{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:21:05Z","timestamp":1777890065407,"version":"3.51.4"},"reference-count":48,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402023, 62476181"],"award-info":[{"award-number":["62402023, 62476181"]}],"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\/iccv51701.2025.00658","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7004-7013","source":"Crossref","is-referenced-by-count":0,"title":["Layer-Wise Vision Injection With Disentangled Attention for Efficient LVLMs"],"prefix":"10.1109","author":[{"given":"Xuange","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing University of Technology,CN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dengjie","family":"Li","sequence":"additional","affiliation":[{"name":"Meituan Inc.,CN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing University of Technology,CN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zenghao","family":"Bao","sequence":"additional","affiliation":[{"name":"Meituan Inc.,CN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Meituan Inc.,CN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baisong","family":"Yang","sequence":"additional","affiliation":[{"name":"Meituan Inc.,CN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongying","family":"Liu","sequence":"additional","affiliation":[{"name":"Meituan Inc.,CN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujie","family":"Zhong","sequence":"additional","affiliation":[{"name":"Meituan Inc.,CN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongtong","family":"Yuan","sequence":"additional","affiliation":[{"name":"Beijing University of Technology,CN"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Openflamingo: An open-source framework for training large autoregressive vision-language models","volume":"abs\/2308.01390","author":"Awadalla","year":"2023","journal-title":"ArXiv"},{"key":"ref4","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","volume":"abs\/2308.12966","author":"Bai","year":"2023","journal-title":"ArXiv"},{"key":"ref6","author":"Bavishi","year":"2023","journal-title":"Introducing our multimodal models"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00439"},{"key":"ref8","author":"Cai","year":"2024","journal-title":"Matryoshka multimodal models"},{"key":"ref9","article-title":"Matryoshka multimodal models","author":"Cai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01487"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.721"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref14","author":"Chu","year":"2023","journal-title":"Mobilevlm: A fast, strong and open vision language assistant for mobile devices"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref16","author":"Dong","year":"2024","journal-title":"Internlm-xcomposer2-4khd: A pioneering large vision-language model handling resolutions from 336 pixels to 4 k hd"},{"key":"ref17","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","volume":"abs\/2306.13394","author":"Fu","year":"2023","journal-title":"ArXiv"},{"key":"ref18","article-title":"Multimodal-gpt: A vision and language model for dialogue with humans","volume":"abs\/2305.04790","author":"Gong","year":"2023","journal-title":"ArXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref21","article-title":"Llava-onevision: Easy visual task transfer","volume":"abs\/2408.03326","author":"Li","year":"2024","journal-title":"ArXiv"},{"key":"ref22","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"In International conference on machine learning","author":"Li"},{"key":"ref23","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"In International conference on machine learning","author":"Li"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32567"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32567"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref28","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3653415"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref31","article-title":"Llava-prumerge: Adaptive token reduction for efficient large multimodal models","author":"Shang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","author":"Shang","year":"2024","journal-title":"Llava-prumerge: Adaptive token reduction for efficient large multimodal models"},{"key":"ref33","author":"She","year":"2024","journal-title":"Mammothmoda: Multi-modal large language model"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref35","article-title":"Gemma: Open models based on gemini research and technology","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Llama: open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02008"},{"key":"ref38","author":"Xing","year":"2025","journal-title":"Pyramiddrop: Accelerating your large vision-language models via pyramid visual redundancy reduction"},{"key":"ref39","article-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities","volume":"abs\/2308.02490","author":"Yu","year":"2023","journal-title":"ArXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref41","article-title":"Glm-130b: An open bilingual pre-trained model","author":"Zeng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref43","article-title":"Tinyllama: An open-source small language model","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","author":"Zhang","year":"2024","journal-title":"Token-level correlation-guided compression for efficient multimodal document understanding"},{"key":"ref45","article-title":"Tinyllava: A framework of small-scale large multimodal models","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","author":"Zhu","year":"2024","journal-title":"Focusllava: A coarse-to-fine approach for efficient and effective visual token compression"},{"key":"ref48","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\/11446304.pdf?arnumber=11446304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:25:53Z","timestamp":1777613153000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446304\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00658","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}