{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T07:21:25Z","timestamp":1781076085287,"version":"3.54.1"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62225603"],"award-info":[{"award-number":["62225603"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00030","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"239-249","source":"Crossref","is-referenced-by-count":6,"title":["LLaVA-KD: A Framework of Distilling Multimodal Large Language Models"],"prefix":"10.1109","author":[{"given":"Yuxuan","family":"Cai","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyang","family":"He","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinwei","family":"He","sequence":"additional","affiliation":[{"name":"Huazhong Agricultural University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ao","family":"Tong","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenye","family":"Gan","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhucun","family":"Xue","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Qwen-Vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref4","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref5","article-title":"Distillation scaling laws","author":"Busbridge","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref6","article-title":"Mobilevlm: A fast, reproducible and strong vision language assistant for mobile devices","author":"Chu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref8","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref9","article-title":"Sphinx-X: Scaling data and parameters for a family of multi-modal large language models","author":"Gao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref11","article-title":"Minillm: Knowledge Distillation of Large Language Models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Gu","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref13","article-title":"Efficient multimodal learning from data-centric perspective","author":"He","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref18","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref19","article-title":"Distillm: Towards streamlined distillation for large language models","author":"Ko","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref20","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning","author":"Li","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3637265"},{"key":"ref23","article-title":"Moe-Llava: Mixture of experts for large vision-language models","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref25","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref28","article-title":"Feast Your Eyes: mixture-ofresolution adaptation for multimodal large language models","author":"Luo","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref29","first-page":"417","article-title":"Groma: Localized visual tokenization for grounding multimodal large language models","volume-title":"European Conference on Computer Vision","author":"Ma","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.109"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3557680"},{"key":"ref32","article-title":"Llava-Mod: Making llava tiny via moe knowledge distillation","author":"Shu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00926"},{"key":"ref35","article-title":"Tinyllm: Learning a small student from multiple large language models","author":"Tian","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref36","article-title":"Cambrian-1: A Fully Open, Vision-centric exploration of multimodal llms","author":"Tong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3103973"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.605"},{"key":"ref39","first-page":"69925","article-title":"Visionllm V2: An end-to-end generalist multimodal large language model for hundreds of vision-language tasks","volume":"37","author":"Wu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","article-title":"Rethinking kullback-leibler divergence in knowledge distillation for large language models","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_40"},{"key":"ref42","article-title":"Llavadi: What matters for multimodal large language models distillation","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Qwen2 Technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01510"},{"key":"ref45","article-title":"Minicpm-v: a gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref46","first-page":"13040","article-title":"mplug-owl2: Revolutionizing multi-modal large language model with modality collaboration","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ye","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"ref50","first-page":"71737","article-title":"Omg-Llava: bridging image-level, object-level, pixel-level reasoning and understanding","volume":"37","author":"Zhang","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_5"},{"key":"ref52","article-title":"Tinyllava: A framework of small-scale large multimodal models","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3688863.3689575"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445139.pdf?arnumber=11445139","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:13:34Z","timestamp":1777529614000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445139\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00030","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}