{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T07:05:14Z","timestamp":1790233514846,"version":"4.1.0"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370099","type":"print"},{"value":"9783032370105","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\/978-3-032-37010-5_26","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:47:43Z","timestamp":1790232463000},"page":"470-487","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Prune Once: Retraining-Free Task-Agnostic Pruning for\u00a0Vision-Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0801-905X","authenticated-orcid":false,"given":"Minseok","family":"Kang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7071-7711","authenticated-orcid":false,"given":"Hyunwoo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7351-3399","authenticated-orcid":false,"given":"Chanyoung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0381-0067","authenticated-orcid":false,"given":"Minwoo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5947-5487","authenticated-orcid":false,"given":"Jaekoo","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1344-1054","authenticated-orcid":false,"given":"Dahuin","family":"Jung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"26_CR1","unstructured":"Alizadeh, M., et al.: Prospect pruning: finding trainable weights at initialization using meta-gradients. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"26_CR3","unstructured":"Awadalla, A., et al.: OpenFlamingo: an open-source framework for training large autoregressive vision-language models (2023). arXiv:2308.01390 arXiv preprint"},{"key":"26_CR4","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1613\/jair.4900","volume":"55","author":"R Bernardi","year":"2016","unstructured":"Bernardi, R., et al.: Automatic description generation from images: a survey of models, datasets, and evaluation measures. J. Artif. Intell. Res. (JAIR) 55, 409\u2013442 (2016)","journal-title":"J. Artif. Intell. Res. (JAIR)"},{"key":"26_CR5","unstructured":"Blalock, D., Ortiz, J.J.G., Frankle, J., Guttag, J.: What is the state of neural network pruning? In: Proceedings of Machine Learning and Systems (MLSys) (2020)"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Cao, M., Li, S., Li, J., Nie, L., Zhang, M.: Image-text retrieval: a survey on recent research and development. arXiv preprint arXiv:2203.14713 (2022)","DOI":"10.24963\/ijcai.2022\/759"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Dorszewski, T., T\u011btkov\u00e1, L., Jenssen, R., Hansen, L.K., Wickstr\u00f8m, K.K.: From colors to classes: emergence of concepts in vision transformers. In: Explainable Artificial Intelligence, pp. 28\u201347. Springer (2025)","DOI":"10.1007\/978-3-032-08317-3_2"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Farina, M., Mancini, M., Cunegatti, E., Liu, G., Iacca, G., Ricci, E.: MultiFlow: shifting towards task-agnostic vision-language pruning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16185\u201316195 (2024)","DOI":"10.1109\/CVPR52733.2024.01532"},{"key":"26_CR10","unstructured":"Frantar, E., Alistarh, D.: SparseGPT: massive language models can be accurately pruned in one-shot. In: ICML (2023)"},{"key":"26_CR11","unstructured":"Gandelsman, Y., Efros, A.A., Steinhardt, J.: Interpreting CLIP\u2019S image representation via text-based decomposition (2023). arXiv:2310.05916 arXiv preprint"},{"key":"26_CR12","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. In: NeurIPS (2015)"},{"key":"26_CR13","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: NeurIPS (2015)"},{"key":"26_CR14","unstructured":"He, X., Sygnowski, J., Galashov, A., Rusu, A.A., Teh, Y.W., Pascanu, R.: Task agnostic continual learning via meta learning. In: 4th Lifelong Machine Learning Workshop at ICML (2020)"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Jamal, M.A., Qi, G.J.: Task agnostic meta-learning for few-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11719\u201311727 (2019)","DOI":"10.1109\/CVPR.2019.01199"},{"key":"26_CR16","unstructured":"de\u00a0Jorge, P., Sanyal, A., Behl, H.S., Torr, P.H.S., Rogez, G., Dokania, P.K.: Progressive skeletonization: trimming more fat from a network at initialization. In: International Conference on Learning Representations (ICLR) (2021)"},{"issue":"1","key":"26_CR17","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"26_CR18","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical report, University of Toronto (2009)"},{"key":"26_CR19","unstructured":"Lee, J., Park, S., Mo, S., Ahn, S., Shin, J.: Layer-adaptive sparsity for the magnitude-based pruning. In: ICLR (2021)"},{"key":"26_CR20","unstructured":"Lee, N., Ajanthan, T., Torr, P.: SNIP: single-shot network pruning based on connection sensitivity. In: ICLR (2019)"},{"key":"26_CR21","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":"26_CR22","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)"},{"key":"26_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36, pp. 34892\u201334916 (2023)","DOI":"10.52202\/075280-1516"},{"key":"26_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":"26_CR26","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: Indian Conference on Computer Vision, Graphics & Image Processing (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"26_CR28","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"26_CR29","unstructured":"Shi, D., Tao, C., Jin, Y., Yang, Z., Yuan, C., Wang, J.: UPop: unified and progressive pruning for compressing vision-language transformers. In: ICML (2023)"},{"key":"26_CR30","unstructured":"Sun, M., Liu, Z., Bair, A., Kolter, J.Z.: A simple and effective pruning approach for large language models. In: ICLR (2024)"},{"key":"26_CR31","unstructured":"Sung, Y.L., Yoon, J., Bansal, M.: ECoFLaP: efficient coarse-to-fine layer-wise pruning for vision-language models. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"26_CR32","unstructured":"Tanaka, H., Kunin, D., Yamins, D.L., Ganguli, S.: Pruning neural networks without any data by iteratively conserving synaptic flow. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"26_CR33","unstructured":"Wang, C., Zhang, G., Grosse, R.: Picking winning tickets before training by preserving gradient flow. In: International Conference on Learning Representations (ICLR) (2020)"},{"key":"26_CR34","unstructured":"Wang, H., Zhang, J., Ma, Q.: Exploring intrinsic dimension for vision-language model pruning. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, S., Zhang, W.Q., Suo, H., Wan, Y.: Task-agnostic structured pruning of speech representation models. In: Proceedings Interspeech 2023, pp. 231\u2013235 (2023)","DOI":"10.21437\/Interspeech.2023-1442"},{"key":"26_CR36","unstructured":"Wang, P., et al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhou, W., Zeng, Y., Zhang, X.: EfficientVLM: fast and accurate vision-language models via knowledge distillation and modal-adaptive pruning. In: Findings of the Association for Computational Linguistics: ACL 2023 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.873"},{"key":"26_CR38","unstructured":"Wang, Y., Li, D., Sun, R.: NTK-SAP: improving neural network pruning by aligning training dynamics. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"26_CR39","unstructured":"Williams, M., Aletras, N.: How does calibration data affect the post-training pruning and quantization of large language models? (2023). arXiv:2311.09755 arXiv preprint"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: NAS-BERT: task-agnostic and adaptive-size BERT compression with neural architecture search. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 1933\u20131943 (2021)","DOI":"10.1145\/3447548.3467262"},{"key":"26_CR41","unstructured":"Yin, L., et\u00a0al.: Outlier weighed layerwise sparsity (OWL): a missing secret sauce for pruning LLMs to high sparsity. arXiv preprint arXiv:2310.05175 (2023)"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: BMcook: a task-agnostic compression toolkit for big models. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 396\u2013405 (2022)","DOI":"10.18653\/v1\/2022.emnlp-demos.40"}],"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\/978-3-032-37010-5_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:47:54Z","timestamp":1790232474000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37010-5_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370099","9783032370105"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37010-5_26","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":"25 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"}}]}}