Hugging Face Trending Papers June 10, 2026

Re-evaluating Confidence Remasking in Masked Diffusion Language Models

Read the original on Hugging Face Trending Papers →

Masked diffusion language models (dLLMs) have recently emerged as a competitive alternative to autoregressive language models, with the promise of faster inference via parallel token generation. A notable limitation of the masked formulation, however, is that once a token has been unmasked it can no longer be revised, leaving dLLMs vulnerable to early sampling mistakes.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Jun 11

Re-evaluating Confidence Remasking in Masked Diffusion Language Models

arXiv:2606. 12232v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) have recently emerged as a competitive alternative to autoregressive language models, with the promise of faster inference via parallel token generation.

By Stipe Frkovic, Metod Jazbec, Dan Zhang, Christian A. Naesseth, Ilija Bogunovic, Eric Nalisnick

llms diffusion

arXiv AI

Jun 10

Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models

arXiv:2606. 10829v1 Announce Type: cross Abstract: Masked diffusion language models can reduce inference steps by revealing multiple tokens per denoising iteration, but this parallelism is fragile: positions that are individually confident may be unsafe to commit together when their predictions are coupled.

By Yusuf Sahin, Ahmed Rockey Saikia, Volkan Cevher, Paolo Favaro

llms rag diffusion benchmarks

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 AI

Jun 3

$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction

arXiv:2604. 18995v2 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction.

By Zhenbang Du, Kejing Xia, Xinrui Zhong, Yonggan Fu, Nicolai Oswald, Binfei Ji, Brucek Khailany, Pavlo Molchanov, Yingyan Lin

llms diffusion fine-tuning efficiency

arXiv Machine Learning

Jun 4

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models

arXiv:2606. 04446v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive large language model inference by drafting multiple tokens and verifying them in a single target-model forward pass.

By Liyuan Zhang, Jiarui Zhang, Jinwei Yao, Ran Yan, Yuchen Yang, Jiahao Zhang, Tongkai Yang, Yi Wu, Binhang Yuan

llms diffusion

arXiv Machine Learning

Jun 11

Teaching Diffusion to Speculate Left-to-Right

arXiv:2606. 11552v1 Announce Type: cross Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference costs due to inherently sequential token generation.

By Lexington Whalen, Yuki Ito, Ryo Sakamoto

llms diffusion benchmarks safety

Related stories

Re-evaluating Confidence Remasking in Masked Diffusion Language Models

Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models

Understanding Evaluation Illusion in Diffusion Large Language Models

$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction

D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models

Teaching Diffusion to Speculate Left-to-Right