{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:52:02Z","timestamp":1774716722425,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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":["62306084"],"award-info":[{"award-number":["62306084"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2051"],"award-info":[{"award-number":["U23B2051"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen College Stability Support Plan","award":["GXWD20231128102243003"],"award-info":[{"award-number":["GXWD20231128102243003"]}]},{"name":"Shenzhen Science and Technology Program","award":["ZDSYS20230626091203008"],"award-info":[{"award-number":["ZDSYS20230626091203008"]}]},{"name":"Shenzhen Science and Technology Program","award":["KJZD20230923115113026"],"award-info":[{"award-number":["KJZD20230923115113026"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tpami.2025.3599479","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T18:47:32Z","timestamp":1755197252000},"page":"11817-11833","source":"Crossref","is-referenced-by-count":1,"title":["LR\n                    <i>Quant+<\/i>\n                    : A Unified and Learnable Framework to Post-Training Quantization for Transformer-Based Large Foundation Models"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3482-9012","authenticated-orcid":false,"given":"Jiaqi","family":"Zhao","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Zeng","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1758-3646","authenticated-orcid":false,"given":"Ming","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linxuan","family":"Han","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2286-6668","authenticated-orcid":false,"given":"Yuzhang","family":"Shang","sequence":"additional","affiliation":[{"name":"Illinois Institute of Technology, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1262-4174","authenticated-orcid":false,"given":"Miao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref6","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref8","first-page":"10 323","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Frantar"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref10","article-title":"Learned step size quantization","author":"Esser","year":"2019"},{"key":"ref11","article-title":"QuIP: 2-bit quantization of large language models with guarantees","author":"Chee","year":"2023"},{"key":"ref12","article-title":"QLoRA: Efficient finetuning of quantized LLMs","author":"Dettmers","year":"2023"},{"key":"ref13","article-title":"SPQR: A sparse-quantized representation for near-lossless LLM weight compression","author":"Dettmers","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.26"},{"key":"ref15","article-title":"OneBit: Towards extremely low-bit large language models","author":"Xu","year":"2024"},{"key":"ref16","article-title":"BitNet: Scaling 1-bit transformers for large language models","author":"Wang","year":"2023"},{"key":"ref17","first-page":"7197","article-title":"Up or down? Adaptive rounding for post-training quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nagel"},{"key":"ref18","first-page":"4466","article-title":"Accurate post training quantization with small calibration sets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hubara"},{"key":"ref19","first-page":"27 168","article-title":"ZeroQuant: Efficient and affordable post-training quantization for large-scale transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yao"},{"key":"ref20","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022"},{"key":"ref21","article-title":"Bloom: A 176B-parameter open-access multilingual language model","author":"Workshop","year":"2022"},{"key":"ref22","first-page":"38 087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref23","article-title":"OmniQuant: Omnidirectionally calibrated quantization for large language models","author":"Shao","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.102"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/164"},{"key":"ref26","article-title":"CBQ: Cross-block quantization for large language models","author":"Ding","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01580"},{"key":"ref28","first-page":"7474","article-title":"Rotated binary neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.122"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_12"},{"key":"ref31","article-title":"LRP-QViT: Mixed-precision vision transformer quantization via layer-wise relevance propagation","author":"Ranjan","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107289"},{"key":"ref33","article-title":"LLM. int8 (): 8-bit matrix multiplication for transformers at scale","author":"Dettmers","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"key":"ref35","article-title":"QuIP#: Even better LLM quantization with hadamard incoherence and lattice codebooks","author":"Tseng","year":"2024"},{"key":"ref36","first-page":"196","article-title":"Atom: Low-bit quantization for efficient and accurate LLM serving","volume-title":"Proc. Mach. Learn. Syst.","author":"Zhao"},{"key":"ref37","first-page":"17 402","article-title":"Outlier suppression: Pushing the limit of low-bit transformer language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref38","article-title":"FPTQ: Fine-grained post-training quantization for large language models","author":"Li","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3180"},{"key":"ref40","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s00591-010-0080-8"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1080\/00224065.1986.11979014"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547826"},{"key":"ref44","article-title":"LLaMa: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref45","article-title":"LLaMa 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref46","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref47","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref48","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02520"},{"key":"ref50","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref51","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref52","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075835"},{"issue":"1","key":"ref54","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref56","article-title":"Think you have solved question answering? Try ARC, the AI2 reasoning challenge","author":"Clark","year":"2018"},{"key":"ref57","article-title":"BoolQ: Exploring the surprising difficulty of natural yes\/no questions","author":"Clark","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref60","article-title":"A framework for few-shot language model evaluation","author":"Gao","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref64","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref68","first-page":"57730","article-title":"MM-Vet: Evaluating large multimodal models for integrated capabilities","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref69","first-page":"41","article-title":"Retrieval-based language models and applications","volume-title":"Proc. 61st Annu. Meeting Assoc. Comput. Linguistics","author":"Asai"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.225"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1035"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2006.888101"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11230086\/11125954.pdf?arnumber=11125954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:53:05Z","timestamp":1762455185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11125954\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":72,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3599479","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}