{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T01:56:37Z","timestamp":1768010197869,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":6,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3765766.3765832","type":"proceedings-article","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T14:07:31Z","timestamp":1767362851000},"page":"458-460","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HART-Pruner: A Human-Aligned Token Reduction Method for Interpretable and Efficient Vision-Language Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3995-4542","authenticated-orcid":false,"given":"Miho","family":"Takahashi","sequence":"first","affiliation":[{"name":"Software Innovation Center, NTT, Inc., Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5635-7936","authenticated-orcid":false,"given":"Rintaro","family":"Harada","sequence":"additional","affiliation":[{"name":"Software Innovation Center, NTT, Inc., Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0234-3552","authenticated-orcid":false,"given":"Akiko","family":"Masaki-Kato","sequence":"additional","affiliation":[{"name":"Software Innovation Center, NTT, Inc., Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9814-5475","authenticated-orcid":false,"given":"Takeharu","family":"Eda","sequence":"additional","affiliation":[{"name":"Software Innovation Center, NTT, Inc., Tokyo, Japan"}]}],"member":"320","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002497"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"e_1_3_3_1_4_2","unstructured":"Yuzhang Shang Mu Cai Bingxin Xu Yong\u00a0Jae Lee and Yan Yan. 2025. LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2025)."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"}],"event":{"name":"HAI '25: International Conference on Human-Agent Interaction","location":"Yokohama Japan","acronym":"HAI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 13th International Conference on Human-Agent Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3765766.3765832","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:17:37Z","timestamp":1767986257000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3765766.3765832"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":6,"alternative-id":["10.1145\/3765766.3765832","10.1145\/3765766"],"URL":"https:\/\/doi.org\/10.1145\/3765766.3765832","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2026-01-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}