@inproceedings{oba-bollegala-2026-diffusion,
title = "Diffusion Language Models: Foundations and Frontiers of Non-Autoregressive Language Generation",
author = "Oba, Daisuke and
Bollegala, Danushka",
editor = "Okazaki, Naoaki and
Wang, Zhongqing",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics: Tutorial Abstracts",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-tutorials.6/",
pages = "44--50",
ISBN = "979-8-89176-443-9",
abstract = "Diffusion language models (DLMs) have recently emerged as a non-autoregressive approach to language generation, enabling parallel, iterative, and refinement-based decoding beyond the conventional left-to-right paradigm. This tutorial offers the NLP community a technical map of this emerging field: starting from diffusion formulations for text, we clarify their connections to autoregressive language modeling, masked language modeling, and earlier iterative generation methods. We then survey recent progress in large-scale DLMs, efficient inference, training objectives, and post-training, including reinforcement learning for reasoning and alignment. Throughout the tutorial, we treat DLMs not as a solved replacement for autoregressive language models, but as a rapidly developing paradigm whose efficiency claims, controllability, practical assessment, and deployment implications require careful examination. We close by discussing representative open directions, from broader formulations such as flow-based language modeling to reliability, safety, and social bias as key requirements for the social acceptability of DLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oba-bollegala-2026-diffusion">
<titleInfo>
<title>Diffusion Language Models: Foundations and Frontiers of Non-Autoregressive Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daisuke</namePart>
<namePart type="family">Oba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danushka</namePart>
<namePart type="family">Bollegala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: Tutorial Abstracts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongqing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-443-9</identifier>
</relatedItem>
<abstract>Diffusion language models (DLMs) have recently emerged as a non-autoregressive approach to language generation, enabling parallel, iterative, and refinement-based decoding beyond the conventional left-to-right paradigm. This tutorial offers the NLP community a technical map of this emerging field: starting from diffusion formulations for text, we clarify their connections to autoregressive language modeling, masked language modeling, and earlier iterative generation methods. We then survey recent progress in large-scale DLMs, efficient inference, training objectives, and post-training, including reinforcement learning for reasoning and alignment. Throughout the tutorial, we treat DLMs not as a solved replacement for autoregressive language models, but as a rapidly developing paradigm whose efficiency claims, controllability, practical assessment, and deployment implications require careful examination. We close by discussing representative open directions, from broader formulations such as flow-based language modeling to reliability, safety, and social bias as key requirements for the social acceptability of DLMs.</abstract>
<identifier type="citekey">oba-bollegala-2026-diffusion</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-tutorials.6/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>44</start>
<end>50</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Diffusion Language Models: Foundations and Frontiers of Non-Autoregressive Language Generation
%A Oba, Daisuke
%A Bollegala, Danushka
%Y Okazaki, Naoaki
%Y Wang, Zhongqing
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: Tutorial Abstracts
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-443-9
%F oba-bollegala-2026-diffusion
%X Diffusion language models (DLMs) have recently emerged as a non-autoregressive approach to language generation, enabling parallel, iterative, and refinement-based decoding beyond the conventional left-to-right paradigm. This tutorial offers the NLP community a technical map of this emerging field: starting from diffusion formulations for text, we clarify their connections to autoregressive language modeling, masked language modeling, and earlier iterative generation methods. We then survey recent progress in large-scale DLMs, efficient inference, training objectives, and post-training, including reinforcement learning for reasoning and alignment. Throughout the tutorial, we treat DLMs not as a solved replacement for autoregressive language models, but as a rapidly developing paradigm whose efficiency claims, controllability, practical assessment, and deployment implications require careful examination. We close by discussing representative open directions, from broader formulations such as flow-based language modeling to reliability, safety, and social bias as key requirements for the social acceptability of DLMs.
%U https://aclanthology.org/2026.aacl-tutorials.6/
%P 44-50
Markdown (Informal)
[Diffusion Language Models: Foundations and Frontiers of Non-Autoregressive Language Generation](https://aclanthology.org/2026.aacl-tutorials.6/) (Oba & Bollegala, AACL-IJCNLP 2026)
ACL