arXiv AI June 3, 2026 By Zhiyuan Liu, Yicun Yang, Yaojie Zhang, Junjie Chen, Chang Zou, Qingyuan Wei, Shaobo Wang, Yichen Zhu, Linfeng Zhang

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

Read the original on arXiv AI →

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

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 26

Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM

arXiv:2606. 26120v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) offer a promising alternative to autoregressive models, excelling in text generation tasks due to their bidirectional attention mechanisms.

By Tianyi Wu, Xiaoxi Sun, Yanhua Jiao, Yulin Li, Yixin Chen, YunHao Cao, YiQi Hu, Zhuotao Tian

llms diffusion efficiency benchmarks

arXiv Machine Learning

Aug 10

Retrofitting Linear Attention into Diffusion Language Models

arXiv:2608. 06628v1 Announce Type: new Abstract: Diffusion language models (dLLMs) offer a promising alternative to autoregressive models by accelerating inference through parallel decoding.

By Jinha Kim, Younghun Roh, Jaeyeon Kim

llms diffusion efficiency benchmarks

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

arXiv Machine Learning

Aug 4

Orchestrating Dual-Boundaries: An Arithmetic Intensity Inspired Acceleration Framework for Diffusion Language Models

arXiv:2511. 21759v2 Announce Type: replace-cross Abstract: Diffusion-based large language models (dLLMs) have recently gained significant attention for their exceptional performance and inherent potential for parallel decoding.

By Linye Wei, Wenjue Chen, Pingzhi Tang, Xiaotian Guo, Le Ye, Runsheng Wang, Meng Li

llms diffusion

arXiv AI

Jul 21

LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Models

arXiv:2607. 16339v1 Announce Type: new Abstract: Diffusion-based Large Language Models(DLLMs) enable parallel generation via Semi-Autoregressive (SAR) decoding in text generation.

By Xingru Chen, Zelang Liang, Yongjia Ma, Jiqing Zhan, Shuling Yang, Lian Wen, Kun Zhan

llms rag diffusion efficiency

Related stories

Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM

Retrofitting Linear Attention into Diffusion Language Models

A Survey on Diffusion Language Models

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

Orchestrating Dual-Boundaries: An Arithmetic Intensity Inspired Acceleration Framework for Diffusion Language Models

LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Models