Discrete Diffusion Models: A Unified Framework from Tokenization to Generation

[2607.13431] Discrete Diffusion Models: A Unified Framework from Tokenization to Generation Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2607.13431 (cs) [Submitted on 15 Jul 2026 ( v1 ), last revised 25 Aug 2026 (this version, v2)] Title: Discrete Diffusion Models: A Unified Framework from Tokenization to Generation Authors: Ye Yuan , Weien Li , Rui Song , Zeyu Li , Haochen Liu , Xiangyu Kong , Zixuan Dong , Linfeng Du , Zipeng Sun , Weixu Zhang , Jiaxin Huang , Changjiang Han , Yonghan Yang , Zichen Zhao , Xiuyuan Hu , Haolun Wu , Yankai Chen , Fengran Mo , Jikun Kang , Bowei He , Dawn Song , Philip S. Yu , Xue Liu View PDF HTML (experimental) Abstract: Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) modeling for discrete data, offering parallel generation and iterative global refinement capabilities. Unlike continuous diffusion, where the state space is fixed, DDMs are fundamentally shaped by how the discrete state space is constructed: the tokenization scheme, the vocabulary topology, and domain-specific structural alphabets. This work introduces a unified conceptual framework that views discrete diffusion models through the construction of the underlying discrete state space. Within this framework, existing formulations, including transition-matrix, masking/absorbing-state, and score/ratio-based approaches, emerge as different instantiations of a common design space. The framework further exposes common design trade-offs across training objectives, inference algorithms, scaling behavior, systems optimization, and evaluation protocols, suggesting several promising directions for future research. Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2607.13431 [cs.LG] (or arXiv:2607.13431v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2607.13431 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ye Yuan [ view email ] [v1] Wed, 15 Jul 2026 04:23:22 UTC (618 KB) [v2] Tue, 25 Aug 2026 01:41:24 UTC (619 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG < prev | next > new | recent | 2026-07 Change to browse by: cs cs.AI cs.CL References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from (opens in new tab) (opens in new tab) (opens in new tab)

Related documents

• Discrete Diffusion Models: A Unified Framework from Tokenization to Generation#670685
• From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion#821030
• Know When to Hold 'em: Correct-Token Retention in Uniform-State Diffusion Language Models#1156547
• Local Diffusion Models and Phases of Data Distributions#158764
• Diverse Sampling in Diffusion Models with Marginal Preserving Particle Guidance#168337