{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:48Z","timestamp":1778048328689,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00112","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1084-1093","source":"Crossref","is-referenced-by-count":0,"title":["MR-Pruner: Training-free Multi-resolution Visual Token Pruning for Multi-modal Large Language Models"],"prefix":"10.1109","author":[{"given":"Seunghoon","family":"Han","sequence":"first","affiliation":[{"name":"Chungnam National University,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyewon","family":"Lee","sequence":"additional","affiliation":[{"name":"Chungnam National University,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soyoung","family":"Park","sequence":"additional","affiliation":[{"name":"Chungnam National University,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jong-Ryul","family":"Lee","sequence":"additional","affiliation":[{"name":"Chungnam National University,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungsu","family":"Lim","sequence":"additional","affiliation":[{"name":"Chungnam National University,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"issue":"2","key":"ref2","first-page":"3","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","volume":"1","author":"Bai","year":"2023"},{"key":"ref3","article-title":"Token merging: Your vit but faster","volume-title":"Proceedings of International Conference on Learning Representations","author":"Bolya"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proceedings of International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref9","author":"Fu","year":"2024","journal-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32427"},{"key":"ref13","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of International conference on machine learning","author":"Li"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref15","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","volume-title":"Proceedings of International Conference on Learning Representations","author":"Liang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref17","author":"Liu","year":"2024","journal-title":"Llavanext: Improved reasoning, ocr, and world knowledge"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref20","article-title":"Inf-llava: Dual-perspective perception for high-resolution multimodal large language model","author":"Ma","year":"2024"},{"key":"ref21","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.02122"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref24","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref25","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref26","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01521"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.51"},{"key":"ref31","article-title":"Llava-uhd v2: an mllm integrating high-resolution feature pyramid via hierarchical window transformer","author":"Zhang","year":"2024"},{"key":"ref32","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proceedings of International Conference on Learning Representations","author":"Zhu"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492336.pdf?arnumber=11492336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:07Z","timestamp":1778046967000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492336\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00112","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}