Hugging Face Trending Papers June 10, 2026

Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models

Read the original on Hugging Face Trending Papers →

Diffusion large language models (dLLMs) offer an efficient alternative to autoregressive models through parallel decoding, yet existing post-training methods largely rely on random masking strategies that overlook intrinsic token dependencies. In this work, we present an empirical analysis of attention in dLLMs and show that tokens attending more strongly to unmasked context exhibit greater generation stability and play a critical role in reasoning.

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 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 Machine Learning

Jun 5

Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models

arXiv:2511. 21338v2 Announce Type: replace Abstract: Masked Diffusion Language Models (MDLMs) have recently emerged as a promising alternative to Autoregressive Language Models (ARLMs), leveraging a denoising objective that, in principle, should enable more uniform context utilisation.

By Julianna Piskorz, Cristina Pinneri, Alvaro Correia, Motasem Alfarra, Risheek Garrepalli, Christos Louizos

llms diffusion fine-tuning safety

arXiv Machine Learning

Aug 4

Just on Time: Token-Level Early Stopping for Diffusion Language Models

arXiv:2602. 11133v2 Announce Type: replace Abstract: Diffusion language models generate text through iterative refinement, a process that is often computationally inefficient because many tokens reach stability long before the final denoising step.

By Zakhar Kohut, Severyn Shykula, Mykola Vysotskyi, Serhii Dmytryshyn, Dmytro Khamula, Michal Zakrzewski, Damian Rynczak, Jacek Ma{\l}ecki, Taras Rumezhak, Volodymyr Karpiv

llms diffusion nlp fine-tuning benchmarks

arXiv AI

Sep 2

Denoising Diffusion Generative Models Secretly Calculate Attentions

arXiv:2609.00885v1 Announce Type: new Abstract: Denoising diffusion models are the dominant architecture for image generation, whereas most natural language generation and modeling are primarily hand...

By Farzan Haddadi, Leila Monfared, Ebrahim Rezaii, Mohammadreza Malek-Mohammadi, Pejman Zakalvand, Narges Mokhtari

llms diffusion

Hugging Face Trending Papers

Jun 3

SAID: Accelerating Diffusion-Based Language Models via Scaffold-Aware Iterative Decoding

Diffusion large language models (DLLMs) enable non-autoregressive generation by iteratively denoising corrupted token sequences with bidirectional context. Despite their ability to update multiple positions in parallel, inference remains costly due to the many denoising steps required for high-quality generation.

llms diffusion benchmarks

arXiv AI

Jun 2

FLARE: Diffusion for Hybrid Language Model

arXiv:2606. 01774v1 Announce Type: cross Abstract: Autoregressive (AR) large language models (LLMs) have achieved broad practical success, but sequential decoding remains a key bottleneck for low-latency deployment.

By Yuchen Zhu, Jing Shi, Chongjian Ge, Hao Tan, Yiran Xu, Wanrong Zhu, Jason Kuen, Koustava Goswami, Rajiv Jain, Yongxin Chen, Molei Tao, Jiuxiang Gu

llms diffusion efficiency data-engineering

One email a morning, machine-written

Related stories

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

Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models

Just on Time: Token-Level Early Stopping for Diffusion Language Models

Denoising Diffusion Generative Models Secretly Calculate Attentions

SAID: Accelerating Diffusion-Based Language Models via Scaffold-Aware Iterative Decoding

FLARE: Diffusion for Hybrid Language Model