{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T12:56:38Z","timestamp":1761396998333,"version":"3.37.3"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,1,19]],"date-time":"2025-01-19T00:00:00Z","timestamp":1737244800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,19]],"date-time":"2025-01-19T00:00:00Z","timestamp":1737244800000},"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":[[2025,1,19]]},"DOI":"10.1109\/iceic64972.2025.10879650","type":"proceedings-article","created":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T18:17:22Z","timestamp":1739902642000},"page":"1-4","source":"Crossref","is-referenced-by-count":1,"title":["Analysis of Transformer Decoder Architecture and KV Cache Behavior During LLM Inference"],"prefix":"10.1109","author":[{"given":"Kyudan","family":"Jung","sequence":"first","affiliation":[{"name":"Chung-Ang University"}]},{"given":"Jeong Youn","family":"Kwon","sequence":"additional","affiliation":[{"name":"Chung-Ang University"}]},{"given":"Young-Dae","family":"Mun","sequence":"additional","affiliation":[{"name":"Chung-Ang University"}]},{"given":"Byeong-Geun","family":"Kang","sequence":"additional","affiliation":[{"name":"Chung-Ang University"}]},{"given":"Joon-Seok","family":"Song","sequence":"additional","affiliation":[{"name":"Chung-Ang University"}]},{"given":"Min-Ji","family":"Kim","sequence":"additional","affiliation":[{"name":"Chung-Ang University"}]},{"given":"Nam-Joon","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University"}]},{"given":"Hyungon","family":"Ryu","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Hyuk-Jae","family":"Lee","sequence":"additional","affiliation":[{"name":"Chung-Ang University"}]}],"member":"263","reference":[{"journal-title":"Evaluation of openai o1: Opportunities and challenges of agi","year":"2024","author":"Zhong","key":"ref1"},{"key":"ref2","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dosovitskiy","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1093\/acref\/9780192803511.013.0843"},{"journal-title":"Robust speech recognition via large-scale weak super-vision","year":"2022","author":"Radford","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2294"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref11","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2, NIPS\u201914, (Cambridge, MA, USA), p. 3104\u20133112, MIT Press","author":"Sutskever","year":"2014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"journal-title":"Layer normalization","year":"2016","author":"Ba","key":"ref15"},{"journal-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","year":"2022","author":"Dao","key":"ref16"},{"journal-title":"Flashattention-2: Faster attention with better parallelism and work partitioning","year":"2023","author":"Dao","key":"ref17"}],"event":{"name":"2025 International Conference on Electronics, Information, and Communication (ICEIC)","start":{"date-parts":[[2025,1,19]]},"location":"Osaka, Japan","end":{"date-parts":[[2025,1,22]]}},"container-title":["2025 International Conference on Electronics, Information, and Communication (ICEIC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10879455\/10879601\/10879650.pdf?arnumber=10879650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T20:01:12Z","timestamp":1740081672000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10879650\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,19]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/iceic64972.2025.10879650","relation":{},"subject":[],"published":{"date-parts":[[2025,1,19]]}}}