Hugging Face Trending Papers July 27, 2026

Rethinking the Generation Order of Block Diffusion Language Models

Read the original on Hugging Face Trending Papers →

Diffusion language models enable flexible arbitrary-order generation, but existing sampling methods are mostly designed for early masked diffusion models (MDMs). In this work, we study sampling for recent block diffusion language models (BDLMs).

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 Hugging Face Trending Papers.

arXiv AI

Jun 9

Unified Energy for Invariant and Independent Decoding in Diffusion Language Models

arXiv:2606. 09159v1 Announce Type: cross Abstract: Diffusion Language Models (DLMs) enable parallel text generation by iteratively denoising a full sequence, offering attractive flexibility compared to auto-regressive (AR) decoding.

By Yuchen Yan, Minkai Xu, Zaiquan Yang, Yatao Bian

llms diffusion

arXiv Machine Learning

Jul 8

Diffusion Language Model Parallel Decoding via Product-of-Experts Bridge

arXiv:2606. 08048v1 Announce Type: cross Abstract: Diffusion language models (DLMs) offer substantial speed advantages through parallel decoding, but the lack of token dependencies limits generation quality compared to autoregressive (AR) models.

By Juntong Shi, Brian L. Trippe, Jure Leskovec, Stefano Ermon, Minkai Xu

llms diffusion

arXiv Machine Learning

Jun 30

Understanding Evaluation Illusion in Diffusion Large Language Models

arXiv:2606. 29228v1 Announce Type: cross Abstract: Despite the capability of parallel decoding, diffusion large language models (dLLMs) require many denoising steps to maintain generation quality, motivating recent research on efficient decoding strategies.

By Hengxiang Zhang, Jiaxi Ren, Hongxin Wei

llms diffusion

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 Computation and Language

Sep 14

Representation-based Masked Diffusion Model

The paper introduces Representation-based Masked Diffusion Model (RMDM), a new framework for language modeling that improves upon existing Masked Diffusion Models by incorporating global semantic guidance. RMDM encodes text into a continuous semantic space with a pretrained encoder, normalizes this representation to a Gaussian prior via an invertible transformation, and then trains a masked diffusion model conditioned on this latent representation to coordinate parallel token updates. Experiments show that RMDM yields higher generation quality, especially when using aggressive few‑step sampling.

By Yangrong Hu, Ding Huang, Xueyu Zhou, Jian Huang

diffusion

arXiv Machine Learning

Jun 30

Adaptive Block Diffusion: Resolving Training-Inference Mismatch in Diffusion Language Models

arXiv:2606. 29275v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) are typically trained under fixed context structures, restricting denoising to predetermined token subsets.

By Gagan Jain

llms diffusion

One email a morning, machine-written

Related stories

Unified Energy for Invariant and Independent Decoding in Diffusion Language Models

Diffusion Language Model Parallel Decoding via Product-of-Experts Bridge

Understanding Evaluation Illusion in Diffusion Large Language Models

Mean-Field Parallel Decoding for Discrete Diffusion Language Models

Representation-based Masked Diffusion Model

Adaptive Block Diffusion: Resolving Training-Inference Mismatch in Diffusion Language Models