{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:06:43Z","timestamp":1767182803778,"version":"3.41.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T00:00:00Z","timestamp":1748131200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T00:00:00Z","timestamp":1748131200000},"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":[[2025,5,25]]},"DOI":"10.1109\/iscas56072.2025.11043916","type":"proceedings-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T17:42:19Z","timestamp":1751046139000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["XNC: XOR and NOT-Based Lossless Compression for Optimizing Unquantized Embedding Layers in Large Language Models"],"prefix":"10.1109","author":[{"given":"Junghyeok","family":"Lee","sequence":"first","affiliation":[{"name":"Seoul National University of Science and Technology,Department of Electrical and Information Engineering and Research Center for Electrical and Information Technology,Seoul,Korea"}]},{"given":"Jihoon","family":"Jang","sequence":"additional","affiliation":[{"name":"Seoul National University of Science and Technology,Department of Electrical and Information Engineering and Research Center for Electrical and Information Technology,Seoul,Korea"}]},{"given":"Hyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University of Science and Technology,Department of Electrical and Information Engineering and Research Center for Electrical and Information Technology,Seoul,Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3348662"},{"year":"2024","key":"ref2","article-title":"iphone 16 pro max"},{"year":"2024","key":"ref3","article-title":"Galaxy s24 ultra"},{"article-title":"The llama 3 herd of models","year":"2024","author":"Dubey","key":"ref4"},{"article-title":"Gemma 2: Improving open language models at a practical size","year":"2024","author":"Team","key":"ref5"},{"article-title":"Qwen2 technical report","year":"2024","author":"Yang","key":"ref6"},{"article-title":"Phi-3 technical report: A highly capable language model locally on your phone","year":"2024","author":"Abdin","key":"ref7"},{"key":"ref8","article-title":"Smollm-blazingly fast and remarkably powerful","volume-title":"Hugging Face Blog","author":"Allal","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3108776"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-024-01442-8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/474"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3410231"},{"article-title":"Rethinking the value of network pruning","year":"2018","author":"Liu","key":"ref13"},{"article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","year":"2022","author":"Frantar","key":"ref14"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref15"},{"article-title":"Qserve: W4a8kv4 quantization and system co-design for efficient llm serving","year":"2024","author":"Lin","key":"ref16"},{"article-title":"Quarot: Outlier-free 4-bit inference in rotated llms","year":"2024","author":"Ashkboos","key":"ref17"},{"key":"ref18","first-page":"87","article-title":"Awq: Activation-aware weight quanti-zation for on-device llm compression and acceleration","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Lin"},{"article-title":"Spinquant\u2013llm quantization with learned rotations","year":"2024","author":"Liu","key":"ref19"},{"key":"ref20","first-page":"377","article-title":"Base-delta-immediate compression: Practical data compression for on-chip caches","volume-title":"Proceedings of the 21st international conference on Parallel architectures and compilation techniques","author":"Pekhimenko"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001172"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/e17-2025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00085"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1028176.1006719"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.101"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2017.015073"},{"key":"ref27","article-title":"Smolvlm-small yet mighty vision language model","volume-title":"Hugging Face Blog","author":"Andres","year":"2024"},{"article-title":"Qwen2.5-vl","year":"2025","author":"Team","key":"ref28"}],"event":{"name":"2025 IEEE International Symposium on Circuits and Systems (ISCAS)","start":{"date-parts":[[2025,5,25]]},"location":"London, United Kingdom","end":{"date-parts":[[2025,5,28]]}},"container-title":["2025 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11043142\/11042930\/11043916.pdf?arnumber=11043916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T06:20:39Z","timestamp":1751091639000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11043916\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,25]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iscas56072.2025.11043916","relation":{},"subject":[],"published":{"date-parts":[[2025,5,25]]}}}