Forward-Free Diffusion Language Models with BPTT-Free Looped Refinement

[2606.08357] Forward-Free Diffusion Language Models with BPTT-Free Looped Refinement Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2606.08357 (cs) [Submitted on 6 Jun 2026 ( v1 ), last revised 27 Aug 2026 (this version, v2)] Title: Forward-Free Diffusion Language Models with BPTT-Free Looped Refinement Authors: Haotian Sun , Rushi Qiang , Yuqian Zheng , Bo Dai View PDF HTML (experimental) Abstract: Diffusion language models generate text through iterative denoising, offering a powerful alternative to autoregressive generation. However, discrete language spaces lack a natural neighborhood structure for defining effective perturbations, motivating artificial corruption schemes in the forward process. Such prescribed forward processes often produce states that are mathematically convenient but misaligned with the drafts and errors encountered during generation, resulting in degraded sample quality. To address this limitation, we propose FReDA, a forward-free diffusion language model that eliminates the need for a hand-designed forward process. We formulate diffusion language modeling as recursive distribution refinement, in which model-generated drafts serve as implicit intermediate states and the learned refinement model progressively moves the draft distribution toward the target distribution. Training detaches the preceding refinement passes and backpropagates only through the final pass, avoiding backpropagation through time (BPTT) across refinement iterations while retaining standard backpropagation within the final Transformer pass. Concretely, FReDA refines drafts by proposing candidate sequences and either directly performing self-refinement or selecting among parallel candidates via Best-of-N refinement. With this design, FReDA is neighborhood-agnostic, sampler-adaptive, and compatible with flexible refinement parameterizations. Extensive evaluations in the sub-8B regime show that FReDA-4B outperforms larger diffusion base models on reasoning and coding benchmarks, achieving absolute gains of up to 15%, while reaching a 1.5-1.8x average speedup over diffusion baselines and scaling effectively with additional refinement computation. Subjects: Computation and Language (cs.CL) Cite as: arXiv:2606.08357 [cs.CL] (or arXiv:2606.08357v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2606.08357 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Haotian Sun [ view email ] [v1] Sat, 6 Jun 2026 22:10:46 UTC (160 KB) [v2] Thu, 27 Aug 2026 08:53:04 UTC (162 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CL < prev | next > new | recent | 2026-06 Change to browse by: cs 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? ) 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)

Related documents

• Forward-Free Diffusion Language Models with BPTT-Free Looped Refinement#677633
• Self-Augmenting Retrieval for Diffusion Language Models#259459
• Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models#800070
• Hill Sampling for Test-Time Scaling: A Simple and Better Alternative to Repeated Sampling, Evolution, and Training#1061149
• Augmenting large language models with chemistry tools#16635