← Back to all news
arXiv Machine Learning By Sitan Chen, Liye Wang

Parallelism, critical windows, and separations among diffusion language models

Read the original on arXiv Machine Learning →

The paper compares the parallelism capabilities of three diffusion large language model paradigms—masked, uniform, and Gaussian diffusion. It proves that uniform and Gaussian diffusion can sample with a number of forward passes scaling with the dual total correlation of the distribution, potentially much less than the context length, whereas masked diffusion may require more passes. The study establishes a provable separation in parallelism, showing that masked diffusion’s critical windows are asymptotically narrower than those of the other two approaches.

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.

Related stories

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
llmsragdiffusionbenchmarks
More like this →
arXiv Machine Learning
Sep 11

Continuous Diffusion Scales Competitively with Discrete Diffusion for Language

The paper revisits the continuous diffusion language model Plaid and introduces RePlaid, aligning its architecture with modern discrete diffusion models. RePlaid achieves a compute gap of only 20× compared to autoregressive models, surpasses Duo with fewer parameters, and outperforms MDLM in over‑trained settings. On OpenWebText, RePlaid sets a new state‑of‑the‑art continuous diffusion perplexity of 22.1 and demonstrates superior generation quality, while theoretical analysis links likelihood‑based training to linear cross‑entropy over time and structured embedding geometries.

By Zhihan Yang, Wei Guo, Shuibai Zhang, Subham Sekhar Sahoo, Yongxin Chen, Arash Vahdat, Morteza Mardani, John Thickstun
llmsragdiffusionbenchmarks
More like this →