Large Language Diffusion Models — interactive visual explainer | Rudrite Research

Researchers Nie et al. published a paper on arXiv in 2025 introducing an 8-billion-parameter diffusion language model that generates text by un-masking tokens rather than left-to-right, rivaling autoregressive models. An interactive visual explainer of the paper is available online.

Large Language Diffusion Models Generate text by un-masking, not left-to-right — an 8B diffusion LM that rivals autoregression. Nie et al. · arXiv 2025 · Model Architectures. Read the paper ↗ https://arxiv.org/abs/2502.09992 A free, interactive, animated visual explainer of Large Language Diffusion Models — every exhibit computed from the real formulas, with verbatim quotes from the source. Questions - What is Large Language Diffusion Models? - Generate text by un-masking, not left-to-right — an 8B diffusion LM that rivals autoregression. - Who published Large Language Diffusion Models, and where? - Nie et al. — arXiv 2025 arXiv:2502.09992 . - Where can I find a visual explainer of Large Language Diffusion Models? - Right here — a free, interactive, animated walkthrough of the whole paper, with exhibits computed from the real formulas and verbatim quotes from the source.