arXiv Machine Learning June 2, 2026 By Bumjun Kim, Dongjae Jeon, Moongyu Jeon, Albert No

DAPD: Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs

Read the original on arXiv Machine Learning →

arXiv:2603. 12996v2 Announce Type: replace Abstract: Parallel decoding for Diffusion LLMs (dLLMs) is difficult because each denoising step provides only token-wise marginal distributions, while unmasking multiple tokens simultaneously requires accounting for inter-token dependencies.

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 4

Supportive Token Revealing for Fast Diffusion Language Model Decoding

arXiv:2606. 04236v1 Announce Type: cross Abstract: Discrete diffusion language models can generate text efficiently by updating multiple masked positions in parallel, but this parallelism introduces a quality-latency trade-off.

By Giries Abu Ayoub, Mario Barbara, Llu\'is Pastor-P\'erez, Tanja Bien, Aneesh Barthakur, Alaa Maalouf, Loay Mualem

llms diffusion benchmarks

arXiv Computation and Language

Aug 28

Dependency-Aware Revocable Decoding for Efficient Diffusion Large Language Model Inference

The paper introduces Dependency-Aware Revocable Decoding (DARD), a training‑free framework for diffusion large language models that separates tokens into masked, candidate, and unmasked states. DARD verifies candidate tokens using a selective context that excludes less reliable tokens and adaptively regulates their influence on subsequent decoding. Experiments on 12 textual and multimodal benchmarks across three open‑source dLLMs show that DARD improves the speed‑quality Pareto frontier, achieving a 2.71× speedup and a 4.35‑point CIDEr gain over Saber on Flickr30K.

By Wooje Park, Insu Lee, Minyoung Noh, Jaeyun Jang, Sungmin Lee, Kyuhong Shim, Byonghyo Shim

llms diffusion multimodal benchmarks

arXiv AI

Jun 2

DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention

arXiv:2603. 08026v2 Announce Type: replace-cross Abstract: Masked diffusion language models enable parallel token decoding, providing a promising alternative to the sequential nature of autoregressive generation.

By Younjoo Lee, Seungkyun Dan, Junghoo Lee, Jaiyoung Park, Jung Ho Ahn

llms diffusion efficiency benchmarks

arXiv Computation and Language

Sep 15

DA-DLM: Explicitly Modeling Token Dependencies in Diffusion Language Models

arXiv:2609.15070v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) generate text by iteratively denoising a masked sequence, independently predicting multiple tokens at each step. This...

By Pengyu Ji, Zichen Zhang, Xiang Hu, Kewei Tu

llms diffusion nlp

arXiv Machine Learning

Jun 16

Mean-Field Parallel Decoding for Discrete Diffusion Language Models

arXiv:2606. 15805v1 Announce Type: new Abstract: Discrete diffusion language models enable parallel token generation, offering a pathway to low-latency decoding.

By Tamim Zoabi, Ameen Ali, Liran Ringel, Lior Wolf

llms diffusion benchmarks

arXiv AI

Jul 24

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding

arXiv:2607. 20467v1 Announce Type: new Abstract: While parallel decoding is central to the efficiency of Diffusion Large Language Models (dLLMs), current strategies are often hindered by overly conservative confidence thresholds.

By Yanhua Jiao, Tianyi Wu, Xiaoxi Sun, Yulin Li, HuiLing Zhen, Libo Qin, Baotian Hu, Zhuotao Tian, Min Zhang

llms diffusion benchmarks

One email a morning, machine-written

Related stories

Supportive Token Revealing for Fast Diffusion Language Model Decoding

Dependency-Aware Revocable Decoding for Efficient Diffusion Large Language Model Inference

DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention

DA-DLM: Explicitly Modeling Token Dependencies in Diffusion Language Models

Mean-Field Parallel Decoding for Discrete Diffusion Language Models

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding