{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:06:24Z","timestamp":1788937584813,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373588","type":"print"},{"value":"9783032373595","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\/978-3-032-37359-5_12","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:11:12Z","timestamp":1788934272000},"page":"205-222","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Look Less, Think Faster: Joint Token-Compute Adaptation for\u00a0Multimodal LLMs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2797-6973","authenticated-orcid":false,"given":"Pengcheng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5611-0335","authenticated-orcid":false,"given":"Zhiquan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1011-6002","authenticated-orcid":false,"given":"Jayoung","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5776-9388","authenticated-orcid":false,"given":"Zhuoyan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2913-9420","authenticated-orcid":false,"given":"Ran","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4239-5632","authenticated-orcid":false,"given":"Saurabh","family":"Bagchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4173-9453","authenticated-orcid":false,"given":"Yin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3651-6362","authenticated-orcid":false,"given":"Somali","family":"Chaterji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"12_CR1","unstructured":"Bai, J., et al.: Qwen-VL: a versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"12_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"12_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"12_CR4","doi-asserted-by":"publisher","unstructured":"Chen, L., et al.: An image is worth 1\/2 tokens after layer 2: plug-and-play inference acceleration for large vision-language models. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15139. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73004-7_2","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"12_CR5","unstructured":"Chu, X., et\u00a0al.: MobileVLM: a fast, strong and open vision language assistant for mobile devices. arXiv preprint arXiv:2312.16886 (2023)"},{"key":"12_CR6","unstructured":"Chu, X., et\u00a0al.: MobileVLM V2: faster and stronger baseline for vision language model. arXiv preprint arXiv:2402.03766 (2024)"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning. In: NeurIPS (2023)","DOI":"10.52202\/075280-2142"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Molmo and pixmo: open weights and open data for state-of-the-art vision-language models. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00018"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: QLORA: efficient finetuning of quantized LLMs. In: NeurIPS (2023)","DOI":"10.52202\/075280-0441"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the v in vqa matter: elevating the role of image understanding in visual question answering. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: Vizwiz grand challenge: answering visual questions from blind people. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"key":"12_CR12","doi-asserted-by":"publisher","unstructured":"Huang, K., Zou, H., Xi, Y., Wang, B., Xie, Z., Yu, L.: IVTP: instruction-guided visual token pruning for large vision-language models. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15075. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72643-9_13","DOI":"10.1007\/978-3-031-72643-9_13"},{"key":"12_CR13","unstructured":"Huang, Y., et al.: MoDES: accelerating mixture-of-experts multimodal large language models via dynamic expert skipping. In: CVPR (2026)"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"12_CR15","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. In: ICLR (2017)"},{"key":"12_CR16","unstructured":"Javaheripi, M., et\u00a0al.: Phi-2: the surprising power of small language models. Microsoft Research Blog (2023)"},{"key":"12_CR17","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)"},{"key":"12_CR18","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, W.X., Wen, J.R.: Evaluating object hallucination in large vision-language models. In: EMNLP (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Lin, B., et al.: MoE-LLaVA: mixture of experts for large vision-language models. IEEE Trans. Multimed. (2026)","DOI":"10.1109\/TMM.2026.3654458"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Lin, Z., Lin, M., Lin, L., Ji, R.: Boosting multimodal large language models with visual tokens withdrawal for rapid inference. In: AAAI (2025)","DOI":"10.1609\/aaai.v39i5.32567"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"12_CR23","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023). LLaVA: Large Language and Vision Assistant"},{"key":"12_CR24","doi-asserted-by":"publisher","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player? In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15064. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72658-3_13","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. In: NeurIPS (2022)","DOI":"10.52202\/068431-0182"},{"key":"12_CR26","unstructured":"Maddison, C., Mnih, A., Teh, Y.: The concrete distribution: a continuous relaxation of discrete random variables. In: ICLR (2017)"},{"key":"12_CR27","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Shang, Y., Cai, M., Xu, B., Lee, Y.J., Yan, Y.: LLaVA-PruMerge: adaptive token reduction for efficient large multimodal models. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.02122"},{"key":"12_CR29","unstructured":"Shu, F., et\u00a0al.: LLaVA-MoD: making llava tiny via moe-knowledge distillation. In: ICLR (2025)"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards vqa models that can read. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. Neurocomputing (2024)","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"12_CR32","unstructured":"Tian, X., et al.: DriveVLM: the convergence of autonomous driving and large vision-language models. In: Conference on Robot Learning (2025)"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Vasu, P.K.A., et al.: FastVLM: efficient vision encoding for vision language models. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01841"},{"key":"12_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Wang, C., Wang, Z., Xu, X., Tang, Y., Zhou, J., Lu, J.: QuantVLM: post-training quantization for efficient vision\u2013language models. In: NeurIPS (2024)","DOI":"10.52202\/079017-3638"},{"key":"12_CR36","unstructured":"Wang, P., et\u00a0al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Learning to inference adaptively for multimodal large language models. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00339"},{"key":"12_CR38","unstructured":"Yuan, Z., Li, Z., Huang, W., Ye, Y., Sun, L.: TinyGPT-V: efficient multimodal large language model via small backbones (2023). arXiv preprint arXiv:2312.16862"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-LLaMA: an instruction-tuned audio-visual language model for video understanding. EMNLP Demo Track (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"12_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: a survey. IEEE TPAMI (2024)","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, K., et\u00a0al.: LMMs-Eval: reality check on the evaluation of large multimodal models. In: Findings of the Association for Computational Linguistics: NAACL 2025 (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.51"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Liu, Z., Li, Y., Wang, L.: AIM: adaptive inference of multi-modal llms via token merging and pruning. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01877"},{"key":"12_CR43","unstructured":"Zhou, B., et al.: TinyLLaVA: a framework of small-scale large multimodal models. arXiv preprint arXiv:2402.14289 (2024)"},{"key":"12_CR44","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. In: ICLR. (2024)"},{"key":"12_CR45","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhu, M., Liu, N., Xu, Z., Peng, Y.: LLaVA-Phi: efficient multi-modal assistant with small language model. In: EMCLR (2024)","DOI":"10.1145\/3688863.3689575"}],"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\/978-3-032-37359-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:11:21Z","timestamp":1788934281000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37359-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373588","9783032373595"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37359-5_12","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":"10 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"}}]}}