{"paper_id":"27f15cc7-d126-43be-b1cc-db35835cbd9f","body_text":"Efficient Diffusion Language Models: A Comprehensive Survey | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 23 January 2026 V1 Latest version Share on Efficient Diffusion Language Models: A Comprehensive Survey Authors : Haokun Lin 0009-0000-1084-7115 [email protected] , Xinle Jia , Shaozhen Liu , Shujun Xia , Weitao Huang , Haobo Xu , Junyang Li , … Show All … , Yicheng Xiao , Xingrun Xing , Ziyu Guo , Renrui Zhang , Qi Li , Yichen Wu , Renzhen Wang , Xiaojuan Qi , Caifeng Shan , Hongsheng Li , and Zhenan Sun Show Fewer Authors Info & Affiliations https://doi.org/10.22541/au.176918713.36402137/v1 1173 views 459 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract Diffusion language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) language models, offering competitive performance with a fundamentally different generation paradigm. Instead of producing tokens strictly left-to-right, dLLMs iteratively refine partially masked sequences, enabling bidirectional context modeling and supporting parallel token updates. This design creates new opportunities for accelerating generation and improving controllability. However, practical deployment of dLLMs remains challenging due to the high cost of training at scale and the lack of mature inference optimizations such as cache-friendly decoding and robust parallel sampling. In this work, we provide a comprehensive overview of recent progress on efficient dLLMs. To reflect how efficiency bottlenecks arise across the full lifecycle of dLLMs, spanning training, decoding, and deployment, we organize existing approaches into five categories: Training, Inference, Context, Framework, and Multimodality. For each category, we summarize representative methods and highlight their motivations, key techniques, and empirical trade-offs. Finally, we discuss open challenges and outline promising directions for future research toward high-throughput, robust, and practically deployable diffusion language models. Github Repository: https://github.com/FelixMessi/Awesome-Efficient-dLLMs . Supplementary Material File (efficient_dlm.pdf) Download 458.23 KB Information & Authors Information Version history V1 Version 1 23 January 2026 Copyright This work is licensed under a Creative Commons Attribution 4.0 International License Keywords diffusion large language models efficient deep learning inference acceleration multimodal learning Authors Affiliations Haokun Lin 0009-0000-1084-7115 [email protected] Institute of Automation, Chinese Academy of Sciences City University of Hong View all articles by this author Xinle Jia Nanjing University View all articles by this author Shaozhen Liu Institute of Automation, Chinese Academy of Sciences View all articles by this author Shujun Xia City University of Hong View all articles by this author Weitao Huang Jiaotong University View all articles by this author Haobo Xu Tsinghua University View all articles by this author Junyang Li Institute of Automation, Chinese Academy of Sciences View all articles by this author Yicheng Xiao Tsinghua University View all articles by this author Xingrun Xing Institute of Automation, Chinese Academy of Sciences View all articles by this author Ziyu Guo The Chinese University of Hong View all articles by this author Renrui Zhang The Chinese University of Hong View all articles by this author Qi Li Institute of Automation, Chinese Academy of Sciences View all articles by this author Yichen Wu City University of Hong Harvard University View all articles by this author Renzhen Wang Jiaotong University View all articles by this author Xiaojuan Qi The University of Hong Kong View all articles by this author Caifeng Shan Nanjing University View all articles by this author Hongsheng Li The Chinese University of Hong View all articles by this author Zhenan Sun Institute of Automation, Chinese Academy of Sciences View all articles by this author Metrics & Citations Metrics Article Usage 1173 views 459 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Haokun Lin, Xinle Jia, Shaozhen Liu, et al. Efficient Diffusion Language Models: A Comprehensive Survey. Authorea . 23 January 2026. DOI: https://doi.org/10.22541/au.176918713.36402137/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(\".js__slcInclude\").on(\"change\", function(e){ if ($(this).val() == 'refworks') $('#direct').prop(\"checked\", false); $('#direct').prop(\"disabled\", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {\"doi\":\"10.22541/au.176918713.36402137/v1\",\"type\":\"Article\"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob(\"bG9jYXRpb24=\"),_bnb=atob(\"b3JpZ2lu\"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(\" \")); $.get(\"/resource/lodash?t=\"+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML=\"window.__CF$cv$params={r:'9fdf4100ddd5c13d',t:'MTc3OTE1MzM2Mg=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);\";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();","source_license":"CC-BY-4.0","license_restricted":false}