{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T01:38:21Z","timestamp":1780450701747,"version":"3.54.1"},"reference-count":22,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/lca.2024.3363492","type":"journal-article","created":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T18:39:04Z","timestamp":1707331144000},"page":"37-40","source":"Crossref","is-referenced-by-count":6,"title":["eDKM: An Efficient and Accurate Train-Time Weight Clustering for Large Language Models"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0481-2682","authenticated-orcid":false,"given":"Minsik","family":"Cho","sequence":"first","affiliation":[{"name":"Apple, Cupertino, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2703-6674","authenticated-orcid":false,"given":"Keivan A.","family":"Vahid","sequence":"additional","affiliation":[{"name":"Apple, Cupertino, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5976-4095","authenticated-orcid":false,"given":"Qichen","family":"Fu","sequence":"additional","affiliation":[{"name":"Apple, Cupertino, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4533-6577","authenticated-orcid":false,"given":"Saurabh","family":"Adya","sequence":"additional","affiliation":[{"name":"Apple, Cupertino, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0991-1808","authenticated-orcid":false,"given":"Carlo C. Del","family":"Mundo","sequence":"additional","affiliation":[{"name":"Apple, Cupertino, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9606-3687","authenticated-orcid":false,"given":"Mohammad","family":"Rastegari","sequence":"additional","affiliation":[{"name":"Apple, Cupertino, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7838-1623","authenticated-orcid":false,"given":"Devang","family":"Naik","sequence":"additional","affiliation":[{"name":"Apple, Cupertino, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0451-0591","authenticated-orcid":false,"given":"Peter","family":"Zatloukal","sequence":"additional","affiliation":[{"name":"Apple, Cupertino, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref3","article-title":"DKM: Differentiable K-means clustering layer for neural network compression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cho"},{"key":"ref4","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dean"},{"key":"ref5","first-page":"18518","article-title":"HAWQ-V2: Hessian aware trace-weighted quantization of neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref6","article-title":"Training with quantization noise for extreme model compression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fan"},{"key":"ref7","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2023"},{"key":"ref8","article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Han"},{"key":"ref9","article-title":"AWQ: Activation-aware weight quantization for LLM compression and acceleration","author":"Lin","year":"2023"},{"key":"ref10","article-title":"LLM-QAT: Data-free quantization aware training for large language models","author":"Liu","year":"2023"},{"key":"ref11","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_36"},{"key":"ref13","article-title":"Lookahead: A far-sighted alternative of magnitude-based pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Park"},{"key":"ref14","article-title":"Model compression via distillation and quantization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Polino"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref16","article-title":"And the bit goes down: Revisiting the quantization of neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Stock"},{"key":"ref17","article-title":"Stanford alpaca: An instruction-following LLaMA model","author":"Taori","year":"2023"},{"key":"ref18","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref19","article-title":"Soft weight-sharing for neural network compression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ullrich"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref21","first-page":"5363","article-title":"Deep k-means: Re-training and parameter sharing with harder cluster assignments for compressing deep convolutions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref23","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref24","article-title":"Neural epitome search for architecture-agnostic network compression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10208\/10375809\/10423861.pdf?arnumber=10423861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T02:39:07Z","timestamp":1709865547000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10423861\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":22,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lca.2024.3363492","relation":{},"ISSN":["1556-6056","1556-6064","2473-2575"],"issn-type":[{"value":"1556-6056","type":"print"},{"value":"1556-6064","type":"electronic"},{"value":"2473-2575","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}