{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T22:24:46Z","timestamp":1769034286648,"version":"3.49.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402252,62536003"],"award-info":[{"award-number":["62402252,62536003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,14]]},"DOI":"10.1109\/cloudcom67567.2025.11331377","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:37:16Z","timestamp":1768941436000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["QER: Quantized Low-Rank Error Reconstructor for LLM Low-Bitwidth Quantization"],"prefix":"10.1109","author":[{"given":"Shoukai","family":"Xu","sequence":"first","affiliation":[{"name":"South China University of Technology,Guangzhou,China"}]},{"given":"Runhao","family":"Zeng","sequence":"additional","affiliation":[{"name":"SHENZHEN MSU-BIT UNIVERSITY,Shenzhen,China"}]},{"given":"Zhiyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"South China University of Technology,Guangzhou,China"}]},{"given":"Hao","family":"Huang","sequence":"additional","affiliation":[{"name":"South China University of Technology,Guangzhou,China"}]},{"given":"Qingfang","family":"Zheng","sequence":"additional","affiliation":[{"name":"PengCheng Laboratory,Shenzhen,China"}]},{"given":"Xiangyuan","family":"Lan","sequence":"additional","affiliation":[{"name":"PengCheng Laboratory,Shenzhen,China"}]},{"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"PengCheng Laboratory,Shenzhen,China"}]},{"given":"Mingkui","family":"Tan","sequence":"additional","affiliation":[{"name":"South China University of Technology,Guangzhou,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref2","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"vol. abs\/2302.13971"},{"key":"ref3","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3090167"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2025.3542324"},{"key":"ref6","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Awq: Activation-aware weight quantization for llm compression and accel-eration","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International Conference on Machine Learning","author":"Xiao"},{"key":"ref9","first-page":"30318","article-title":"Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Dettmers","year":"2022"},{"key":"ref10","article-title":"Omniquant: Omnidirectionally calibrated quan-tization for large language models","author":"Shao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Outlier suppression+: Accurate quantization of large language mod-els by equivalent and optimal shifting and scaling","author":"Wei","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.26"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i21.34385"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i21.34443"},{"key":"ref15","article-title":"QLLM: accu-rate and efficient low-bitwidth quantization for large language models","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Liu","year":"2024"},{"key":"ref16","article-title":"Qa-lora: Quantization-aware low-rank adaptation of large language models","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Xu","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.498"},{"key":"ref18","article-title":"Spinquant: LLM quantization with learned rotations","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"Liu","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2786"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.26"},{"key":"ref21","volume-title":"A framework for few-shot language model evaluation","author":"Gao","year":"2021"}],"event":{"name":"2025 lEEE International Conference on Cloud Computing Technology and Science (CloudCom)","location":"Shenzhen, China","start":{"date-parts":[[2025,11,14]]},"end":{"date-parts":[[2025,11,16]]}},"container-title":["2025 lEEE International Conference on Cloud Computing Technology and Science (CloudCom)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11330195\/11331311\/11331377.pdf?arnumber=11331377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:41:57Z","timestamp":1768981317000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11331377\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/cloudcom67567.2025.11331377","relation":{},"subject":[],"published":{"date-parts":[[2025,11,14]]}}}