{"slug": "discrete-beckmann-transport-models-for-one-step-language-modeling-and-reasoning", "title": "Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning", "summary": "Researchers submitted a paper to arXiv on 14 Sep 2026 introducing Discrete Beckmann Transport Models (DBTM), a time-independent flow whose autonomous transport map provably carries any point in the ambient space to a fixed point on the simplex vertices in a single step. DBTM removes the need for a pretrained teacher model and time conditioning by minimizing a conservation-equation residual directly from data, and on language modeling and reasoning tasks it enables one- and few-step generation that improves quality and accuracy over discrete diffusion and continuous flow baselines.", "body_md": "# Computer Science > Machine Learning\n\n  [Submitted on 14 Sep 2026]\n\n# Title:Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning\n\n[View PDF](https://arxiv.org/pdf/2609.15903)\n\n[HTML (experimental)](https://arxiv.org/html/2609.15903v1)\n\nAbstract:Discrete diffusion and flow models are a promising alternative to autoregressive language models, but compressing many-step sampling into fewer steps typically requires distilling a pretrained teacher model. This caps the student at the teacher's quality and requires a costly two-stage training pipeline. We introduce Discrete Beckmann Transport Models (DBTM), built on a time-independent flow whose autonomous transport map provably carries any point in the ambient space to a fixed point on the vertices of the simplex in a single step. We show that this fixed-point property is characterized by a conservation equation whose residual can be minimized directly from data, removing the requirement for a teacher flow and time conditioning. Under this construction, a partially trained map corresponds to the flow truncated at finite time, so generation reduces to iterating one map until it reaches a fixed point. We further extend the map to a partial-context interpolant where additional function evaluations act as refinement steps rather than ODE integration steps. On language modeling and reasoning tasks, DBTM enables one- and few-step generation that improves quality and accuracy over discrete diffusion and continuous flow baselines.\n    \n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/discrete-beckmann-transport-models-for-one-step-language-modeling-and-reasoning", "canonical_source": "https://arxiv.org/abs/2609.15903", "published_at": "2026-09-15 03:49:27+00:00", "updated_at": "2026-09-15 04:01:20.029168+00:00", "lang": "en", "topics": ["large-language-models", "machine-learning", "ai-research", "generative-ai"], "entities": ["Discrete Beckmann Transport Models", "DBTM", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/discrete-beckmann-transport-models-for-one-step-language-modeling-and-reasoning", "markdown": "https://wpnews.pro/news/discrete-beckmann-transport-models-for-one-step-language-modeling-and-reasoning.md", "text": "https://wpnews.pro/news/discrete-beckmann-transport-models-for-one-step-language-modeling-and-reasoning.txt", "jsonld": "https://wpnews.pro/news/discrete-beckmann-transport-models-for-one-step-language-modeling-and-reasoning.jsonld"}}