AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Denoising Token Prediction in Masked Autoregressive Models

Ting Yao, Yehao Li, Yingwei Pan, Zhaofan Qiu, Tao Mei

ICCV 2025 · Image generation › Fast diffusion sampling · approach: Discrete diffusion solvers · 6 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 Transformer-based diffusion head (cross-attention over all tokens) (ablation)MAR-B · ImageNet 256 (ablation, De-MAR-B, w/ CFG)FID: 2.31 -> 2.10Improved
add denoising head with noised unmasked inputs (ablation)MAR-B · ImageNet 256 (ablation, De-MAR-B, w/ CFG)FID: 2.31 -> 2.22Improved
add denoising head on top of Transformer diffusion head (ablation)MAR-B + Diff. Head · ImageNet 256 (ablation, De-MAR-B, w/ CFG)FID: 2.10 -> 2.04Improved
add Transformer diffusion head on top of denoising head (ablation)MAR-B + De. Head · ImageNet 256 (ablation, De-MAR-B, w/ CFG)FID: 2.22 -> 2.04Improved
add Transformer diffusion head (ablation)MAR-B · ImageNet 256 (ablation, De-MAR-B, w/ CFG)IS: 281.7 -> 283.1Improved
add denoising head (ablation)MAR-B · ImageNet 256 (ablation, De-MAR-B, w/ CFG)Recall: 0.57 -> 0.57No clear effect
add both heads (De-MAR-B vs MAR-B) (ablation)MAR-B · ImageNet 256 (ablation, De-MAR-B, w/ CFG)Recall: 0.57 -> 0.59Improved
replace MAR with De-MAR (both heads)MAR-B · ImageNet 256 (class-cond., w/o CFG)FID: 3.48 -> 3.14Improved
replace MAR with De-MAR (both heads)MAR-L · ImageNet 256 (class-cond., w/ CFG)FID: 1.78 -> 1.66Improved
replace MAR with De-MAR (both heads)MAR-H · ImageNet 256 (class-cond., w/ CFG)FID: 1.55 -> 1.47Improved
replace MAR with De-MAR (both heads)MAR · MS-COCO 256 text-to-imageFID: 6.36 -> 5.27Improved
scale De-MAR from Base to HugeDe-MAR · ImageNet 256 (class-cond., w/ CFG)FID: 2.04 -> 1.66 -> 1.47Improved

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