{"ID":2869489,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.15188","arxiv_id":"2509.15188","title":"Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning","abstract":"Autoregressive (AR) language models generate text one token at a time, which limits their inference speed. Diffusion-based language models offer a promising alternative, as they can decode multiple tokens in parallel. However, we identify a key bottleneck in current diffusion LMs: the long decoding-window problem, where tokens generated far from the input context often become irrelevant or repetitive. Previous solutions like semi-autoregressive address this issue by splitting windows into blocks (sacrificing bidirectionality), but we find that this also leads to time-interval expansion problem, sacrificing the speed. Therefore, semi-AR eliminates the main advantages of diffusion models. To overcome this, we propose Convolutional decoding (Conv), a normalization-based method that narrows the decoding window without hard segmentation, leading to better fluency and flexibility. Additionally, we introduce Rejecting Rule-based Fine-Tuning (R2FT), a post-hoc training scheme that better aligns tokens at positions far from context. Our methods achieve state-of-the-art results on open-ended generation benchmarks (e.g., AlpacaEval) among diffusion LM baselines, with significantly lower step size than previous works, demonstrating both speed and quality improvements.","short_abstract":"Autoregressive (AR) language models generate text one token at a time, which limits their inference speed. Diffusion-based language models offer a promising alternative, as they can decode multiple tokens in parallel. However, we identify a key bottleneck in current diffusion LMs: the long decoding-window problem, wher...","url_abs":"https://arxiv.org/abs/2509.15188","url_pdf":"https://arxiv.org/pdf/2509.15188v3","authors":"[\"Yeongbin Seo\",\"Dongha Lee\",\"Jaehyung Kim\",\"Jinyoung Yeo\"]","published":"2025-09-18T17:48:21Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Diffusion Model\",\"Language Model\"]","has_code":false}