{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:14:13Z","timestamp":1781018053988,"version":"3.54.1"},"reference-count":67,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306090,U24A20328"],"award-info":[{"award-number":["62306090,U24A20328"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Natural Science Foundation of Guangdong Province of China","doi-asserted-by":"publisher","award":["2024A1515010147"],"award-info":[{"award-number":["2024A1515010147"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008544","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["KQTD20240729102207002"],"award-info":[{"award-number":["KQTD20240729102207002"]}],"id":[{"id":"10.13039\/501100008544","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing, China","doi-asserted-by":"publisher","award":["L254018"],"award-info":[{"award-number":["L254018"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Jiangsu Science and Technology Major Program","doi-asserted-by":"publisher","award":["BG2024041"],"award-info":[{"award-number":["BG2024041"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002338","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M764192"],"award-info":[{"award-number":["2024M764192"]}],"id":[{"id":"10.13039\/501100002338","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\/iccv51701.2025.02184","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23530-23540","source":"Crossref","is-referenced-by-count":4,"title":["FALCON: Resolving Visual Redundancy and Fragmentation in High-Resolution Multimodal Large Language Models via Visual Registers"],"prefix":"10.1109","author":[{"given":"Renshan","family":"Zhang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Shao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gongwei","family":"Chen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiwen","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weili","family":"Guan","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02506"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00558"},{"key":"ref4","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Spa-bench: A comprehensive benchmark for smartphone agent evaluation","volume-title":"In The Thirteenth International Conference on Learning Representations","author":"Chen","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"issue":"3","key":"ref8","volume":"2","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* ChatGPT quality"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref10","article-title":"Vision transformers need registers","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Darcet","year":"2024"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"In International Conference on Learning Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref12","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Bridging nonlinearities and stochastic regularizers with gaussian error linear units","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.70675\/802872a7z8092z4556za1fdz2c7af45f0e72"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"key":"ref16","article-title":"Mini-monkey: Alleviating the semantic sawtooth effect for lightweight MLLMs via complementary image pyramid","volume-title":"In The Thirteenth International Conference on Learning Representations","author":"Huang","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02775"},{"key":"ref18","article-title":"Openvla: An open-source vision-language-action model","volume-title":"In 8th Annual Conference on Robot Learning","author":"Jin Kim","year":"2024"},{"key":"ref19","article-title":"Seed-bench: Benchmarking mul-timodal 11 ms with generative comprehension","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"LLaVA-onevision: Easy visual task transfer","author":"Li","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref21","article-title":"STAR: Learning diverse robot skill abstractions through rotation-augmented vector quantization","volume-title":"In Forty-second International Conference on Machine Learning","author":"Li","year":"2025"},{"key":"ref22","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"In International conference on machine learning","author":"Li","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_17"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00308"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3637265"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1580"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00845"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref31","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref32","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3653415"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref36","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"In The 36th Conference on Neural Information Processing Systems (NeurIPS)","author":"Lu","year":"2022"},{"key":"ref38","article-title":"Feast your eyes: Mixture-ofresolution adaptation for multimodal large language models","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01621"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755029"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01026"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00667"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367749"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1330"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_25"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref50","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.282"},{"key":"ref55","article-title":"Deco: Decoupling token compression from semantic abstraction in multimodal large language models","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"mplug-docowl: Modularized multimodal large language model for document understanding","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.187"},{"key":"ref59","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref63","article-title":"Internlm-xcomposer-2.5: A versatile large vision language model supporting long-contextual input and output","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Token-level correlation-guided compression for efficient multimodal document understanding","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"From redundancy to relevance: Enhancing explainability in multimodal large language models","volume-title":"In Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics","author":"Zhang","year":"2025"},{"key":"ref66","article-title":"MMErealworld: Could your multimodal LLM challenge highresolution real-world scenarios that are difficult for humans?","volume-title":"In The Thirteenth International Conference on Learning Representations","author":"Zhang","year":"2025"},{"key":"ref67","article-title":"Beyond llava-hd: Diving into high-resolution large multimodal models","author":"Zhang","year":"2024","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\/11443500.pdf?arnumber=11443500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:00:56Z","timestamp":1777611656000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443500\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02184","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}