AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster

Grigory Bartosh, Teodora Pandeva, Sushrut Karmalkar, Javier Zazo

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Denoising diffusion probabilistic models · 2 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
reduce sampling steps from T=100 to T=10FLDD · ROCStoriesMAUVE: 0.538 -> 0.511Mixed
reduce sampling steps from T=100 to T=10FLDD · ROCStoriesPPL: 55.2 -> 60.5Hurt
reduce sampling steps from T=100 to T=10FLDD · QM9FCD: 0.328 -> 0.385Hurt
reduce sampling steps from T=100 to T=10FLDD · ZINC250kFCD: 8.487 -> 10.414Hurt
reduce sampling steps from T=100 to T=10FLDD · QM9Validity: 99.67 -> 99.08Hurt
learn masking schedule conditioned on data instead of uniform unmasking (ablation)masked diffusion model · binarized MNIST (4 steps)sample qualityImproved
use FLDD instead of conventional discrete diffusion with few stepsFLDD · ROCStoriesMAUVE: 0.511 (T=10) vs 0.598 (SEDD, step count not stated)Mixed

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