Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning

• URL: http://arxiv.org/abs/2509.15188v2
• Date: Mon, 29 Sep 2025 07:50:10 GMT
• Title: Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning
• Authors: Yeongbin Seo, Dongha Lee, Jaehyung Kim, Jinyoung Yeo,
• Abstract summary: Autoregressive (AR) language models generate text one token at a time, which limits their inference speed.<n>We propose Conal decoding (Conv), a normalization-based method that narrows the decoding window.<n>We also introduce Rejecting Rule-based Fine-Tuning (R2FT), a post-hoc training scheme that better aligns tokens at positions far from context.
• Score: 23.58934174168992
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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, but this sacrifices speed and bidirectionality, eliminating the main advantage 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.

Related papers

• Residual Context Diffusion Language Models [90.07635240595926]
  Residual Context Diffusion (RCD) is a module that converts discarded token representations into contextual residuals and injects them back for the next denoising step.<n>RCD consistently improves frontier dLLMs by 5-10 points in accuracy with minimal extra computation overhead.
  arXiv  Detail & Related papers  (2026-01-30T13:16:32Z)
• Window-Diffusion: Accelerating Diffusion Language Model Inference with Windowed Token Pruning and Caching [10.315266731366123]
  We present a window-based token pruning and caching method for inference.<n>Experiments on LLaDA and Dream show that, under matched compute budgets, our method achieves up to $99times$ inference speedup.
  arXiv  Detail & Related papers  (2026-01-28T07:49:20Z)
• Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding [36.74241893088594]
  Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation.<n>Recent works have accelerated inference via KV cache reuse or decoding, but overlook the intrinsic inefficiencies within the block-wise diffusion process.<n>We propose Streaming-dLLM, a training-free framework that streamlines inference across both spatial and temporal dimensions.
  arXiv  Detail & Related papers  (2026-01-25T17:36:04Z)
• WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference [44.87788417755154]
  We propose WeDLM, a diffusion decoding framework built entirely on standard causal attention.<n>We show that WeDLM preserves the quality of strong AR backbones while delivering substantial speedups.
  arXiv  Detail & Related papers  (2025-12-28T01:25:48Z)
• Finish First, Perfect Later: Test-Time Token-Level Cross-Validation for Diffusion Large Language Models [47.5976588836299]
  Diffusion large language models (dLLMs) offer advantages such as accelerated parallel decoding and bidirectional context modeling.<n>The vanilla decoding strategy in discrete dLLMs suffers from a critical limitation: once a token is accepted, it can no longer be revised in subsequent steps.<n>We propose Tolerator, a training-free decoding strategy that leverages cross-validation among predicted tokens.
  arXiv  Detail & Related papers  (2025-10-06T17:56:46Z)
• Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs [57.69190972274813]
  Diffusion Large Language Models (DLLMs) have emerged as a compelling alternative to Autoregressive models.<n>ExistingDLLMs are plagued by a severe quality-speed trade-off, where faster parallel decoding leads to significant performance degradation.<n>We introduce Wide-In, Narrow-Out (WINO), a training-free decoding algorithm that enables revokable decoding inDLLMs.
  arXiv  Detail & Related papers  (2025-07-24T16:51:33Z)
• Accelerating Diffusion LLMs via Adaptive Parallel Decoding [60.407727995313074]
  We introduce adaptive parallel decoding (APD), a novel method that dynamically adjusts the number of tokens sampled in parallel.<n>APD provides markedly higher throughput with minimal quality degradations on downstream benchmarks.
  arXiv  Detail & Related papers  (2025-05-31T06:10:10Z)
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding [51.711605076319216]
  Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities.<n>We introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop.<n>We propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality.
  arXiv  Detail & Related papers  (2025-05-28T17:39:15Z)
• FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion [22.207275433870937]
  Diffusion language models offer parallel token generation and inherent bidirectionality.<n>State-of-the-art diffusion models (e.g., Dream 7B, LLaDA 8B) suffer from slow inference.<n>We introduce Guided Diffusion, a training-free method that uses a lightweight pretrained autoregressive model to supervise token unmasking.
  arXiv  Detail & Related papers  (2025-05-27T17:39:39Z)
• Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion [55.0194604505437]
  Speculative decoding has emerged as a widely adopted method to accelerate large language model inference.<n>This paper proposes an adaptation of speculative decoding which uses discrete diffusion models to generate draft sequences.
  arXiv  Detail & Related papers  (2024-08-10T21:24:25Z)
• Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration [54.897493351694195]
  We propose a novel parallel decoding approach, namely textithidden transfer, which decodes multiple successive tokens simultaneously in a single forward pass. In terms of acceleration metrics, we outperform all the single-model acceleration techniques, including Medusa and Self-Speculative decoding.
  arXiv  Detail & Related papers  (2024-04-18T09:17:06Z)
• CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning [59.88924847995279]
  We propose a novel Cross-Modal LLM Fine-Tuning (CALF) framework for MTSF.<n>To reduce the distribution discrepancy, we develop the cross-modal match module.<n>CALF establishes state-of-the-art performance for both long-term and short-term forecasting tasks.
  arXiv  Detail & Related papers  (2024-03-12T04:04:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.