{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T07:14:05Z","timestamp":1771571645035,"version":"3.50.1"},"reference-count":7,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/apccas67402.2025.11376880","type":"proceedings-article","created":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T20:54:40Z","timestamp":1771534480000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["An Energy-Efficient Vision Language Model Inference with Importance-aware Token Pruning"],"prefix":"10.1109","author":[{"given":"Zhamaliddin","family":"Kalzhan","sequence":"first","affiliation":[{"name":"School of Electrical Engineering KAIST,Daejeon,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songyeon","family":"Hong","sequence":"additional","affiliation":[{"name":"Graduate School of AI Semiconductor KAIST,Daejeon,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hoi-Jun","family":"Yoo","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering KAIST,Daejeon,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"key":"ref2","article-title":"Mobilevlm v2: Faster and stronger baseline for vision language model","author":"Xiangxiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Hugo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Towards vqa models that can read","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Amanpreet"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Jacob","year":"2018","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Efficient streaming language models with attention sinks","author":"Guangxuan","journal-title":"ICLR 2024"}],"event":{"name":"2025 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","location":"Busan, Korea, Republic of","start":{"date-parts":[[2025,10,12]]},"end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373921\/11376610\/11376880.pdf?arnumber=11376880","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T06:49:42Z","timestamp":1771570182000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11376880\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":7,"URL":"https:\/\/doi.org\/10.1109\/apccas67402.2025.11376880","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}