{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:06:04Z","timestamp":1777889164963,"version":"3.51.4"},"reference-count":38,"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\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["24511103100"],"award-info":[{"award-number":["24511103100"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001459","name":"Ministry of Education, Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001459","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\/iccv51701.2025.00262","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2728-2737","source":"Crossref","is-referenced-by-count":0,"title":["From Holistic to Localized: Local Enhanced Adapters for Efficient Visual Instruction Fine-Tuning"],"prefix":"10.1109","author":[{"given":"Pengkun","family":"Jiao","sequence":"first","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Singapore Management University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied Al, Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong-Wah","family":"Ngo","sequence":"additional","affiliation":[{"name":"Singapore Management University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied Al, Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv preprint"},{"issue":"2","key":"ref3","first-page":"3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"1","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Llava-mole: Sparse mixture of lora experts for mitigating data conflicts in instruction finetuning mllms","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"issue":"3","key":"ref6","first-page":"6","volume":"2","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90 %* chatgpt quality"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref9","article-title":"Mousi: Poly-visual-expert vision-language models","author":"Fan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","author":"Glorot","year":"2011"},{"key":"ref11","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Harder tasks need more experts: Dynamic routing in moe models","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Rode: Linear rectified mixture of diverse experts for food large multi-modal models","author":"Jiao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_22"},{"key":"ref15","article-title":"Don\u2019t deceive me: Mitigating gaslighting through attention reallocation in 1 mms","author":"Jiao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref16","first-page":"81461","article-title":"Lumen: Unleashing versatile vision-centric capabilities of large multimodal models","volume":"37","author":"Jiao","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref18","first-page":"1973019742","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":"ref19","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref23","article-title":"Adamole: Fine-tuning large language models with adaptive mixture of low-rank adaptation experts","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-6319"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-022-00329-y"},{"key":"ref30","article-title":"Cambrian1: A fully open, vision-centric exploration of multimodal 1 lms","author":"Tong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00914"},{"key":"ref32","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Mixture of lora experts","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref35","article-title":"Llava-uhd: an 1 mm perceiving any aspect ratio and high-resolution images","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3590924"},{"key":"ref37","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv preprint"}],"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\/11444834.pdf?arnumber=11444834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:35Z","timestamp":1777612055000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444834\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00262","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}