unstructured":"Gu, S., et\u00a0al.: Infinity-MM: scaling multimodal performance with large-scale and high-quality instruction data. arXiv preprint arXiv:2410.18558 (2024)"},{"key":"9_CR23","unstructured":"Gu, Y., Dong, L., Wei, F., Huang, M.: MiniLLM: knowledge distillation of large language models. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"9_CR24","unstructured":"Hong, W., et\u00a0al.: CogVLM2: visual language models for image and video understanding. arXiv preprint arXiv:2408.16500 (2024)"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Hu, A., et al.: mPLUG-DocOwl 1.5: unified structure learning for OCR-free document understanding. arXiv preprint arXiv:2403.12895 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"key":"9_CR26","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"9_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/978-3-319-46493-0_15","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Kembhavi","year":"2016","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 235\u2013251. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_15"},{"key":"9_CR28","unstructured":"Ko, J., Kim, S., Chen, T., Yun, S.Y.: DistiLLM: towards streamlined distillation for large language models. arXiv preprint arXiv:2402.03898 (2024)"},{"key":"9_CR29","unstructured":"Li, B., et al.: LLaVA-OneVision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Li, B., Ge, Y., Chen, Y., Ge, Y., Zhang, R., Shan, Y.: Seed-bench-2-plus: benchmarking multimodal large language models with text-rich visual comprehension. arXiv preprint arXiv:2404.16790 (2024)","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"9_CR31","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":"9_CR32","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0162, pp. 12888\u201312900. PMLR (2022)"},{"key":"9_CR33","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, F., Diao, H., Wang, Y., Wang, X., Duan, L.Y.: DenseFusion-1M: merging vision experts for comprehensive multimodal perception. arXiv preprint arXiv:2407.08303 (2024)","DOI":"10.52202\/079017-0588"},{"key":"9_CR34","unstructured":"Lin, J., et al.: Vila: on pre-training for visual language models. arXiv preprint arXiv:2312.07533 (2023)"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"9_CR36","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":"9_CR37","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"9_CR38","unstructured":"Lu, P., et al.: MathVista: evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255 (2023)"},{"key":"9_CR39","unstructured":"Lu, S., et al.: Ovis: structural embedding alignment for multimodal large language model. arXiv:2405.20797 (2024)"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S., Hoque, E.: ChartQA: a benchmark for question answering about charts with visual and logical reasoning. arXiv preprint arXiv:2203.10244 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"9_CR41","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"9_CR42","unstructured":"Mikolov, T., Le, Q.V., Sutskever, I.: Exploiting similarities among languages for machine translation. arXiv preprint arXiv:1309.4168 (2013)"},{"key":"9_CR43","unstructured":"OpenAI: GPT-4v(ision) system card (2023). https:\/\/openai.com\/research\/gpt-4v-system-card. Accessed 13 Feb 2024"},{"key":"9_CR44","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv e-prints (2019)"},{"key":"9_CR45","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: Zero: memory optimizations toward training trillion parameter models. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201316. IEEE (2020)","DOI":"10.1109\/SC41405.2020.00024"},{"key":"9_CR46","unstructured":"Riquelme, C., et al.: Scaling vision with sparse mixture of experts. In: Advances in Neural Information Processing Systems, vol. 34, pp. 8583\u20138595 (2021)"},{"key":"9_CR47","unstructured":"Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q., Hinton, G., Dean, J.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. In: International Conference on Learning Representations (2017). https:\/\/openreview.net\/forum?id=B1ckMDqlg"},{"key":"9_CR48","unstructured":"Shi, M., et al.: Eagle: exploring the design space for multimodal LLMs with mixture of encoders. arXiv preprint arXiv:2408.15998 (2024)"},{"key":"9_CR49","unstructured":"Shu, F., et al.: LLaVA-MoD: making LLaVA tiny via MoE knowledge distillation. arXiv preprint arXiv:2408.15881 (2024)"},{"key":"9_CR50","unstructured":"Smith, S.L., Turban, D.H., Hamblin, S., Hammerla, N.Y.: Offline bilingual word vectors, orthogonal transformations and the inverted softmax. arXiv preprint arXiv:1702.03859 (2017)"},{"key":"9_CR51","doi-asserted-by":"publisher","unstructured":"Soldaini, L., et al.: Dolma: an open corpus of three trillion tokens for language model pretraining research. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 15725\u201315788. Association for Computational Linguistics, Bangkok, Thailand (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.840, https:\/\/aclanthology.org\/2024.acl-long.840\/","DOI":"10.18653\/v1\/2024.acl-long.840"},{"key":"9_CR52","unstructured":"Sreenivas, S.T., et al.: X-token: projection-guided cross-tokenizer knowledge distillation. arXiv preprint arXiv:2605.21699 (2026)"},{"key":"9_CR53","doi-asserted-by":"publisher","first-page":"127063","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"9_CR54","unstructured":"Sujet\u00a0AI, Allaa\u00a0Boutaleb, H.R.: Sujet-finance-QA-vision-100k: a large-scale dataset for financial document VQA (2024). https:\/\/huggingface.co\/datasets\/sujet-ai\/Sujet-Finance-QA-Vision-100k"},{"key":"9_CR55","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"9_CR56","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"9_CR57","doi-asserted-by":"crossref","unstructured":"Tong, S., et al.: Cambrian-1: a fully open, vision-centric exploration of multimodal LLMs. arXiv preprint arXiv:2406.16860 (2024)","DOI":"10.52202\/079017-2771"},{"key":"9_CR58","unstructured":"Wang, P., et al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv:2409.12191 (2024)"},{"key":"9_CR59","unstructured":"Wang, W., et al.: Enhancing the reasoning ability of multimodal large language models via mixed preference optimization. arXiv preprint arXiv:2411.10442 (2024)"},{"key":"9_CR60","unstructured":"Wang, W., et al.: InternVL3. 5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"9_CR61","unstructured":"Yang, A., et al.: Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)"},{"key":"9_CR62","unstructured":"Yao, Y., et al.: MiniCPM-V: a GPT-4V level MLLM on your phone. arXiv preprint arXiv:2408.01800 (2024)"},{"key":"9_CR63","unstructured":"Yu, W., et al.: MM-Vet: evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490 (2023)"},{"key":"9_CR64","unstructured":"Yu, W., et al.: MM-Vet V2: a challenging benchmark to evaluate large multimodal models for integrated capabilities. arXiv preprint arXiv:2408.00765 (2024)"},{"key":"9_CR65","doi-asserted-by":"crossref","unstructured":"Yue, X., et al.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. arXiv preprint arXiv:2311.16502 (2023)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"9_CR66","unstructured":"Yue, X., et al.: MMMU-Pro: a more robust multi-discipline multimodal understanding benchmark. arXiv preprint arXiv:2409.02813 (2024)"},{"key":"9_CR67","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, X., Hu, B., Shi, H., Zhang, M.: Cognitive visual-language mapper: advancing multimodal comprehension with enhanced visual knowledge alignment. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (2024)","DOI":"10.18653\/v1\/2024.acl-long.411"},{"key":"9_CR68","unstructured":"Zhang, Y.F., et al.: Beyond LLaVA-HD: diving into high-resolution large multimodal models. arXiv preprint arXiv:2406.08487 (2024)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37281-9_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:50:36Z","timestamp":1789123836000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37281-9_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372802","9783032372819"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37281-9_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"12 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}