AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Unveiling the Potential of Diffusion Large Language Model in Controllable Generation

Zhen Xiong, Yujun Cai, Zhecheng Li, Yiwei Wang

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Masked diffusion language model decoding

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 schema scaffolding (S3) instead of direct prompting (ablation)LLaDA-1.5 · WikiBio, 8 stepsSchema Compliance: 0.312 -> 0.994Improved
add schema scaffolding (S3) (ablation)LLaDA-1.5 · WikiBio, 32 stepsSchema Compliance: 0.792 -> 0.997Improved
add 3 few-shot examples to baseline (ablation)LLaDA-1.5 · WikiBio, 8 stepsSchema Compliance: 0.312 -> 0.443Improved
add complete schema to the prompt (ablation)LLaDA-1.5 · WikiBio, 16 stepsSchema Compliance: 0.576 -> 0.738Improved
add S3 instead of baseline (ablation)LLaDA-1.5 · WikiBio, 8 stepsF1: 0.068 -> 0.130Improved
add few-shot examples (ablation)LLaDA-1.5 · WikiBio, 8 stepsF1: 0.068 -> 0.068No clear effect
use vanilla scaffolding S2 (fixed mask slots) instead of baseline (ablation)LLaDA-1.5 · WikiBio, 8 stepsHallucination Rate: 0.404 -> 0.465Hurt
replace S2 by S3 with null placeholder for surplus slots (ablation)LLaDA-1.5 · WikiBio, 8 stepsHallucination Rate: 0.465 -> 0.340Improved
use vanilla S2 scaffolding (ablation)LLaDA-1.5 · WikiBioprecisionHurt
increase denoising steps from 8 to 32 (ablation)baseline LLaDA-1.5 · WikiBioSchema Compliance: 0.312 -> 0.792Improved
increase denoising steps (ablation)LLaDA-1.5 content fidelity · WikiBiocontent fidelityNo clear effect
add few-shot examples (ablation)LLaDA-1.5 · WikiBio, 8 stepsHallucination Rate: 0.404 -> 0.366Improved

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