{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T20:52:53Z","timestamp":1775508773007,"version":"3.50.1"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["2022ZD0117901"],"award-info":[{"award-number":["2022ZD0117901"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373355"],"award-info":[{"award-number":["62373355"]}],"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":["62322607"],"award-info":[{"award-number":["62322607"]}],"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":["62236010"],"award-info":[{"award-number":["62236010"]}],"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":["62141608"],"award-info":[{"award-number":["62141608"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L252033"],"award-info":[{"award-number":["L252033"]}],"id":[{"id":"10.13039\/501100004826","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":[[2026,5]]},"DOI":"10.1109\/tpami.2026.3650761","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:38:31Z","timestamp":1767638311000},"page":"5493-5504","source":"Crossref","is-referenced-by-count":0,"title":["Beyond LLaVA-HD: Diving Into High-Resolution Multimodal Large Language Models"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6227-0183","authenticated-orcid":false,"given":"YiFan","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Center for Research on Intelligent Perception and Computing (CRIPAC), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4516-2524","authenticated-orcid":false,"given":"Qingsong","family":"Wen","sequence":"additional","affiliation":[{"name":"Squirrel Ai Learning, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0079-7668","authenticated-orcid":false,"given":"Chaoyou","family":"Fu","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0602-169X","authenticated-orcid":false,"given":"Kun","family":"Wang","sequence":"additional","affiliation":[{"name":"Squirrel Ai Learning, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2296-9688","authenticated-orcid":false,"given":"Xue","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9425-3065","authenticated-orcid":false,"given":"Zhang","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Center for Research on Intelligent Perception and Computing (CRIPAC), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-8647","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Center for Research on Intelligent Perception and Computing (CRIPAC), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8797-4646","authenticated-orcid":false,"given":"Rong","family":"Jin","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref3","article-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"ref4","article-title":"OpenFlamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref7","article-title":"VITA: Towards open-source interactive omni multimodal LLM","author":"Fu","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3590929"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3557703"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3557680"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3557692"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535389"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755364"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref15","article-title":"Thyme: Think beyond images","author":"Zhang","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3637265"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3590940"},{"key":"ref19","article-title":"Kwai keye-VL technical report","author":"Team","year":"2025"},{"key":"ref20","article-title":"Qwen-VL: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_18"},{"key":"ref24","article-title":"LLaVA-NeXT: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_23"},{"key":"ref26","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref27","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.440"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref30","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.775"},{"key":"ref32","article-title":"Measuring multimodal mathematical reasoning with math-vision dataset","author":"Wang","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.571"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.46"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.528"},{"key":"ref36","article-title":"Dynamic prompt learning via policy gradient for semi-structured mathematical reasoning","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Lu","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref40","article-title":"LLaVAR: Enhanced visual instruction tuning for text-rich image understanding","author":"Zhang","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2026.3654458"},{"key":"ref43","article-title":"CuMo: Scaling multimodal LLM with co-upcycled mixture-of-experts","volume-title":"Proc. 38th Annu. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2024"},{"key":"ref44","article-title":"OtterHD: A high-resolution multi-modality model","author":"Li","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref48","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023"},{"key":"ref49","article-title":"LLaVA-OneVision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"ref51","article-title":"MME-realworld: Could your multimodal LLM challenge high-resolution real-world scenarios that are difficult for humans?","author":"Zhang","year":"2024"},{"key":"ref52","article-title":"Improving convergence and generalization using parameter symmetries","author":"Zhao","year":"2024"},{"key":"ref53","article-title":"Token merging: Your ViT but faster","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bolya","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref55","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref56","first-page":"11324","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref57","article-title":"Palm 2 technical report","author":"Anil","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.891"},{"key":"ref59","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref60","article-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"ref61","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref62","first-page":"71683","article-title":"OBELICS: An open web-scale filtered dataset of interleaved image-text documents","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lauren\u00e7on","year":"2024"},{"key":"ref63","article-title":"PaLM-E: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref64","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3571946"},{"key":"ref66","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref67","article-title":"mPLUG-Owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref70","article-title":"SVIT: Scaling up visual instruction tuning","author":"Zhao","year":"2023"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2300479"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref73","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":"ref74","first-page":"57730","article-title":"MM-Vet: Evaluating large multimodal models for integrated capabilities","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu","year":"2024"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref77","article-title":"MathVista: Evaluating mathematical reasoning of foundation models in visual contexts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lu","year":"2024"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref79","article-title":"An LLM-free multi-dimensional benchmark for MLLMs hallucination evaluation","author":"Wang","year":"2023"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11329123.pdf?arnumber=11329123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:18Z","timestamp":1775505378000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329123\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":80,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3650761","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":[[2026,5]]}}}