{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:04:27Z","timestamp":1750219467335,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819681853","type":"print"},{"value":"9789819681860","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-8186-0_9","type":"book-chapter","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T10:15:31Z","timestamp":1750155331000},"page":"103-114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Language-Guided Adaptive Vision Token Pruning for\u00a0Efficient Multimodal Large Language Models"],"prefix":"10.1007","author":[{"given":"Omer Faruk","family":"Deniz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tarik","family":"Arici","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fateme","family":"Sheikholeslami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Burak","family":"Gozluklu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ameni","family":"Trabelsi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suleiman","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yapeng","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Latifur","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"9_CR1","unstructured":"Introducing IDEFICS: An open reproduction of state-of-the-art visual language model. https:\/\/huggingface.co\/blog\/idefics"},{"key":"9_CR2","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv (2023)"},{"key":"9_CR3","unstructured":"Bai, J., et al.: Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv (2023)"},{"key":"9_CR4","unstructured":"Berthet, Q., Blondel, M., Teboul, O., Cuturi, M., Vert, J.P., Bach, F.: Learning with differentiable Perturbed optimizers. In: NeurIPS (2020)"},{"key":"9_CR5","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: Your ViT but faster. arXiv (2022)"},{"key":"9_CR6","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic. arXiv (2023)"},{"key":"9_CR7","doi-asserted-by":"crossref","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: ECCV, pp. 19\u201335. Springer (2025)","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"9_CR8","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. In: NeurIPS (2023)"},{"key":"9_CR9","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., Zettlemoyer, L.: GPT3.int8(): 8-bit matrix multiplication for transformers at scale. NeurIPS (2022)"},{"key":"9_CR10","unstructured":"Devlin, J.: BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv (2018)"},{"key":"9_CR11","unstructured":"Fu, C., et al.: MME: A comprehensive evaluation benchmark for multimodal large language models. arXiv (2024)"},{"key":"9_CR12","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":"9_CR13","unstructured":"Gu, Y., Dong, L., Wei, F., Huang, M.: MiniLLM: knowledge distillation of large language models. arXiv (2023)"},{"key":"9_CR14","unstructured":"Hu, E.J., et al.: LoRA: Low-rank adaptation of large language models. arXiv (2021)"},{"key":"9_CR15","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, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"9_CR16","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with Gumbel-Softmax. arXiv (2016)"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Kong, Z., et\u00a0al.: SPViT: enabling faster vision transformers via latency-aware soft token pruning. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"9_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. PMLR (2023)"},{"key":"9_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. arXiv (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: ICCV (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Liu, N.F., et al.: Lost in the middle: How language models use long contexts. TACL (2024)","DOI":"10.1162\/tacl_a_00638"},{"key":"9_CR22","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. In: NeurIPS (2022)"},{"key":"9_CR23","first-page":"21702","volume":"36","author":"X Ma","year":"2023","unstructured":"Ma, X., Fang, G., Wang, X.: LLM-Pruner: on the structural pruning of large language models. NeurIPS 36, 21702\u201321720 (2023)","journal-title":"NeurIPS"},{"key":"9_CR24","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: DynamicViT: efficient vision transformers with dynamic token sparsification. NeurIPS (2021)"},{"key":"9_CR25","unstructured":"Shang, Y., Cai, M., Xu, B., Lee, Y.J., Yan, Y.: LLaVA-PruMerge: Adaptive token reduction for efficient large multimodal models. arXiv (2024)"},{"key":"9_CR26","unstructured":"Shi, F., et al.: Large language models can be easily distracted by irrelevant context. In: International Conference on Machine Learning, pp. 31210\u201331227. PMLR (2023)"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: CVPR, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"9_CR28","unstructured":"Vaswani, A.: Attention is all you need. NeurIPS (2017)"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, X., Li, H., Liu, L., Wu, Z., Jiang, Y.G.: Efficient video transformers with spatial-temporal token selection. In: ECCV. Springer (2022)","DOI":"10.1007\/978-3-031-19833-5_5"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: MMBench: Is your multi-modal model an all-around player? (2023)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"9_CR31","unstructured":"Zhang, Y., et\u00a0al.: SparseVLM: visual token Sparsification for efficient vision-language model inference. arXiv (2024)"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhu, M., Liu, N., Ou, Z., Mou, X., Tang, J.: LLaVA-Phi: efficient multi-modal assistant with small language model. arXiv (2024)","DOI":"10.1145\/3688863.3689575"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8186-0_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T10:15:43Z","timestamp":1750155343000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8186-0_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819681853","9789819681860"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8186-0_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"18 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}