AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct

Haoyang Zheng, Xinyang Liu, Xiangrui Kong, Nan Jiang, Zheyuan Hu, Weijian Luo, Wei Deng, Guang Lin

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Masked diffusion language model decoding · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add score decomposition (ablation)DiDi-Instruct · OpenWebText (8 NFEs)generative PPL: 33584 -> 62.236Improved
add coupled time t (ablation)DiDi-Instruct · OpenWebText (8 NFEs)generative PPL: 360.75 -> 62.236Improved
add omega(t) correction (ablation)DiDi-Instruct · OpenWebText (8 NFEs)generative PPL: 82.489 -> 62.236Improved
add pi(t) weighting (ablation)DiDi-Instruct · OpenWebText (8 NFEs)generative PPL: 69.656 -> 62.236Improved
add regularization (ablation)DiDi-Instruct · OpenWebText (8 NFEs)generative PPL: 84.594 -> 62.236Improved
add regularization (ablation)DiDi-Instruct · OpenWebText (128 NFEs)generative PPL: 18.446 vs 17.499 without itHurt
add guided inference (RGAS) (ablation)DiDi-Instruct · OpenWebText (8 NFEs)generative PPL: 88.274 -> 62.236Improved
add guided inference (RGAS) (ablation)DiDi-Instruct · OpenWebText (128 NFEs)generative entropy: 5.00 -> 5.15Improved
add score decomposition (cumulative) (ablation)Baseline without tricks · OpenWebText (8 NFEs)generative PPL: 803.922 -> 667.830Improved
add coupled time t (cumulative) (ablation)Baseline + score decomposition · OpenWebText (8 NFEs)generative PPL: 667.830 -> 101.019Improved
add guided inference (cumulative) (ablation)DiDi-Instruct with regularization · OpenWebText (8 NFEs)generative PPL: 88.274 -> 62.236Improved
distill with DiDi-Instruct instead of 1024-step teacherMDLM 169M · OpenWebText (16 NFEs)generative PPL: 38.53 -> 38.188Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy