AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Multivariate Diffusion Transformer with Decoupled Attention for High-Fidelity Mask-Text Collaborative Facial Generation

Yushe Cao, Dianxi Shi, Xing Fu, Xuechao Zou, Haikuo Peng, Xueqi Li, Chun Yu, Junliang Xing

AAAI 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 0 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
use unified tokenization of mask instead of channel concatenation (ablation)MDiTFace · MM-CelebA testMask accuracy (%): 88.73 -> 94.64Improved
use unified tokenization instead of channel concatenation (ablation)MDiTFace · MM-CelebA testIRS: 0.3699 -> 0.6993Improved
use unified tokenization instead of channel concatenation (ablation)MDiTFace · MM-CelebA testCMMD: 0.476 -> 0.482No clear effect
replace holistic tri-stream attention with improved decoupled attention (ablation)MDiTFace · MM-CelebA testMask accuracy (%): 94.72 -> 94.64No clear effect
use hard decoupled attention instead of improved decoupled attention (ablation)MDiTFace · MM-CelebA testMask accuracy (%): 94.64 -> 91.22Hurt
increase LoRA rank beyond 8 (ablation)MDiTFace · MM-CelebA testMask accuracy (%): 94.64 -> 94.73 (r=32)No clear effect
raise condition dropout probability p from 0.1 to 0.9 (ablation)MDiTFace · MM-CelebA testMask accuracy (%): 94.64 -> 84.00Hurt
raise condition dropout probability p from 0.1 to 0.9 (ablation)MDiTFace · MM-CelebA testCLIP.T (%): 26.75 -> 27.02Mixed

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