arXiv Machine Learning September 16, 2026 By Fengrui Zuo, Zhiwei Ke, Yiming Liu, Wenqi Lou, Chao Wang, Xuehai Zhou

Window-Diffusion: Accelerating Diffusion Language Model Inference with Windowed Token Pruning and Caching

Read the original on arXiv Machine Learning →

The paper introduces Window-Diffusion, a method that accelerates diffusion language model inference by pruning and caching tokens within a sliding window. It categorizes undecoded tokens into active, buffer, and far-field groups, computing only the first two while discarding the rest. Experiments on LLaDA and Dream demonstrate up to 99× speedup with minimal loss in generation quality.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 15

Residual Context Diffusion Language Models

arXiv:2601. 22954v2 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to purely autoregressive language models because they can decode multiple tokens in parallel.

By Yuezhou Hu, Harman Singh, Monishwaran Maheswaran, Haocheng Xi, Coleman Hooper, Jintao Zhang, Aditya Tomar, Michael W. Mahoney, Sewon Min, Mehrdad Farajtabar, Kurt Keutzer, Amir Gholami, Chenfeng Xu

llms diffusion benchmarks

arXiv Computation and Language

Aug 25

Accelerating Diffusion Language Models via Structured Suffix Modeling

The paper introduces a training‑free structured suffix modeling technique to accelerate Diffusion Language Models (DLMs). It partitions the suffix into local, middle, and tail regions, retaining varying numbers of tokens per region and incorporating previous decoding results into current token representations. Experiments on three DLMs show significant speedups—up to 72.81× in long‑sequence inference—while often improving performance, and the method is compatible with existing acceleration strategies.

By Zifeng Cheng, Keda Li, Zhiwei Jiang, Cong Wang, Fei Shen, Qing Gu

llms diffusion efficiency benchmarks

Hugging Face Trending Papers

Aug 24

Accelerating Diffusion Language Models via Structured Suffix Modeling

Diffusion Language Models (DLMs) exhibit strong parallel decoding capabilities by denoising multiple tokens in a single generation step. However, this parallelism comes with substantial computational...

llms diffusion efficiency benchmarks

arXiv AI

Jun 3

dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching

arXiv:2506. 06295v2 Announce Type: replace-cross Abstract: Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models.

By Zhiyuan Liu, Yicun Yang, Yaojie Zhang, Junjie Chen, Chang Zou, Qingyuan Wei, Shaobo Wang, Yichen Zhu, Linfeng Zhang

llms diffusion efficiency

arXiv Machine Learning

Jun 5

A Survey on Diffusion Language Models

arXiv:2508. 10875v3 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm.

By Tianyi Li, Mingda Chen, Bowei Guo, Zhiqiang Shen

llms diffusion nlp efficiency multimodal benchmarks

arXiv AI

Jun 2

BlockBatch: Multi-Scale Consensus Decoding for Efficient Diffusion Language Model Inference

arXiv:2605. 29233v2 Announce Type: replace-cross Abstract: Diffusion language models (dLLMs) generate text by iteratively denoising multiple token positions in parallel, offering an attractive alternative to strictly autoregressive decoding.

By Xiaoyou Wu, Cheng-Jhih Shih, Binfei Ji, Yong Liu, Yingyan Celine Lin

llms diffusion

One email a morning, machine-written

Related stories

Residual Context Diffusion Language Models

Accelerating Diffusion Language Models via Structured Suffix Modeling

Accelerating Diffusion Language Models via Structured Suffix Modeling

dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching

A Survey on Diffusion Language Models

BlockBatch: Multi-Scale Consensus Decoding for Efficient Diffusion Language Model Inference