{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:28:20Z","timestamp":1763191700829,"version":"3.45.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227736","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["HyDRA: Hierarchical and Dynamic Rank Adaptation for Mobile Vision Language Model"],"prefix":"10.1109","author":[{"given":"Yuanhao","family":"Xi","sequence":"first","affiliation":[{"name":"Liaoning Technical University,Huludao,China"}]},{"given":"Xiaohuan","family":"Bing","sequence":"additional","affiliation":[{"name":"Liaoning Technical University,Huludao,China"}]},{"given":"Ramin","family":"Yahyapour","sequence":"additional","affiliation":[{"name":"University of Göttingen,Göttingen,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2024.3383473"},{"journal-title":"Mobilevlm: A fast, reproducible and strong vision language assistant for mobile devices","year":"2023","author":"Chu","key":"ref3"},{"key":"ref4","article-title":"Cheap and quick: Efficient vision-language instruction tuning for large language models","volume":"36","author":"Luo","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"journal-title":"Lora: Low-rank adaptation of large language models","year":"2021","author":"Hu","key":"ref6"},{"journal-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","year":"2024","author":"Han","key":"ref7"},{"journal-title":"Parameter-efficient fine-tuning methods for pretrained language models: A critical review and assessment","year":"2023","author":"Xu","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.239"},{"key":"ref10","article-title":"Qlora: Efficient finetuning of quantized llms","volume":"36","author":"Dettmers","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"Lorahub: Efficient cross-task generalization via dynamic lora composition","year":"2023","author":"Huang","key":"ref11"},{"journal-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","year":"2024","author":"Fu","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref17","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume":"35","author":"Lu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref20","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"journal-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref21"},{"journal-title":"Attention is all you need","year":"2017","author":"Vaswani","key":"ref22"},{"journal-title":"Adam: a method for stochastic optimization","year":"2014","author":"Kingma","key":"ref23"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"journal-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref26"},{"journal-title":"Mistral 7b","year":"2023","author":"Jiang","key":"ref27"},{"journal-title":"Tinyllama: An open-source small language model","year":"2024","author":"Zhang","key":"ref28"},{"journal-title":"Minicpm: Unveiling the potential of small language models with scalable training strategies","year":"2024","author":"Hu","key":"ref29"},{"journal-title":"Textbooks are all you need ii: phi-1.5 technical report","year":"2023","author":"Li","key":"ref30"},{"journal-title":"Citekey: gptvision","article-title":"Gpt-4v (ision) system card","year":"2023","key":"ref31"},{"key":"ref32","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in neural information processing systems"},{"journal-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","year":"2023","author":"Zhu","key":"ref33"},{"issue":"3","key":"ref34","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3688863.3689575"},{"key":"ref36","article-title":"Phi-2: The surprising power of small language models","author":"Javaheripi","year":"2023","journal-title":"Microsoft Research Blog"},{"key":"ref37","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"International conference on machine learning","author":"Houlsby"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00662"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227736.pdf?arnumber=11227736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:25:15Z","timestamp":1763191515000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227736\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227736","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}