AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing

Iskander Azangulov, Teodora Pandeva, Niranjani Prasad, Javier Zazo, Sushrut Karmalkar

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
use PUNT conditional-independence-tested parallel unmasking instead of top-k, EB-sampler and Dilated samplersDream 7B and LLaDA 1.5 · IFEval and MTBench (long-form)accuracy vs forward evaluations: up to 16% higher accuracy on IFEvalImproved
use PUNT on short-answer tasks (GSM8K, HumanEval, MBPP)LLaDA, MBPP temperature 0.7 · MBPP pass@1 vs NFEpass@1No clear effect
measure by denoising steps instead of NFE for short-answer tasksPUNT on MBPP (LLaDA) · MBPPpass@1 vs stepsImproved
vary the independence threshold epsilon (0.01 to 0.32) (ablation)PUNT · MTBench 1024-token generation (LLaDA)parallel sampling KL errorNo clear effect
vary hyperparameters of PUNT (ablation)PUNT · alignment benchmarksaccuracyNo clear effect
apply PUNT to protein generation with MemDLMMemDLM (ESM-2 150M masked diffusion) · unconditional membrane protein generationmean pLDDTImproved

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