Article(id=1325493569858974164, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1325493569112388051, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202550788, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1761840000000, receivedDateStr=2025-10-31, revisedDate=1765987200000, revisedDateStr=2025-12-18, acceptedDate=null, acceptedDateStr=null, onlineDate=1793951893534, onlineDateStr=2026-11-06, pubDate=1769875200000, pubDateStr=2026-02-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793951893534, onlineIssueDateStr=2026-11-06, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793951893534, creator=13701087609, updateTime=1793951893534, updator=13701087609, issue=Issue{id=1325493569112388051, tenantId=1146029695717560320, journalId=1324759914146529478, year='2026', volume='63', issue='2', pageStart='275', pageEnd='538', issueExtLink='null', onlineDate='null', pubDate='1769875200000', pubDateStr='2026-02-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793951893355, creator='13701087609', updateTime=1793952511329, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1325496161167090054, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1325493569112388051, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1325496161167090055, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1325493569112388051, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=276, endPage=293, ext={EN=ArticleExt(id=1325493570127409622, articleId=1325493569858974164, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=History, Present, and Future of Low-Bit Quantization for Large Language Model: A Case Study on Complex-Domain Quantization, columnId=1325493570068689365, journalTitle=Journal of Computer Research and Development, columnName=Research Highlights, runingTitle=null, highlight=null, articleAbstract=
With the exponential growth in the parameter scale of large language models (LLMs), model deployment and inference face severe challenges in terms of memory and computational resources. Quantization, as a core compression technique, significantly reduces storage requirements and computational overhead by lowering the numerical precision of weights and activations. We first review the development of quantization techniques, from classic Int8/4 methods to cutting-edge extreme-low bit algorithms. Then we summarize the technical characteristics and performance evolution of typical methods, identifying a key challenge: traditional real-domain quantization is limited by discretization errors at extreme-low bitrates, making it difficult to break its performance ceiling. To address this limitation, we systematically review the complex-domain quantization series of work. This series introduces a quantization paradigm based on the complex domain, which significantly expands the model’s expressive space by utilizing amplitude and phase as two degrees of freedom in the parameter representation. Moreover, drawing on the classic paradigm in signal processing where stable representations are achieved by applying the Fourier transform and low-pass filtering to time-domain signals, we further propose a technical path that proceeds from real-valued models through complex-domain transformation and complex-domain quantization, ultimately achieving multiplier-free stable inference. Experimental results demonstrate that iFairy outperforms existing extreme-low-bit methods on multiple benchmark datasets and effectively breaks the real-domain performance ceiling. This showcases the potential value of complex-domain quantization in achieving both efficient modeling and performance preservation. Through a systematic analysis of quantization’s evolution and the case study on complex-domain quantization, we reveal development patterns and future trends, providing a reference for the theoretical research and engineering implementation of efficient LLMs.
, authors=Peizhuang Cong
1, Feiyu Wang
1, Guo’an Wang
1, Yanshu Wang
1, Ce Zheng
2, Tong Yang
1, *, authorsList=Peizhuang Cong, Feiyu Wang, Guo’an Wang, Yanshu Wang, Ce Zheng, Tong Yang, authorCompany=null, correspAuthors=Tong Yang, authorNote=
born in 1994. PhD, postdoctoral researcher. Member of CCF. His main research interests include LLM quantization and inference optimization, and new architecture of networking
born in 1999. PhD candidate. His main research interests include LLM quantization technology and inference acceleration
born in 2004. Master candidate. His main research interests include edge intelligence and model compression algorithms
born in 1994. PhD, postdoctoral researcher. His main research interests include high-performance network measurement algorithms, distributed machine learning systems, and LLM quantization and inference acceleration
born in 1994. PhD candidate. Her main research interests include network measurement algorithms and LLMs
born in 1982. PhD, associate professor, PhD supervisor. His main research interests include LLM, network measurement, and new data structures
, correspAuthorsNote=null, copyrightStatement=Copyright © 2026 Journal of Computer Research and Development. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1325493575370289654, articleId=1325493569858974164, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=大语言模型低比特量化的历史、现状和未来:以复域量化为例, columnId=1325493570202907095, journalTitle=计算机研究与发展, columnName=前沿亮点, runingTitle=null, highlight=null, articleAbstract=
随着大语言模型(large language model,LLM)参数规模的指数级增长,模型部署和推理面临着严峻的内存和计算资源挑战。量化技术作为模型压缩的核心方法,通过降低权重和激活值的数值精度,显著减少了模型的存储需求和计算开销。首先回顾了量化技术的发展历程,从经典的Int8/4量化方法到前沿的超低比特量化算法,总结了典型方法的技术特征与性能演进规律,指出传统实数域量化在极低比特条件下存在受限于离散化误差的挑战,难以突破性能上限。为此,进而系统性地梳理了复域量化系列工作。该系列工作提出了基于复数域的量化范式,通过在参数表示中引入幅度与相位2个自由度,显著扩展了模型的表达空间;此外,类比信号处理中通过将时域信号进行傅里叶变换与低通滤波实现稳定表示的经典范式,进一步提出了由实数模型经复域变换与复域量化,达成了无乘法稳定推理的技术路线。实验结果表明,该方案在多个基准数据集上优于现有超低比特量化方法,有效突破了实数域模型的性能天花板,展现出复域量化在高效建模与性能保持方面的潜在价值。总体而言,通过对量化技术演进及复域量化系列研究的系统分析,旨在揭示超低比特量化的发展规律与未来趋势,为高效大模型的理论研究与工程实现提供参考。
, authors=丛培壮
1, 王飞宇
1, 王国安
1, 王砚舒
1, 郑策
2, 杨仝
1, *, authorsList=丛培壮, 王飞宇, 王国安, 王砚舒, 郑策, 杨仝, authorCompany=null, correspAuthors=杨仝, authorNote=
 |
1994年生。博士,博士后研究员。CCF会员。主要研究方向为大语言模型量化与推理优化、新型网络架构 |
 |
1999年生。博士研究生。主要研究方向为大语言模型量化技术、推理加速 |
 |
2004年生。硕士研究生。主要研究方向为端侧智能、模型压缩算法 |
 |
1994年生。博士,博士后研究员。主要研究方向为高性能网络测量算法、分布式机器学习系统、大语言模型量化与推理加速 |
 |
1994年生。博士研究生。主要研究方向为网络测量算法、大语言模型 |
 |
1982年生。博士,副教授,博士生导师。主要研究方向为大语言模型、网络测量、新型数据结构 |
, correspAuthorsNote=
, copyrightStatement=版权所有 © 2026 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=iq6YKT48wtPCvso5eKmVLA==, magXml=yJLtjptMyl2P4Wb7D4PQFQ==, pdfUrl=null, pdf=fxOzQWq2QN+ES4aJGSbaDQ==, pdfFileSize=2057357, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=ldn+4HE2y+6xLqghdUPA0Q==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=yrxDM4jUSW2ju9J+q2w8SQ==, mapNumber=null, fund=null)}, authors=[Author(id=1325493577450664446, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=congpeizhuang@pku.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325493577551327744, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, authorId=1325493577450664446, language=EN, stringName=Peizhuang Cong, firstName=Peizhuang, middleName=null, lastName=Cong, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1State Key Laboratory of Multimedia Information Processing (Peking University), Beijing 100871, bio={"content":"
born in 1994. PhD, postdoctoral researcher. Member of CCF. His main research interests include LLM quantization and inference optimization, and new architecture of networking
"}, bioImg=null, bioContent=
born in 1994. PhD, postdoctoral researcher. Member of CCF. His main research interests include LLM quantization and inference optimization, and new architecture of networking
, aboutCorrespAuthor=null), CN=AuthorExt(id=1325493577656185345, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, authorId=1325493577450664446, language=CN, stringName=丛培壮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1多媒体信息处理全国重点实验室(北京大学) 北京 100871, bio={"img":"15JXvScX3mMxOMGA5M0ePg==","content":"
1994年生。博士,博士后研究员。CCF会员。主要研究方向为大语言模型量化与推理优化、新型网络架构
"}, bioImg=15JXvScX3mMxOMGA5M0ePg==, bioContent=
1994年生。博士,博士后研究员。CCF会员。主要研究方向为大语言模型量化与推理优化、新型网络架构
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325493575621947895, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, xref=1, ext=[AuthorCompanyExt(id=1325493575630336504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493575621947895, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Laboratory of Multimedia Information Processing (Peking University), Beijing 100871), AuthorCompanyExt(id=1325493575638725113, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493575621947895, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1多媒体信息处理全国重点实验室(北京大学) 北京 100871)])]), Author(id=1325493577744265731, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325493577823957509, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, authorId=1325493577744265731, language=EN, stringName=Feiyu Wang, firstName=Feiyu, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1State Key Laboratory of Multimedia Information Processing (Peking University), Beijing 100871, bio={"content":"
born in 1999. PhD candidate. His main research interests include LLM quantization technology and inference acceleration
"}, bioImg=null, bioContent=
born in 1999. PhD candidate. His main research interests include LLM quantization technology and inference acceleration
, aboutCorrespAuthor=null), CN=AuthorExt(id=1325493577928815110, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, authorId=1325493577744265731, language=CN, stringName=王飞宇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1多媒体信息处理全国重点实验室(北京大学) 北京 100871, bio={"img":"ldGCE54Bzjhz1ZP/hicG3A==","content":"
1999年生。博士研究生。主要研究方向为大语言模型量化技术、推理加速
"}, bioImg=ldGCE54Bzjhz1ZP/hicG3A==, bioContent=
1999年生。博士研究生。主要研究方向为大语言模型量化技术、推理加速
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325493575621947895, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, xref=1, ext=[AuthorCompanyExt(id=1325493575630336504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493575621947895, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Laboratory of Multimedia Information Processing (Peking University), Beijing 100871), AuthorCompanyExt(id=1325493575638725113, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493575621947895, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1多媒体信息处理全国重点实验室(北京大学) 北京 100871)])]), Author(id=1325493577987535368, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325493578067227146, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, authorId=1325493577987535368, language=EN, stringName=Guo’an Wang, firstName=Guo’an, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1State Key Laboratory of Multimedia Information Processing (Peking University), Beijing 100871, bio={"content":"
born in 2004. Master candidate. His main research interests include edge intelligence and model compression algorithms
"}, bioImg=null, bioContent=
born in 2004. Master candidate. His main research interests include edge intelligence and model compression algorithms
, aboutCorrespAuthor=null), CN=AuthorExt(id=1325493578138530315, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, authorId=1325493577987535368, language=CN, stringName=王国安, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1多媒体信息处理全国重点实验室(北京大学) 北京 100871, bio={"img":"tcCXxn0h+GYDKN3l0QJWJg==","content":"
2004年生。硕士研究生。主要研究方向为端侧智能、模型压缩算法
"}, bioImg=tcCXxn0h+GYDKN3l0QJWJg==, bioContent=
2004年生。硕士研究生。主要研究方向为端侧智能、模型压缩算法
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325493575621947895, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, xref=1, ext=[AuthorCompanyExt(id=1325493575630336504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493575621947895, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Laboratory of Multimedia Information Processing (Peking University), Beijing 100871), AuthorCompanyExt(id=1325493575638725113, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493575621947895, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1多媒体信息处理全国重点实验室(北京大学) 北京 100871)])]), Author(id=1325493578209833485, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325493578293719567, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, authorId=1325493578209833485, language=EN, stringName=Yanshu Wang, firstName=Yanshu, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1State Key Laboratory of Multimedia Information Processing (Peking University), Beijing 100871, bio={"content":"
born in 1994. PhD, postdoctoral researcher. His main research interests include high-performance network measurement algorithms, distributed machine learning systems, and LLM quantization and inference acceleration
"}, bioImg=null, bioContent=
born in 1994. PhD, postdoctoral researcher. His main research interests include high-performance network measurement algorithms, distributed machine learning systems, and LLM quantization and inference acceleration
, aboutCorrespAuthor=null), CN=AuthorExt(id=1325493578398577168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, authorId=1325493578209833485, language=CN, stringName=王砚舒, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1多媒体信息处理全国重点实验室(北京大学) 北京 100871, bio={"img":"FCymz4EoHzZRnIyA49H6Cw==","content":"
1994年生。博士,博士后研究员。主要研究方向为高性能网络测量算法、分布式机器学习系统、大语言模型量化与推理加速
"}, bioImg=FCymz4EoHzZRnIyA49H6Cw==, bioContent=
1994年生。博士,博士后研究员。主要研究方向为高性能网络测量算法、分布式机器学习系统、大语言模型量化与推理加速
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325493575621947895, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, xref=1, ext=[AuthorCompanyExt(id=1325493575630336504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493575621947895, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Laboratory of Multimedia Information Processing (Peking University), Beijing 100871), AuthorCompanyExt(id=1325493575638725113, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493575621947895, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1多媒体信息处理全国重点实验室(北京大学) 北京 100871)])]), Author(id=1325493578490851858, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325493578574737940, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, authorId=1325493578490851858, language=EN, stringName=Ce Zheng, firstName=Ce, middleName=null, lastName=Zheng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2School of Cyber Science and Technology, Beihang University, Beijing 100191, bio={"content":"
born in 1994. PhD candidate. Her main research interests include network measurement algorithms and LLMs
"}, bioImg=null, bioContent=
born in 1994. PhD candidate. Her main research interests include network measurement algorithms and LLMs
, aboutCorrespAuthor=null), CN=AuthorExt(id=1325493578646041109, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, authorId=1325493578490851858, language=CN, stringName=郑策, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2北京航空航天大学网络空间安全学院 北京 100191, bio={"img":"wjN+IVLNoPYSLV0bWtsv9Q==","content":"
1994年生。博士研究生。主要研究方向为网络测量算法、大语言模型
"}, bioImg=wjN+IVLNoPYSLV0bWtsv9Q==, bioContent=
1994年生。博士研究生。主要研究方向为网络测量算法、大语言模型
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325493577320641018, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, xref=2, ext=[AuthorCompanyExt(id=1325493577329029627, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493577320641018, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2School of Cyber Science and Technology, Beihang University, Beijing 100191), AuthorCompanyExt(id=1325493577337418236, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493577320641018, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2北京航空航天大学网络空间安全学院 北京 100191)])]), Author(id=1325493578763481623, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yangtong@pku.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1325493578847367705, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, authorId=1325493578763481623, language=EN, stringName=Tong Yang, firstName=Tong, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, *, address=
1State Key Laboratory of Multimedia Information Processing (Peking University), Beijing 100871, bio={"content":"
born in 1982. PhD, associate professor, PhD supervisor. His main research interests include LLM, network measurement, and new data structures
"}, bioImg=null, bioContent=
born in 1982. PhD, associate professor, PhD supervisor. His main research interests include LLM, network measurement, and new data structures
, aboutCorrespAuthor=null), CN=AuthorExt(id=1325493578906087962, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, authorId=1325493578763481623, language=CN, stringName=杨仝, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, *, address=
1多媒体信息处理全国重点实验室(北京大学) 北京 100871, bio={"img":"bq8GmYiOn7rDDPNt4bOv3Q==","content":"
1982年生。博士,副教授,博士生导师。主要研究方向为大语言模型、网络测量、新型数据结构
"}, bioImg=bq8GmYiOn7rDDPNt4bOv3Q==, bioContent=
1982年生。博士,副教授,博士生导师。主要研究方向为大语言模型、网络测量、新型数据结构
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325493575621947895, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, xref=1, ext=[AuthorCompanyExt(id=1325493575630336504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493575621947895, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Laboratory of Multimedia Information Processing (Peking University), Beijing 100871), AuthorCompanyExt(id=1325493575638725113, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493575621947895, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1多媒体信息处理全国重点实验室(北京大学) 北京 100871)])])], keywords=[Keyword(id=1325493578998362651, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, orderNo=1, keyword=large language model), Keyword(id=1325493579057082908, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, orderNo=2, keyword=model quantization), Keyword(id=1325493579136774685, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, orderNo=3, keyword=low-bit quantization), Keyword(id=1325493579208077854, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, orderNo=4, keyword=model compression), Keyword(id=1325493579279381023, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, orderNo=5, keyword=complex valued model), Keyword(id=1325493579359072800, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, orderNo=1, keyword=大语言模型), Keyword(id=1325493579417793057, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, orderNo=2, keyword=模型量化), Keyword(id=1325493579484901922, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, orderNo=3, keyword=低比特量化), Keyword(id=1325493579564593699, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, orderNo=4, keyword=模型压缩), Keyword(id=1325493579627508260, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, orderNo=5, keyword=复数模型)], refs=[Reference(id=1325493583318495806, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=陈慧敏, 刘知远, 孙茂松. 大语言模型时代的社会机遇与挑战[J]. 计算机研究与发展, 2024, 61(5): 1094−1103, articleTitle=null, refAbstract=null), Reference(id=1325493583385604671, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Huimin, Liu Zhiyuan, Sun Maosong. The social opportunities and challenges in the era of large language models[J]. Journal of Computer Research and Development, 2024, 61(5): 1094−1103, articleTitle=null, refAbstract=null), Reference(id=1325493583448519232, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Kimi Team. Kimi k2: Qpen agentic intelligence[J]. arXiv preprint arXiv: 2507.20534, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493583528211009, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Jacob B, Kligys S, Chen B, et al. Quantization and training of neural networks for efficient integer-arithmetic-only inference[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2018: 2704−2713, articleTitle=null, refAbstract=null), Reference(id=1325493583595319874, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=TensorFlow Lite Team. Tensorflow lite: An open source deep learning framework for on-device inference[EB/OL]. Google AI Blog, 2017[2025-10-01]. https://blog.tensorflow.org/2017/11/announcing-tensorflow-lite.html, articleTitle=null, refAbstract=null), Reference(id=1325493583654040131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=NVIDIA. TensorRT Developer Guide[M/OL]. NVIDIA Corporation, 2018[2025-10-01]. https://docs.nvidia.com/deeplearning/tensorrt/, articleTitle=null, refAbstract=null), Reference(id=1325493583733731908, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Frantar E, Ashkboos S, Hoefler T, et. al. GPTQ: Accurate post-training quantization for generative pre-trained transformers[C]//Proc of the 11th Int Conf on Learning Representations (ICLR). New York: Curran Associates, 2023, articleTitle=null, refAbstract=null), Reference(id=1325493583805035077, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Ji, Tang Jiaming, Tang Haotian, et al. AWQ: Activation-aware weight quantization for LLM compression and acceleration[C]//Proc of Machine Learning and Systems 6 (MLSys) New York: Curran Associates, 2024, 6: 87−100, articleTitle=null, refAbstract=null), Reference(id=1325493583872143942, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Xiao Guangxuan, Lin Ji, Seznec M, Wu H, et al. SmoothQuant: Accurate and efficient post-training quantization for large language models[C]//Proc of the 40th Int Conf on Machine Learning (ICML). New York: ACM, 2023: 38087−38099, articleTitle=null, refAbstract=null), Reference(id=1325493583935058503, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Hongyu, Ma Shuming, Dong Li, et al. BitNet: Scaling 1-bit transformers for large language models[J]. arXiv preprint arXiv: 2310.11453, 2023, articleTitle=null, refAbstract=null), Reference(id=1325493584010555976, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Yuzhuang, Han Xu, Yang Zonghan, et al. OneBit: Towards extremely low-bit large language models[C]//Proc of the 38th Int Conf on Neural Information Processing Systems (NeurIPS). New York: Curran Associates, 2024, 37: 66357−66382, articleTitle=null, refAbstract=null), Reference(id=1325493584081859145, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Wei, Liu Yangdong, Qin Haotong, et al. BiLLM: Pushing the limit of post-training quantization for LLMs[C]//Proc of the 41st Int Conf on Machine Learning (ICML). New York: PMLR, 2024: 19889−19908, articleTitle=null, refAbstract=null), Reference(id=1325493584144773706, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Ma Shuming, Wang Hongyu, Ma Lingxiao, et al. The era of 1-bit LLMs: All large language models are in 1.58 bits[J]. arXiv preprint arXiv: 2402.17764, 2024, articleTitle=null, refAbstract=null), Reference(id=1325493584216076875, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Fengfu, Liu Bin, Wang Xiaoxing. Ternary weight networks[J]. arXiv Preprint, arXiv: 1605.04711, 2016, articleTitle=null, refAbstract=null), Reference(id=1325493584278991436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Feng, Gong Ruihao, Yu Fengwei, et al. Towards unified int8 training for convolutional neural network[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2020: 1969−1979, articleTitle=null, refAbstract=null), Reference(id=1325493584350294605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Hoffmann J, Borgeaud S, Mensch A, et al. Training compute-optimal large language models[C]//Proc of the 36th Int Conf on Neural Information Processing Systems (NeurIPS). New York: Curran Associates, 2022: 30016−30030, articleTitle=null, refAbstract=null), Reference(id=1325493584413209166, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Trabelsi C, Bilaniuk O, Zhang Y, et al. Deep complex networks[C]//Proc of the 6th Int Conf on Learning Representations (ICLR). New York: Curran Associates, 2018: 3570−3601, articleTitle=null, refAbstract=null), Reference(id=1325493584480318031, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Feiyu, Wang Guoan, Zhang Yihao, et al. iFairy: The first 2-bit complex LLM with all parameters in {±1, ±i}[J]. arXiv preprint arXiv: 2508.05571, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493584543232592, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Feiyu, Tan Xinyu, Huang Bokai, et al. Fairy2i: Training complex LLMs from real LLMs with all parameters in {±1, ±i}[J]. arXiv preprint arXiv: 2512.02901, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493584606147153, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Dettmers T, Lewis M, Belkada Y, et al. GPT3.int8(): 8-bit matrix multiplication for transformers at scale[C]//Proc of the 36th Int Conf on Neural Information Processing Systems (NeurIPS). New York: Curran Associates, 2022, 35: 30318–30332, articleTitle=null, refAbstract=null), Reference(id=1325493586283868754, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Banner R, Nahshan Y, Hoffer E, et. al. Post-training 4-bit quantization of convolutional networks for rapid-deployment[C]//Proc of the 33rd Int Conf on Neural Information Processing Systems (NeurIPS). New York: Curran Associates, 2019: 1149–1159, articleTitle=null, refAbstract=null), Reference(id=1325493586359366227, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Yao Zhewei, Yazdani Aminabadi R, Zhang Minjia, et al. ZeroQuant: Efficient and affordable post-training quantization for large-scale transformers[C]//Proc of the 36th Int Conf on Neural Information Processing Systems (NeurIPS). New York: Curran Associates, 2022, 35: 27168−27183, articleTitle=null, refAbstract=null), Reference(id=1325493586434863700, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Chee J, Cai Y, Kuleshov V, et al. QuIP: 2-bit quantization of large language models with guarantees[C]//Proc of the 37th Int Conf on Neural Information Processing Systems (NeurIPS). New York: Curran Associates, 2023, 36: 4396−4429, articleTitle=null, refAbstract=null), Reference(id=1325493586631995989, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Tseng A, Chee J, Sun Q, et al. QuIP# even better LLM quantization with hadamard incoherence and lattice codebooks[C]//Proc of the 41st Int Conf on Machine Learning (ICML). New York: ACM, 2024: 48630−48656, articleTitle=null, refAbstract=null), Reference(id=1325493586745242198, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Tseng A, Sun Q, Hou D, et al. QTIP: Quantization with trellises and incoherence processing[C]//Proc of the 38th Int Conf on Neural Information Processing Systems (NeurIPS). New York: Curran Associates, 2024: 59597−59620, articleTitle=null, refAbstract=null), Reference(id=1325493586841711191, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Tseng A, Sun Z, De Sa C. Model-preserving adaptive rounding[J]. arXiv preprint arXiv: 2505.22988, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493586925597272, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Shuchang, Wu Yuxin, Ni Zekun, et al. DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients[J]. arXiv preprint arXiv: 1606.06160, 2016, articleTitle=null, refAbstract=null), Reference(id=1325493586992706137, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Dong Zhen, Yao Zhewei, Gholami A, et al. HAWQ: Hessian aware quantization of neural networks with mixed-precision[C]//Proc of the IEEE/CVF Int Conf on Computer Vision (CVPR). Piscataway, NJ: IEEE, 2019: 293–302, articleTitle=null, refAbstract=null), Reference(id=1325493587084980826, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Esser S K, McKinstry J L, Bablani D, et al. Learned step size quantization[C]//Proc of the 8th Int Conf on Learning Representations (ICLR). New York: Curran Associates, 2020: 6910–6921, articleTitle=null, refAbstract=null), Reference(id=1325493587173061211, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Bhalgat Y, Lee J, Nagel M, et al. LSQ+: Improving low-bit quantization through learnable offsets and better initialization[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition Workshops (CVPR workshop). Piscataway, NJ: IEEE, 2020: 696−697, articleTitle=null, refAbstract=null), Reference(id=1325493587244364380, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Shen Sheng, Dong Zhen, Ye Jiayu, et al. Q-BERT: Hessian based ultra low precision quantization of BERT[C]//Proc of the AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2020: 8815−8821, articleTitle=null, refAbstract=null), Reference(id=1325493587315667549, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Frantar E, Alistarh D. Optimal brain compression: A framework for accurate post-training quantization and pruning[C]//Proc of the 36th Conf on Neural Information Processing Systems (NeurIPS). New York: Curran Associates, 2022, 35: 4475−4488, articleTitle=null, refAbstract=null), Reference(id=1325493587378582110, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Ashkboos S, Mohtashami A, Croci M L, et al. QuaRot: Outlier-free 4-bit inference in rotated LLMs[C]//Proc of the 38th Conf on Neural Information Processing Systems (NeurIPS). New York: Curran Associates, 2024, articleTitle=null, refAbstract=null), Reference(id=1325493587462468191, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Frantar E, Alistarh D. Sparsegpt: Massive language models can be accurately pruned in one-shot[C]//Proc of the 40th Int Conf on Machine Learning (ICML). New York: PMLR, 2023: 10323–10337, articleTitle=null, refAbstract=null), Reference(id=1325493587533771360, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Courbariaux M, Bengio Y, David J P. BinaryConnect: Training deep neural networks with binary weights during propagations[C]//Proc of the Advances in Neural Information Processing Systems (NeurIPS). New York: Curran Associates, 2015: 3123–3131, articleTitle=null, refAbstract=null), Reference(id=1325493587600880225, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Rastegari M, Ordonez V, Redmon J, et al. XNOR-Net: ImageNet classification using binary convolutional neural networks[C]//Proc of the of European Conf on Computer Vision (ECCV). Berlin: Springer, 2016: 525–542, articleTitle=null, refAbstract=null), Reference(id=1325493587693154914, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu T, Gupta G, Gopalswamy K, et al. Collage: Light-weight low-precision strategy for LLM training[C]//Proc of the 41st Int Conf on Machine Learning (ICML). New York: ACM, 2024: 57459−57479, articleTitle=null, refAbstract=null), Reference(id=1325493587760263779, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Kumar T, Ankner Z, Spector B F, et al. Scaling laws for precision[C]//Proc of the 13th Int Conf on Learning Representations (ICLR). New York: Curran Associates, 2025: 71833−71864, articleTitle=null, refAbstract=null), Reference(id=1325493587827372644, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Ji Jiaming, Wang Kaile, Qiu Tianyi, et al. Language models resist alignment: Evidence from data compression[C]//Proc of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL). Stroudsburg, PA: ACL, 2025: 23411−23432, articleTitle=null, refAbstract=null), Reference(id=1325493587902870117, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Dettmers T, Zettlemoyer L. The case for 4-bit precision: k-bit inference scaling laws[C]//Proc of the 11th Int Conf on Machine Learning (ICML). New York: PMLR, 2023: 7750−7774, articleTitle=null, refAbstract=null), Reference(id=1325493587965784678, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Zechun, Zhao Changsheng, Huang Hanxian, et al. ParetoQ: Scaling laws in extremely low-bit llm quantization[C]//Proc of the 39th Int Conf on Neural Information Processing Systems (NeurIPS). New York: Curran Associates, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493588024504935, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Dremov A, Grangier D, Katharopoulos A, et al. Compute-optimal quantization-aware Training[J]. arXiv preprint arXiv: 2509.22935, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493588091613800, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yuhang, Panda P. TesseraQ: Ultra low-bit LLM post-training quantization with block reconstruction[J]. arXiv preprint arXiv: 2410.19103, 2024, articleTitle=null, refAbstract=null), Reference(id=1325493588154528361, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Jiaqi, Zhang Miao, Wang Ming, et al. PTQ 1.61: Push the real limit of extremely low-bit post-training quantization methods for large language models[J]. arXiv preprint arXiv: 2502.13179, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493588234220138, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yifei, Wen Jichen, Wang Yang, et. al. VPTQ: Extreme low-bit vector post-training quantization for large language models[C]//Proc of the 2024 Conf on Empirical Methods in Natural Language Processing (EMNLP). Stroudsburg, PA: ACL, 2024: 8181−8196, articleTitle=null, refAbstract=null), Reference(id=1325493588318106219, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Zhaojing, Li Xunchao, Li Minghao, et al. CCQ: Convolutional code for extreme low-bit quantization in LLMs[J]. arXiv preprint arXiv: 2507.07145, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493588397797996, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Gu Hao, Li Lujun, Wang Zheyu et al. BTC-LLM: Efficient sub−1-bit LLM quantization via learnable transformation and binary codebook[J]. arXiv preprint arXiv: 2506.12040, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493588544598638, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Hongyu, Ma Shuming, Wei Furu. Bitnet v2: Native 4-bit activations with hadamard transformation for 1-bit LLMs[J]. arXiv preprint arXiv: 2504.18415, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493588607513199, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee B, Kim D, You Y, et al. LittleBit: Ultra low-bit quantization via latent factorization[C]//Proc of the 39th Conf on Neural Information Processing Systems (NeurIPS). New York: Curran Associates, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493588683010672, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Hong, Wu Decheng, Cen Rui, et al. Tequila: Trapping-free ternary quantization for large language models[J]. arXiv preprint arXiv: 2509.23809, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493588745925233, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Tran B H. Ultra-efficient and effective large language models with Multi-Boolean architectures[C]//Proc of the ICML 2025 Workshop on Machine Learning for Wireless Communication and Networks (ML4Wireless). New York: PMLR, 2025: 1–31, articleTitle=null, refAbstract=null), Reference(id=1325493588804645491, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Du Dayou, Zhang Yijia, Cao Shijie, et al. BitDistiller: Unleashing the potential of sub−4-bit LLMs via self-distillation[C]//Proc of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL). Stroudsburg, PA, ACL, 2024: 102–116, articleTitle=null, refAbstract=null), Reference(id=1325493588888531572, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Xun, Huang Shaohan, Wang Wenhui, et al. BitNet Distillation[J]. arXiv preprint arXiv: 2510.13998, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493588951446133, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Dong Peijie, Li Lujun, Zhong Yuedong, et al. STBLLM: Breaking the 1-bit barrier with structured binary LLMs[C]//Proc of the 13th Int Conf on Learning Representations (ICLR). New York: Curran Associates, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493589031137910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Yan Xianlong, Zhang Tianao, Li Zhiting, et al. Progressive binarization with semi-structured pruning for LLMs[J]. arXiv preprint arXiv: 2502.01705, 2025, articleTitle=null, refAbstract=null), Reference(id=1325493589094052471, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Dehghankar M, Erfanian M, Asudeh A. An efficient matrix multiplication algorithm for accelerating inference in binary and ternary neural networks[C]//Proc of the 42nd Int Conf on Machine Learning (ICML). New York: PMLR, 2025: 12969−12986, articleTitle=null, refAbstract=null), Reference(id=1325493590788551288, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Lei, Ma Lingxiao, Cao Shijie, et al. Ladder: Enabling efficient low-precision deep learning computing through hardware-aware tensor transformation[C]//Proc of the 18th USENIX Symp on Operating Systems Design and Implementation (OSDI). Berkeley, CA: USENIX Association, 2024: 307−323, articleTitle=null, refAbstract=null), Reference(id=1325493590872437369, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Guoyu, Ye Shengyu, Chen Chunyun, et al. LUT-DLA: Lookup table as efficient extreme low-bit deep learning accelerator[C]//Proc of 2025 IEEE Int Symp on High Performance Computer Architecture (HPCA). Piscataway, NJ: IEEE, 2025: 671−684, articleTitle=null, refAbstract=null), Reference(id=1325493590960517754, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=Wei Jianyu, Cao Shijie, Cao Ting, et al. T-MAC: CPU renaissance via table lookup for low-bit LLM deployment on edge[C]//Proc of the 20th European Conf on Computer Systems (Eurosys). New York: ACM, 2025: 278−292, articleTitle=null, refAbstract=null), Reference(id=1325493591077958267, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Mo Zhiwen, Wang Lei, Wei Jianyu, et al. LUT-TensorCore: A software-hardware co-design for LUT-base low-bit LLM inference[C]//Proc of the 52nd Annual Int Symp on Computer Architecture (ISCA). Piscataway, NJ: IEEE, 2025: 514−528, articleTitle=null, refAbstract=null), Reference(id=1325493591379948156, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Ahmed S, Al Arafat A, Najafi D, et al. Deepcompress-vit: Rethinking model compression to enhance efficiency of vision transformers at the edge[C]//Proc of the Computer Vision and Pattern Recognition Conf (CVPR). Piscataway, NJ: IEEE, 2025: 30147−30156, articleTitle=null, refAbstract=null), Reference(id=1325493591480611453, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Sundaram J, Iyer R. LLaVaOLMoBieNet1B: Ternary LLM goes multimodal![J]. arXiv preprint arXiv: 2408.13402, 2024, articleTitle=null, refAbstract=null), Reference(id=1325493591732269694, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Zhaoqing, Xu Haoning, Jin Zengrui, et al. Towards one-bit ASR: Extremely low-bit conformer quantization using co-training and stochastic precision[C]//Proc of Interspeech. Baixas, France: International Speech Communications Association, 2025: 1973−1977, articleTitle=null, refAbstract=null), Reference(id=1325493591853904511, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=63, authorNames=null, journalName=null, refType=null, unstructuredReference=Morrison M, Churchwell C, Pruyne N, et al. Sign value constraint decomposition for efficient 1-bit quantization of speech translation tasks[C]//Proc of 2024 Interspeech. New York: Curran Associates, 2024: 842−846, articleTitle=null, refAbstract=null), Reference(id=1325493592210420352, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=64, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu Z, Kojima T, Matsuo Y, et al. Slender-Mamba: Fully quantized Mamba in 1.58 bits from head to toe[C]//Proc of the 31st Int Conf on Computational Linguistics (COLING). Stroudsburg, PA: ACL, 2025: 4715−4724, articleTitle=null, refAbstract=null), Reference(id=1325493592290112129, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=Hassan A, Meng J, Anupreetham A, et al. SpQuant-SNN: Ultra-low precision membrane potential with sparse activations unlock the potential of on-device spiking neural networks applications[J]. Frontiers in Neuroscience, 2024, 18: 1440000, articleTitle=null, refAbstract=null), Reference(id=1325493592634045058, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=66, authorNames=null, journalName=null, refType=null, unstructuredReference=Su Jianlin, Murtadha A, Lu Yu, et al. Roformer: Enhanced transformer with rotary position embedding[J]. Neurocomputing, 2024, 568: 127063, articleTitle=null, refAbstract=null), Reference(id=1325493592726319747, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=67, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Zhenyan, Song Yixin, Yu Guanghui, et al. Relu2 wins: Discovering efficient activation functions for sparse LLMs[J]. arXiv preprint arXiv: 2402.03804, 2024, articleTitle=null, refAbstract=null), Reference(id=1325493593045086852, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=68, rfOrder=68, authorNames=null, journalName=null, refType=null, unstructuredReference=Merity S, Xiong C, Bradbury J, et al. Pointer sentinel mixture models[J]. arXiv:1609.07843v1, articleTitle=null, refAbstract=null), Reference(id=1325493593162527365, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=69, rfOrder=69, authorNames=null, journalName=null, refType=null, unstructuredReference=Raffel C, Shazeer N, Roberts A. et al. Exploring the limits of transfer learning with a unified text-to-text transformer[J]. Journal of machine learning research, 2020, 21(140): 1−67, articleTitle=null, refAbstract=null), Reference(id=1325493593414185606, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=70, rfOrder=70, authorNames=null, journalName=null, refType=null, unstructuredReference=Yadav V, Bethard S, Surdeanu M. Quick and (not so) dirty: Unsupervised selection of justification sentences for multi-hop question answering[C]//Proc of the 2019 Conf on Empirical Methods in Natural Language Processing and the 9th Int Joint Conf on Natural Language Processing (EMNLP-IJCNLP). Stroudsburg, PA, ACL, 2019: 2578−2589, articleTitle=null, refAbstract=null), Reference(id=1325493593519043207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=71, rfOrder=71, authorNames=null, journalName=null, refType=null, unstructuredReference=Clark P, Cowhey I, Etzioni O, et al. Think you have solved question answering? try ARC, the AI2 reasoning challenge[J]. arXiv preprint arXiv: 1803.05457, 2018, articleTitle=null, refAbstract=null), Reference(id=1325493595192570504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=72, rfOrder=72, authorNames=null, journalName=null, refType=null, unstructuredReference=Zellers R, Holtzman A, Bisk Y, et al. HellaSwag: Can a machine really finish your sentence?[C]//Proc of the 57th Annual Meeting of the Association for Computational Linguistics (ACL). Stroudsburg, PA: ACL, 2019: 4791−4800, articleTitle=null, refAbstract=null), Reference(id=1325493595507143305, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=73, rfOrder=73, authorNames=null, journalName=null, refType=null, unstructuredReference=Clark C, Lee K, Chang M W, et al. BoolQ: Exploring the surprising difficulty of natural yes/no questions[C]//Proc of NAACL-HLT. Stroudsburg, PA: ACL, 2019: 2924−2936, articleTitle=null, refAbstract=null), Reference(id=1325493595565863562, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=74, rfOrder=74, authorNames=null, journalName=null, refType=null, unstructuredReference=Mihaylov T, Clark P, Khot T, et al. Can a suit of armor conduct electricity? A new dataset for open book question answering[C]//Proc of the 2018 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2018: 2381−2391, articleTitle=null, refAbstract=null), Reference(id=1325493595624583819, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=75, rfOrder=75, authorNames=null, journalName=null, refType=null, unstructuredReference=Bisk Y, Zellers R, Bras R, et al. PIQA: Reasoning about physical commonsense in natural language[C]//Proc of the AAAI Conf on Artificial Intelligence (AAAI). Palo Alto, CA: AAAI, 2020: 7432−7439, articleTitle=null, refAbstract=null), Reference(id=1325493595951739532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=76, rfOrder=76, authorNames=null, journalName=null, refType=null, unstructuredReference=Sakaguchi K, Bras R, Bhagavatula C, et al. Winogrande: An adversarial winograd schema challenge at scale[J]. Communications of the ACM, 2021, 64(9): 99–106, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1325493575621947895, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, xref=1, ext=[AuthorCompanyExt(id=1325493575630336504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493575621947895, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1State Key Laboratory of Multimedia Information Processing (Peking University), Beijing 100871), AuthorCompanyExt(id=1325493575638725113, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493575621947895, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1多媒体信息处理全国重点实验室(北京大学) 北京 100871)]), AuthorCompany(id=1325493577320641018, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, xref=2, ext=[AuthorCompanyExt(id=1325493577329029627, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493577320641018, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2School of Cyber Science and Technology, Beihang University, Beijing 100191), AuthorCompanyExt(id=1325493577337418236, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, companyId=1325493577320641018, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2北京航空航天大学网络空间安全学院 北京 100191)])], figs=[ArticleFig(id=1325493579723977253, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, label=Figure 1, caption=
Developmental trends of LLMs quantization technology, figureFileSmall=+RDF31xWJOpWQohaaSHQGA==, figureFileBig=ldn+4HE2y+6xLqghdUPA0Q==, tableContent=null), ArticleFig(id=1325493579791086118, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, label=图1, caption=
LLM量化技术发展趋势, figureFileSmall=+RDF31xWJOpWQohaaSHQGA==, figureFileBig=ldn+4HE2y+6xLqghdUPA0Q==, tableContent=null), ArticleFig(id=1325493579967246887, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, label=Figure 2, caption=
Example of QiD, figureFileSmall=rucXJxOviTBY2IQ/byojcQ==, figureFileBig=xESmLS6n1iAK6nEV4vLhhw==, tableContent=null), ArticleFig(id=1325493580034355752, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, label=图2, caption=
QiD示例, figureFileSmall=rucXJxOviTBY2IQ/byojcQ==, figureFileBig=xESmLS6n1iAK6nEV4vLhhw==, tableContent=null), ArticleFig(id=1325493580093076009, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, label=Figure 3, caption=
Model architecture of BitNet b1.58, figureFileSmall=AI8EnsbWyG4vYbqq6HSVcw==, figureFileBig=OwL9E1UhWFvDmbp4NYRdGw==, tableContent=null), ArticleFig(id=1325493581737243178, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, label=图3, caption=
BitNet b1.58模型架构, figureFileSmall=AI8EnsbWyG4vYbqq6HSVcw==, figureFileBig=OwL9E1UhWFvDmbp4NYRdGw==, tableContent=null), ArticleFig(id=1325493581808546347, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, label=Figure 4, caption=
Full-precision weights distribution of pre-trained tenary model, figureFileSmall=be9160lnFYUHZMNwCGre0w==, figureFileBig=O4TGCdrLzwuFmvSIfdcX8g==, tableContent=null), ArticleFig(id=1325493581884043820, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, label=图4, caption=
预训练三元模型的全精度权重分布, figureFileSmall=be9160lnFYUHZMNwCGre0w==, figureFileBig=O4TGCdrLzwuFmvSIfdcX8g==, tableContent=null), ArticleFig(id=1325493581959541293, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, label=Figure 5, caption=
Illustration of LUT algorithm, figureFileSmall=4PZ/ByfomMCqmlubh9HJhQ==, figureFileBig=oM/6VfaK/4AhXV/k0oRQwA==, tableContent=null), ArticleFig(id=1325493582035038766, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, label=图5, caption=
LUT算法示意图, figureFileSmall=4PZ/ByfomMCqmlubh9HJhQ==, figureFileBig=oM/6VfaK/4AhXV/k0oRQwA==, tableContent=null), ArticleFig(id=1325493582114730543, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, label=Figure 6, caption=
Transformer model design under complex-valued domain, figureFileSmall=HqCQzw5X+pl/zqraBJCffw==, figureFileBig=ozjv1sysJlWVg2AynGKc9Q==, tableContent=null), ArticleFig(id=1325493582198616624, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, label=图6, caption=
复数域下的Transformer模型设计, figureFileSmall=HqCQzw5X+pl/zqraBJCffw==, figureFileBig=ozjv1sysJlWVg2AynGKc9Q==, tableContent=null), ArticleFig(id=1325493582269919793, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, label=Figure 7, caption=
Complex linear layer using PhaseQuant algorithm, figureFileSmall=ghR4bRJDV/gCIhDdY5n+oQ==, figureFileBig=N0dYlbY80Xp4fJWGBEby4g==, tableContent=null), ArticleFig(id=1325493582362194482, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, label=图7, caption=
应用PhaseQuant算法的复数线性层, figureFileSmall=ghR4bRJDV/gCIhDdY5n+oQ==, figureFileBig=N0dYlbY80Xp4fJWGBEby4g==, tableContent=null), ArticleFig(id=1325493582454469171, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, label=Figure 8, caption=
Model architecture of iFairy, figureFileSmall=1OqjTZASSOEtGyYCMZIF/g==, figureFileBig=wFNLqeFS59s3Kw0Khib29A==, tableContent=null), ArticleFig(id=1325493582521578036, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, label=图8, caption=
iFairy模型架构, figureFileSmall=1OqjTZASSOEtGyYCMZIF/g==, figureFileBig=wFNLqeFS59s3Kw0Khib29A==, tableContent=null), ArticleFig(id=1325493582618047029, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, label=Figure 9, caption=
Complexification equivalent transformation of Fairy2i real number model, figureFileSmall=H8IZutfrEb/BBiCJ32YO9Q==, figureFileBig=N0Z5kfTDEbr1WqaOWBgckw==, tableContent=null), ArticleFig(id=1325493582710321719, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, label=图9, caption=
Fairy2i实数模型的复数化等价转换, figureFileSmall=H8IZutfrEb/BBiCJ32YO9Q==, figureFileBig=N0Z5kfTDEbr1WqaOWBgckw==, tableContent=null), ArticleFig(id=1325493582790013496, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, label=Table 1, caption=
Comparison of Representative PTQ and QAT Low-Bit Quantization Methods in LLM, figureFileSmall=null, figureFileBig=null, tableContent=
方法 类别 | 提出时间/应用场景 | 存储压 缩率 | 推理速度 | 任务性能 | 代表性研究成果 |
|---|
| 注:存储压缩率和推理速度都是相对于FP32计算的。 |
| PTQ | Int8 (2018—2022年,CNN→LLM) | ≈4倍 | ≈1.5~2倍实际加速(理论4倍) | 推理端几乎无损 | Integer-only Quantization[1];GPT3.int8()[19] |
| Int4 (2019年提出,2022—2023年,LLM常用低比特部署) | ≈8倍 | ≈3~4倍实际加速(理论8倍) | 轻微下降,可接受 | PTQ-4bit[20];SmoothQuant[8] |
Int2 (2023—2025年,LLM进一步 压缩) | ≈16倍 | ≈6~7倍实际加速 (理论16倍) | 2比特精度明显提升 | QuIP[22]; QuIP#[23]; QTIP[24] |
PTQ工程优化 (2022—2024年, 大模型常用) | 4~8倍 | 2~6倍 | 精度略低于QAT,但部署便捷 | OBC[31];GPTQ[6]; AWQ[7];QuaRot[32] |
| 稀疏+PTQ (2022—2023年,工业落地) | 10~20倍 | 10~20倍 | 兼顾压缩与加速,逐渐工业化 | ZeroQuant[21];SparseGPT[33] |
| 混合精度PTQ (2019—2020年,BERT/NLP) | 4~8倍 | 2~6倍 | 精度接近FP32,灵活性强 | HAWQ[27]; |
| QAT | Int8 (2018—2022年,CNN→LLM) | ≈4倍 | ≈1.5~2倍 | 精度保持优于PTQ | Integer-only Quantization[1]; TensorRT QAT[5] |
| Int4 / 三值QAT (2016—2023年) | ≈8~20倍 | ≈3~10倍 | 精度下降较小,稳定性好 | DoReFa-Net[26];TWN[13]; LSQ[28];LSQ+[29];Q-BERT[30] |
| 二值QAT (2015—2016年,早期探索) | ≈32倍 | 数十倍理论加速,依赖硬件 | 精度显著下降,复杂任务不足 | BinaryConnect[34];XNOR-Net[35]; |
| BitNet (1.58比特,2023年) | ≈20倍 (理论值) | ≈10~20倍 | 性能出现下降,无法突破 原模型精度 | BitNet[9];BitNet b1.58[12] |
| OneBit (1比特,2024年) | ≈32倍 | ≈20倍 | 性能下降明显,高度依赖蒸馏 | OneBit[10] |
| 复域量化(2比特,2025) | ≈16倍 | 2比特位宽与无乘法运算的 双重加速 | 性能超越FP16,突破2比特 性能天花板 | iFairy[17];Fairy2i[18] |
), ArticleFig(id=1325493582873899577, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, label=表1, caption=
LLM中典型PTQ与QAT低比特量化方法对比
, figureFileSmall=null, figureFileBig=null, tableContent=
方法 类别 | 提出时间/应用场景 | 存储压 缩率 | 推理速度 | 任务性能 | 代表性研究成果 |
|---|
| 注:存储压缩率和推理速度都是相对于FP32计算的。 |
| PTQ | Int8 (2018—2022年,CNN→LLM) | ≈4倍 | ≈1.5~2倍实际加速(理论4倍) | 推理端几乎无损 | Integer-only Quantization[1];GPT3.int8()[19] |
| Int4 (2019年提出,2022—2023年,LLM常用低比特部署) | ≈8倍 | ≈3~4倍实际加速(理论8倍) | 轻微下降,可接受 | PTQ-4bit[20];SmoothQuant[8] |
Int2 (2023—2025年,LLM进一步 压缩) | ≈16倍 | ≈6~7倍实际加速 (理论16倍) | 2比特精度明显提升 | QuIP[22]; QuIP#[23]; QTIP[24] |
PTQ工程优化 (2022—2024年, 大模型常用) | 4~8倍 | 2~6倍 | 精度略低于QAT,但部署便捷 | OBC[31];GPTQ[6]; AWQ[7];QuaRot[32] |
| 稀疏+PTQ (2022—2023年,工业落地) | 10~20倍 | 10~20倍 | 兼顾压缩与加速,逐渐工业化 | ZeroQuant[21];SparseGPT[33] |
| 混合精度PTQ (2019—2020年,BERT/NLP) | 4~8倍 | 2~6倍 | 精度接近FP32,灵活性强 | HAWQ[27]; |
| QAT | Int8 (2018—2022年,CNN→LLM) | ≈4倍 | ≈1.5~2倍 | 精度保持优于PTQ | Integer-only Quantization[1]; TensorRT QAT[5] |
| Int4 / 三值QAT (2016—2023年) | ≈8~20倍 | ≈3~10倍 | 精度下降较小,稳定性好 | DoReFa-Net[26];TWN[13]; LSQ[28];LSQ+[29];Q-BERT[30] |
| 二值QAT (2015—2016年,早期探索) | ≈32倍 | 数十倍理论加速,依赖硬件 | 精度显著下降,复杂任务不足 | BinaryConnect[34];XNOR-Net[35]; |
| BitNet (1.58比特,2023年) | ≈20倍 (理论值) | ≈10~20倍 | 性能出现下降,无法突破 原模型精度 | BitNet[9];BitNet b1.58[12] |
| OneBit (1比特,2024年) | ≈32倍 | ≈20倍 | 性能下降明显,高度依赖蒸馏 | OneBit[10] |
| 复域量化(2比特,2025) | ≈16倍 | 2比特位宽与无乘法运算的 双重加速 | 性能超越FP16,突破2比特 性能天花板 | iFairy[17];Fairy2i[18] |
), ArticleFig(id=1325493582961979962, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, label=Table 2, caption=
Evaluation Results of Language Modeling Capability and Downstream Tasks %, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 量化 | 平均PPL↓ | 平均准确率↑ |
|---|
| 注:PPL指困惑度;“↑”表示越高越好,“↓”表示越低越好;“○”表示没有PhaseQuant量化的iFairy;“★”表示BitNet原始论文汇报的结果;“†”表示我们复现的BitNet的结果。黑体数值表示在同类算法(模型参数量、是否量化)中表现最好。 |
| BF16 LLaMA 700M | 否 | 11.02 | 44.61 |
| iFairy○ 700M | 否 | 10.08 | 46.18 |
| BitNet b1.58★ 700M | 是 | 12.87 | 44.26 |
| BitNet b1.58† 700M | 是 | 11.51 | 44.23 |
| iFairy 700M | 是 | 11.13 | 44.70 |
| BF16 LLaMA 1.3B | 否 | 10.21 | 46.32 |
| iFairy○ 1.3B | 否 | 9.34 | 48.23 |
| BitNet b1.58★ 1.3B | 是 | 11.29 | 45.39 |
| BitNet b1.58† 1.3B | 是 | 10.32 | 46.05 |
| iFairy 1.3B | 是 | 10.05 | 46.52 |
), ArticleFig(id=1325493583054254651, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, label=表2, caption=
语言建模能力和下游任务评测结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 量化 | 平均PPL↓ | 平均准确率↑ |
|---|
| 注:PPL指困惑度;“↑”表示越高越好,“↓”表示越低越好;“○”表示没有PhaseQuant量化的iFairy;“★”表示BitNet原始论文汇报的结果;“†”表示我们复现的BitNet的结果。黑体数值表示在同类算法(模型参数量、是否量化)中表现最好。 |
| BF16 LLaMA 700M | 否 | 11.02 | 44.61 |
| iFairy○ 700M | 否 | 10.08 | 46.18 |
| BitNet b1.58★ 700M | 是 | 12.87 | 44.26 |
| BitNet b1.58† 700M | 是 | 11.51 | 44.23 |
| iFairy 700M | 是 | 11.13 | 44.70 |
| BF16 LLaMA 1.3B | 否 | 10.21 | 46.32 |
| iFairy○ 1.3B | 否 | 9.34 | 48.23 |
| BitNet b1.58★ 1.3B | 是 | 11.29 | 45.39 |
| BitNet b1.58† 1.3B | 是 | 10.32 | 46.05 |
| iFairy 1.3B | 是 | 10.05 | 46.52 |
), ArticleFig(id=1325493583150723644, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=EN, label=Table 3, caption=
Experimental Results of Quantitative Perception Training of Real Pre-Training Model %, figureFileSmall=null, figureFileBig=null, tableContent=
| 原始模型 | 量化方法 | 平均PPL↓ | 平均准确率↑ |
|---|
| 注:PPL指困惑度 ;“↑”表示越高越好,“↓”表示越低越好。黑体数值表示在同类算法(模型参数量、是否量化)中表现最好。 |
| LLaMA2-7B | BitNet 1bit | 11.75 | 46.21 |
| Fairy2i | 11.03 | 48.66 |
), ArticleFig(id=1325493583222026813, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1325493569858974164, language=CN, label=表3, caption=
实数预训练模型的量化感知训练实验结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 原始模型 | 量化方法 | 平均PPL↓ | 平均准确率↑ |
|---|
| 注:PPL指困惑度 ;“↑”表示越高越好,“↓”表示越低越好。黑体数值表示在同类算法(模型参数量、是否量化)中表现最好。 |
| LLaMA2-7B | BitNet 1bit | 11.75 | 46.21 |
| Fairy2i | 11.03 | 48.66 |
)], attaches=null, journal=Journal(id=1324759606947315908, delFlag=0, nameCn=计算机研究与发展, nameEn=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, issn=1000-1239, eissn=null, cn=11-1777/TP, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=k2l8zgqwstuxxevFX2qxVA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Computer Research and Development, journalRemark=null, publicationField=null, createdTime=1793776903141, updatedTime=1793850698612, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=k2l8zgqwstuxxevFX2qxVA==, picEn=r6k0Ry+RD+c/VXj5QarmDw==, jcr=null, cjcr=null, exts=[JournalExt(id=1325069127710286688, language=CN, name=计算机研究与发展, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698640, updatedTime=1793850698640, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1325069127777395553, language=EN, name=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698656, updatedTime=1793850698656, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1324759914146529478, websiteList=[Website(id=1325070300139892771, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN, language=CN, createTime=1793850978169, createBy=18614031015, updateTime=1793851040259, updateBy=18614031015, name=计算机研究与发展-中文, tplId=1146099689490845704, title=计算机研究与发展, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070893751349360, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=articleTextType, value=kx, createTime=1793851119697, updateTime=1793851119697, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893730377837, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=banner, value=null, createTime=1793851119692, updateTime=1793851119692, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893772320883, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=grayFlag, value=0, createTime=1793851119702, updateTime=1793851119702, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893721989228, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851119690, updateTime=1793851119690, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893784903797, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=minRunFlag, value=0, createTime=1793851119705, updateTime=1793851119705, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893742960751, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic, createTime=1793851119695, updateTime=1793851119695, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893780709492, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=silenceFlag, value=0, createTime=1793851119704, updateTime=1793851119704, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893738766446, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1793851119694, updateTime=1793851119694, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893755543665, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeColor, value=null, createTime=1793851119698, updateTime=1793851119698, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893763932274, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeStyle, value=null, createTime=1793851119700, updateTime=1793851119700, creator=18614031015, updator=18614031015)]), Website(id=1325070300580294698, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN, language=EN, createTime=1793850978274, createBy=18614031015, updateTime=1793851036638, updateBy=18614031015, name=计算机研究与发展-英文, tplId=1146101810881728533, title=Journal of Computer Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070925288321148, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=articleTextType, value=kx, createTime=1793851127216, updateTime=1793851127216, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925263155321, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=banner, value=null, createTime=1793851127210, updateTime=1793851127210, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925309292671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=grayFlag, value=0, createTime=1793851127221, updateTime=1793851127221, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925254766712, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851127208, updateTime=1793851127208, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925326069889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=minRunFlag, value=0, createTime=1793851127225, updateTime=1793851127225, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925279932539, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic, createTime=1793851127214, updateTime=1793851127214, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925317681280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=silenceFlag, value=0, createTime=1793851127223, updateTime=1793851127223, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925271543930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1793851127212, updateTime=1793851127212, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925292515453, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeColor, value=null, createTime=1793851127217, updateTime=1793851127217, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925300904062, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeStyle, value=null, createTime=1793851127219, updateTime=1793851127219, creator=18614031015, updator=18614031015)])], journalTitle=计算机研究与发展, weixinUrl=null, journalUrl=https://crad.ict.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Computer Research and Development, journalPhotoCn=k2l8zgqwstuxxevFX2qxVA==, journalPhotoEn=r6k0Ry+RD+c/VXj5QarmDw==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202550788, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550788, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202550788, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202550788, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1769875200000, fullTextJson=null, articleText=null, reference=null)