{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T11:40:49Z","timestamp":1779882049767,"version":"3.53.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFC3305600"],"award-info":[{"award-number":["2023YFC3305600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472381"],"award-info":[{"award-number":["62472381"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for the Zhejiang Provincial Universities","award":["226-2024-00208"],"award-info":[{"award-number":["226-2024-00208"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tai.2025.3596925","type":"journal-article","created":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T18:43:18Z","timestamp":1754678598000},"page":"1355-1364","source":"Crossref","is-referenced-by-count":6,"title":["Prompt-Aware Adapter: Learning Adaptive Visual Tokens for Multimodal Large Language Models"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0431-6390","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9572-2345","authenticated-orcid":false,"given":"Hehe","family":"Fan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8106-9768","authenticated-orcid":false,"given":"Wei","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, Nanjing University, Suzhou, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1239-4428","authenticated-orcid":false,"given":"Yongkang","family":"Wong","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7410-2590","authenticated-orcid":false,"given":"Roger","family":"Zimmermann","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref2","article-title":"Introducing ChatGPT","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.2100463"},{"key":"ref4","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref5","article-title":"Vicuna: An open-source Chatbot impressing GPT-4 with 90%* ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3390891"},{"key":"ref7","article-title":"PaLM-E: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref9","first-page":"76137","article-title":"Dense and aligned captions (DAC) promote compositional reasoning in VL models","volume":"36","author":"Doveh","year":"2024","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref10","first-page":"20299","article-title":"VPGTrans: Transfer visual prompt generator across LLMS","volume":"36","author":"Zhang","year":"2023","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref11","article-title":"ProtChatGPT: Towards understanding proteins with large language models","author":"Wang","year":"2024"},{"key":"ref12","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref13","article-title":"MiniGPT-v2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref14","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.440"},{"key":"ref16","article-title":"One model to instruction-follow them all","author":"Su","year":"2023"},{"key":"ref17","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023"},{"key":"ref18","article-title":"InfMLLM: A unified framework for visual-language tasks","author":"Zhou","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01311"},{"key":"ref20","first-page":"33108","article-title":"Dense connector for MLLMs","volume":"37","author":"Yao","year":"2024","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref21","first-page":"1","article-title":"VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks","volume":"36","author":"Wang","year":"2024","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref22","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref23","first-page":"49250","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume":"36","author":"Dai","year":"2024","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref24","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref25","first-page":"2953","article-title":"Exploring models and data for image question answering","volume":"28","author":"Ren","year":"2015","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref26","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023"},{"key":"ref27","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3135117"},{"issue":"240","key":"ref30","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref31","article-title":"LaMDA: Language models for dialog applications","author":"Thoppilan","year":"2022"},{"key":"ref32","article-title":"MiniCPM: Unveiling the potential of small language models with scalable training strategies","author":"Hu","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3637265"},{"key":"ref35","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle","year":"2021"},{"key":"ref36","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref37","article-title":"mPLUG-Owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref38","article-title":"Multimodal-GPT: A vision and language model for dialogue with humans","author":"Gong","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3571946"},{"key":"ref40","first-page":"1","article-title":"Fine-tuning multimodal LLMS to follow zero-shot demonstrative instructions","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Li","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1174"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.25300\/misq\/2024\/17115"},{"key":"ref43","article-title":"Frustratingly short attention spans in neural language modeling","author":"Rockt\u00e4schel","year":"2017"},{"key":"ref44","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume":"29","author":"Lu","year":"2016","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref46","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref47","article-title":"Reformulating vision-language foundation models and datasets towards universal multimodal assistants","author":"Yu","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref49","article-title":"LLAMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref50","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref52","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume":"24","author":"Ordonez","year":"2011","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref61","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref62","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023"},{"key":"ref63","first-page":"20299","article-title":"VPGTrans: Transfer visual prompt generator across LLMS","volume":"36","author":"Zhang","year":"2024","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref64","first-page":"29615","article-title":"Cheap and quick: Efficient vision-language instruction tuning for large language models","volume":"36","author":"Luo","year":"2024","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref65","first-page":"1571","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Liu","year":"2023"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/11417361\/11120837.pdf?arnumber=11120837","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T20:59:06Z","timestamp":1772485146000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11120837\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":65,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tai.2025.3596925","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}