arXiv AI June 8, 2026 By Jonathan Lys, Vincent Gripon, Axel Marmoret, Lukas Mauch, Fabien Cardinaux, Ghouthi Boukli Hacene, Bastien Pasdeloup

D5P4: Partition Determinantal Point Process for Diversity in Parallel Discrete Diffusion Decoding

Read the original on arXiv AI →

arXiv:2603. 19146v2 Announce Type: replace Abstract: Discrete diffusion models are promising alternatives to autoregressive approaches for text generation, yet their decoding methods remain under-studied.

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 AI.

arXiv AI

Jun 2

IDLM: Inverse-distilled Diffusion Language Models

arXiv:2602. 19066v2 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) have recently achieved strong results in text generation.

By David Li, Nikita Gushchin, Dmitry Abulkhanov, Eric Moulines, Ivan Oseledets, Maxim Panov, Alexander Korotin

llms diffusion efficiency

arXiv Machine Learning

Jun 25

Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding

arXiv:2601. 17917v3 Announce Type: replace Abstract: Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation, leveraging parallel decoding and bidirectional attention to achieve superior global coherence compared to autoregressive models.

By Zhongyu Xiao, Zhiwei Hao, Jianyuan Guo, Yong Luo, Jia Liu, Jie Xu, Han Hu

llms diffusion efficiency

arXiv AI

Jun 3

Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Models

arXiv:2601. 12247v3 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) present a promising non-sequential paradigm for text generation, distinct from standard autoregressive (AR) approaches.

By Miao Li, Hanyang Jiang, Sikai Cheng, Hengyu Fu, Yuhang Cai, Baihe Huang, Tinghan Ye, Xuanzhou Chen, Pascal Van Hentenryck

llms diffusion benchmarks

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

Jun 5

Self-Augmenting Retrieval for Diffusion Language Models

arXiv:2606. 06474v1 Announce Type: cross Abstract: Discrete diffusion language models generate text by iteratively denoising an entire response in parallel.

By Paul J\"unger, Justin Lovelace, Linxi Zhao, Dongyoung Go, Kilian Q. Weinberger

llms rag diffusion efficiency benchmarks

arXiv AI

Oct 2

Hierarchical Continuous Diffusion Language Models

Hierarchical Continuous Diffusion Language Models (HC‑DLM) combine discrete token generation with a continuous latent trajectory in a single denoising process, addressing the independence bottleneck of parallel decoding in discrete diffusion models. The training objective is derived from a variational bound on token likelihood, and the latent state is the sole persistent generative element, with tokens read out and fed back at each step. Experiments on Sudoku, Countdown, and LM1B show HC‑DLM outperforming both discrete and continuous diffusion baselines in puzzle accuracy and generative perplexity.

By Hui Ren, Zihan Li, Chang Liu, Huidong Liu, Alexander Schwing

llms diffusion

One email a morning, machine-written

Related stories

IDLM: Inverse-distilled Diffusion Language Models

Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding

Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Models

Unified Energy for Invariant and Independent Decoding in Diffusion Language Models

Self-Augmenting Retrieval for Diffusion Language Models

Hierarchical Continuous Diffusion Language Models