AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Dual-Path Condition Alignment for Diffusion Transformers

Changhao Peng, Yuqi Ye, Shuangjun Du, Wenxu Gao, Wei Gao

ICLR 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis

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 dual-path sampling to DDT (ablation)DDT-L/2 · ImageNet 256x256 (L/2, 400K iters, no CFG)FID: 14.9 -> 12.5Improved
add condition alignment on top of dual-path sampling (ablation)DDT-L/2 · ImageNet 256x256 (L/2, 400K iters, no CFG)FID: 12.5 -> 11.1Improved
resample both t and noise instead of only t (ablation)DUPA-L/2 · ImageNet 256x256 (L/2, 400K iters, no CFG)FID: 13.2 -> 11.1Improved
resample both t and noise instead of only noise (ablation)DUPA-L/2 · ImageNet 256x256 (L/2, 400K iters, no CFG)FID: 12.4 -> 11.1Improved
align at depth 8 rather than 4 or 16 (ablation)DUPA-L/2 · ImageNet 256x256 (L/2, 400K iters, no CFG)FID: 11.8 (depth 4), 12.1 (depth 16) vs 11.1 (depth 8)Improved
cosine similarity instead of NT-Xent (ablation)DUPA-L/2 · ImageNet 256x256 (L/2, 400K iters, no CFG)FID: 11.6 -> 11.1Improved
vary lambda from 0.25 to 1 (ablation)DUPA-L/2 · ImageNet 256x256 (L/2, 400K iters, no CFG)FID: 11.2, 11.1, 11.1, 11.1No clear effect
increase noising times K from 2 to 4 (ablation)DUPA-L/2 · ImageNet 256x256 (L/2, 400K iters, no CFG)FID: 11.1 -> 10.7No clear effect
double batch size of DDT instead of using dual-path (ablation)DDT-L/2 · ImageNet 256x256 (L/2, 400K iters, no CFG)FID: 13.9 vs DUPA 11.1Hurt
replace SiT with DUPA across model sizesSiT/DDT · ImageNet 256x256 (400K steps, no CFG)FID: B/2 33.0 -> 25.2; L/2 18.8 -> 11.1; XL/2 17.2 -> 8.71Improved
self-alignment without external encoder vs REPADUPA-XL/2 · ImageNet 256x256 (with CFG)FID: 1.46 (400 ep) vs REPA 1.42 (800 ep)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