AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

DPad: Efficient Diffusion Language Models with Suffix Dropout

Xinhua Chen, Sitao Huang, Cong Guo, Chiyue Wei, Yintao He, Jianyi Zhang, Hai Helen Li, Yiran Chen

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Masked diffusion language model decoding · 35 citations (OpenAlex)

This paper tried a common change: Add dropout

add DPad suffix dropout · GSM8K (4-shot) · strict-match accuracy: 37.38 -> 63.84 Improved

What 795 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 DPad suffix dropoutLLaDA-Instruct · GSM8K (4-shot)strict-match accuracy: 37.38 -> 63.84Improved
add DPad suffix dropoutLLaDA-Instruct · MATH (4-shot)strict-match accuracy: 8.42 -> 28.04Improved
add DPad suffix dropoutLLaDA-Instruct · MBPP (3-shot)pass@1: 15.00 -> 40.40Improved
add DPad suffix dropoutLLaDA-1.5 · GSM8K (4-shot)flexible-match accuracy: 80.59 -> 80.14No clear effect
add DPad suffix dropoutDream-Base · GSM8K (4-shot)strict-match accuracy: 74.37 -> 75.06No clear effect
add DPad on top of parallel decodingLLaDA-Instruct · MBPP (3-shot)latency speedup: 4.36× -> 10.32×Improved
add DPad on top of parallel decodingDream-Base · HumanEval (0-shot)latency speedup: 2.01× -> 7.01×Improved
add DPad to vanilla Dream at 2048 tokensDream-Base · HumanEval (2048)accuracy: 7.32% accuracy degradationHurt
extend generation length to 1024 tokens (1-shot) (ablation)LLaDA-1.5 · GSM8Klatency speedup of DPad: 1.51× -> 20.3×Improved
use Gaussian instead of uniform dropout (ablation)LLaDA-1.5 · GSM8K (window/budget sweep)flexible and strict-match accuracyImproved
add DPad at 1-shotLLaDA-1.5 · GSM8K (1-shot)strict-match accuracy: baseline ~60% -> ~50% vs DPad ~78% -> ~74%Improved
use k=1 Gaussian decay at 25.0% density (ablation)LLaDA-Instruct · GSM8K subset (50 samples)flexible-match accuracyHurt

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