arXiv Machine Learning July 7, 2026 By Byoungkwon Kim, Minhyuk Sung

Tensor-Train Joint Modeling for Few-Step Discrete Diffusion

Read the original on arXiv Machine Learning →

arXiv:2607. 03788v1 Announce Type: new Abstract: Discrete diffusion promises orders-of-magnitude faster generation than autoregressive (AR) models for sequential discrete data, yet its full potential of few-step generation has remained out of reach due to a fundamental structural limitation.

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

arXiv AI

Jul 21

Breaking the Factorization Barrier in Diffusion Language Models

arXiv:2603. 00045v3 Announce Type: replace-cross Abstract: Diffusion language models theoretically allow for efficient parallel generation but are practically hindered by the ``factorization barrier'': the assumption that simultaneously predicted tokens are independent.

By Ian Li, Zilei Shao, Benjie Wang, Rose Yu, Guy Van den Broeck, Anji Liu

llms diffusion reinforcement-learning

arXiv Machine Learning

Jul 9

Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling

arXiv:2607. 06841v1 Announce Type: cross Abstract: Diffusion models offer a powerful framework for sampling from complex probability densities by learning to reverse a noising process.

By Robert Gruhlke, Julius Berner, David Sommer, Lorenz Richter

diffusion efficiency

arXiv Machine Learning

Jun 3

Bayesian Tensor Decomposition with Diffusion Model Prior

arXiv:2606. 03212v1 Announce Type: new Abstract: Low-rank tensor decomposition (TD) is usually effective on clean, fully observed data, but it often degrades under severe missingness or noise.

By Zerui Tao, Qibin Zhao

diffusion efficiency benchmarks safety

arXiv Machine Learning

Jun 2

Consistent Diffusion Language Models

arXiv:2605. 00161v2 Announce Type: replace Abstract: Diffusion language models (DLMs) are an attractive alternative to autoregressive models because they promise sublinear-time, parallel generation, yet practical gains remain elusive as high-quality samples still demand hundreds of refinement steps.

By Hasan Amin, Yuan Gao, Yaser Souri, Subhojit Som, Ming Yin, Rajiv Khanna, Xia Song

llms diffusion efficiency

arXiv AI

Jun 12

HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens

arXiv:2512. 15133v3 Announce Type: replace-cross Abstract: Proteins inherently possess a consistent sequence-structure duality.

By Yi Zhou, Haohao Qu, Yunqing Liu, Shanru Lin, Le Song, Wenqi Fan

llms diffusion fine-tuning efficiency multimodal benchmarks

arXiv Machine Learning

Jul 31

Latent-Kernel Discrete Flow Maps for Few-Step Generation

arXiv:2607. 27529v1 Announce Type: new Abstract: Discrete diffusion and flow-matching models denoise a sequence over many steps, but to keep each step cheap, they factorize the transition across positions and decide every token independently.

By Mansoor Ahmed, Yue-Tsz Fan, Hemanth Venkateswara, Murray Patterson

llms diffusion benchmarks

Related stories

Breaking the Factorization Barrier in Diffusion Language Models

Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling

Bayesian Tensor Decomposition with Diffusion Model Prior

Consistent Diffusion Language Models

HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens

Latent-Kernel Discrete Flow Maps for Few-Step Generation