{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:17:12Z","timestamp":1778051832239,"version":"3.51.4"},"reference-count":36,"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\/wacv61042.2026.00691","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"7158-7167","source":"Crossref","is-referenced-by-count":0,"title":["EVTP-IVS: Effective Visual Token Pruning For Unifying Instruction Visual Segmentation In Multi-Modal Large Language Models"],"prefix":"10.1109","author":[{"given":"Wenhui","family":"Zhu","sequence":"first","affiliation":[{"name":"Arizona State University,AZ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiwen","family":"Chen","sequence":"additional","affiliation":[{"name":"Clemson University,SC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhipeng","family":"Wang","sequence":"additional","affiliation":[{"name":"LinkedIn Corporation,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shao","family":"Tang","sequence":"additional","affiliation":[{"name":"LinkedIn Corporation,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sayan","family":"Ghosh","sequence":"additional","affiliation":[{"name":"LinkedIn Corporation,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuanzhao","family":"Dong","sequence":"additional","affiliation":[{"name":"Arizona State University,AZ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajat","family":"Koner","sequence":"additional","affiliation":[{"name":"Ludwig Maximilian University of Munich,Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yalin","family":"Wang","sequence":"additional","affiliation":[{"name":"Arizona State University,AZ,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","article-title":"Deep variational information bottleneck","author":"Alemi","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00877"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13413-x"},{"key":"ref5","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2022"},{"key":"ref6","article-title":"Matryoshka multimodal models","volume-title":"Workshop on Video-Language Models@ NeurIPS 2024","author":"Cai"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33747"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00915"},{"key":"ref14","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref15","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02491-7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32567"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02561"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02491"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02122"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5040\/9781350879164"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01878"},{"key":"ref28","article-title":"Gsva: Generalized segmentation via multimodal large language models","author":"Xia","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01843"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i21.34366"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.01939"},{"key":"ref34","article-title":"Psalm: Pixelwise segmentation with large multi-modal model","author":"Zhang","year":"2024"},{"key":"ref35","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"}],"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\/11492448.pdf?arnumber=11492448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:31:01Z","timestamp":1778049061000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492448\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00691","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}