{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:29:30Z","timestamp":1773170970031,"version":"3.50.1"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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":["2023YFB4502804"],"award-info":[{"award-number":["2023YFB4502804"]}]},{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025603"],"award-info":[{"award-number":["62025603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2051"],"award-info":[{"award-number":["U22B2051"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2037"],"award-info":[{"award-number":["U21B2037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072389"],"award-info":[{"award-number":["62072389"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302411"],"award-info":[{"award-number":["62302411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["624B2118"],"award-info":[{"award-number":["624B2118"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2021J06003"],"award-info":[{"award-number":["2021J06003"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M732948"],"award-info":[{"award-number":["2023M732948"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tpami.2025.3644851","type":"journal-article","created":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T18:46:02Z","timestamp":1765997162000},"page":"4524-4538","source":"Crossref","is-referenced-by-count":0,"title":["Boosting Multi-Modal Large Language Model With Enhanced Visual Features"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8744-3423","authenticated-orcid":false,"given":"Yiwei","family":"Ma","sequence":"first","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3807-6969","authenticated-orcid":false,"given":"Weihuang","family":"Lin","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7618-7973","authenticated-orcid":false,"given":"Zhibin","family":"Wang","sequence":"additional","affiliation":[{"name":"Inf Tech Company, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9956-6308","authenticated-orcid":false,"given":"Jiayi","family":"Ji","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-9306","authenticated-orcid":false,"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9097-2318","authenticated-orcid":false,"given":"Chia-Wen","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref3","article-title":"Qwen2 technical report","author":"Yang","year":"2024"},{"key":"ref4","article-title":"Mixtral of experts","author":"Jiang","year":"2024"},{"key":"ref5","article-title":"Qwen-VL: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref6","article-title":"DeepSeek-VL: Towards real-world vision-language understanding","author":"Lu","year":"2024"},{"key":"ref7","first-page":"33108","article-title":"Dense connector for MLLMs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Yao","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.32982"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3637265"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref12","article-title":"MME-RealWorld: Could your multimodal LLM challenge high-resolution real-world scenarios that are difficult for humans?","volume-title":"13th Int. Conf. Learn. Representations","author":"Zhang","year":"2025"},{"key":"ref13","article-title":"MMSearch: Benchmarking the potential of large models as multi-modal search engines","volume-title":"13th Int. Conf. Learn. Representations","author":"Jiang","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01202"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref16","article-title":"EVA-CLIP: Improved training techniques for clip at scale","author":"Sun","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref18","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02491-7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_25"},{"key":"ref22","article-title":"MobileVLM: A fast, reproducible and strong vision language assistant for mobile devices","author":"Chu","year":"2023"},{"key":"ref23","article-title":"MPLUG-OWL3: Towards long image-sequence understanding in multi-modal large language models","volume-title":"13th Int. Conf. Learn. Representations","author":"Ye","year":"2025"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3860"},{"key":"ref25","first-page":"29615","article-title":"Cheap and quick: Efficient vision-language instruction tuning for large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Luo","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.11.015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.12.002"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-81-322-3972-7_19"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3532440"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref36","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref37","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. neural inf. process. syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref38","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref39","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref40","article-title":"Finetuned language models are zero-shot learners","volume-title":"Int. Conf. Learn. Representations","author":"Wei","year":"2022"},{"key":"ref41","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ouyang","year":"2022"},{"key":"ref42","article-title":"Stanford alpaca: An instruction-following LLaMA model","author":"Taori","year":"2023"},{"key":"ref43","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* chatGPT quality","author":"Chiang","year":"2023"},{"key":"ref44","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref45","article-title":"LLaVA-NeXT: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref47","article-title":"NVLM: Open frontier-class multimodal LLMS","author":"Dai","year":"2024"},{"key":"ref48","article-title":"Molmo and PixMo: Open weights and open data for state-of-the-art multimodal models","author":"Deitke","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_23"},{"key":"ref51","article-title":"The LLaMA 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3643469"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref58","first-page":"1697","volume-title":"Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis.","author":"Mathew","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref63","first-page":"57730","article-title":"MM-Vet: Evaluating large multimodal models for integrated capabilities","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Yu","year":"2024"},{"key":"ref64","article-title":"MathVista: Evaluating mathematical reasoning of foundation models in visual contexts","volume-title":"12th Int. Conf. Learn. Representations","author":"Lu","year":"2024"},{"key":"ref65","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lu","year":"2022"},{"key":"ref66","article-title":"Seed-bench: Benchmarking multimodal LLMS with generative comprehension","author":"Li","year":"2023"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866080"},{"key":"ref68","article-title":"MobileVLM V2: Faster and stronger baseline for vision language model","author":"Chu","year":"2024"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11424231\/11301404.pdf?arnumber=11301404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:34:50Z","timestamp":1773106490000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11301404\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":71,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3644851","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}