AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Mixture of Global and Local Experts With Diffusion Transformer for Controllable Face Generation

Xuechao Zou, Shun Zhang, Xing Fu, Yue Li, Kai Li, Yushe Cao, Congyan Lang, Pin Tao, Junliang Xing

TPAMI 2026 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 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
add local experts to the global expert (ablation)Face-MoGLE · MM-CelebA-HQ multimodal ablationFID: 30.36 -> 22.24Improved
add global expert to local experts (ablation)Face-MoGLE · MM-CelebA-HQ multimodal ablationFID: 33.62 -> 22.24Improved
add local experts to the global expert (ablation)Face-MoGLE · MM-CelebA-HQ multimodal ablationmask distance: 2.47 -> 2.44Improved
use local experts instead of only global expert (ablation)Face-MoGLE · MM-CelebA-HQ multimodal ablationCLIP text score: 26.30 -> 27.07Improved
use matrix gating instead of static weights (ablation)Face-MoGLE · MM-CelebA-HQ multimodal ablationFID: 25.74 -> 22.24Improved
use matrix gating instead of scalar gating (ablation)Face-MoGLE · MM-CelebA-HQ multimodal ablationFID: 43.48 -> 22.24Improved
add global-local experts without gating (ablation)Face-MoGLE · MM-CelebA-HQ multimodal ablationFID: 33.25 -> 26.55Improved
add dynamic gating without experts (ablation)Face-MoGLE · MM-CelebA-HQ multimodal ablationFID: 33.25 -> 31.30Improved
add gating on top of experts (ablation)Face-MoGLE · MM-CelebA-HQ multimodal ablationFID: 26.55 -> 22.24Improved
add experts to the baseline (ablation)Face-MoGLE · MM-CelebA-HQ multimodal ablationmask distance: 2.49 -> 3.20Hurt
add experts and gating to the baseline (ablation)Face-MoGLE · MM-CelebA-HQ multimodal ablationCLIP text score: 26.71 -> 26.32No clear effect
replace Collaborative with Face-MoGLEmultimodal face generation · MM-CelebA-HQ multimodal face generationFID: 24.48 -> 22.24Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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