arXiv Machine Learning August 10, 2026 By Meihua Dang, Jiaqi Han, Minkai Xu, Kai Xu, Akash Srivastava, Stefano Ermon

Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement

Read the original on arXiv Machine Learning →

arXiv:2507. 08390v5 Announce Type: replace Abstract: Discrete diffusion models have recently emerged as strong alternatives to autoregressive language models, matching their performance through large-scale training.

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

3d ago

On Trajectory-Aware Training for Masked Diffusion Language Models

arXiv:2609.37974v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The m...

By Manuel Madeira, Amitis Shidani, Alice Bizeul, Victor Turrisi, Louis B\'ethune, Bhavika Devnani, Dan Busbridge, Pierre Ablin, Jo\~ao Monteiro

llms diffusion fine-tuning safety

arXiv Machine Learning

Aug 21

Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo

arXiv:2608. 20123v1 Announce Type: cross Abstract: We study inference-time control for text generation in discrete diffusion language models, where the goal is to steer sampling toward sequence-level rewards without retraining.

By Lohithsai Yadala Chanchu, Hany Abdulsamad, Christian A. Naesseth

llms diffusion safety

arXiv AI

Jun 2

Efficient Weighted Sampling via Score-based Generative Models

arXiv:2502. 04646v2 Announce Type: replace-cross Abstract: Weighted sampling -- sampling from a probability density function (PDF) proportional to the product of a base PDF and a weight function -- is a fundamental technique with wide-ranging applications in variance reduction, biased sampling, data augmentation, and more.

By Heasung Kim, Taekyun Lee, Hyeji Kim, Gustavo de Veciana

diffusion benchmarks

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 AI

Jun 19

Diffusion Language Models: An Experimental Analysis

arXiv:2606. 19475v1 Announce Type: new Abstract: Large Language Models (LLMs) have revolutionized language modeling through autoregressive generation, enabling strong performance across a wide range of tasks.

By Thomas Bertolani, Davide Bucciarelli, Leonardo Zini, Marcella Cornia, Lorenzo Baraldi

llms diffusion benchmarks

arXiv AI

Sep 18

Zarya: A Hybrid Autoregressive--Masked Diffusion Language Model with Flexible Training and Dual-Mode Inference

Zarya is a hybrid language model that jointly trains an autoregressive objective and a masked-diffusion objective within a single architecture. It structures training data into variable-size slots and uses a curriculum that gradually increases slot granularity, allowing a smooth transition from fine-grained AR learning to coarse-grained diffusion learning. At inference, Zarya offers two decoding modes—MDM sampling with first-hitting denoising and slotted speculative decoding that interleaves diffusion-based selection with autoregressive infilling—while fully decoupling training and inference regimes and supporting extensive configurability.

By Leonid Sinev, Ilya Koziev, Vladislav Leshchuk

llms diffusion efficiency benchmarks

One email a morning, machine-written

Related stories

On Trajectory-Aware Training for Masked Diffusion Language Models

Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo

Efficient Weighted Sampling via Score-based Generative Models

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

Diffusion Language Models: An Experimental Analysis

Zarya: A Hybrid Autoregressive--Masked Diffusion Language Model with Flexible Training and Dual-Mode Inference