AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer

Shuai Wang, Liang Li, Yang Chen, Ruopeng Gao, Yao Teng, Limin Wang

ECCV 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Vision-language pretraining · 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 joint understanding-generation training after warmup (ablation)UniDDT · GenEval (Native-UniDDT, by stage)overall: 0.52 -> 0.60Improved
add duality-based post-training of the diffusion decoder (ablation)UniDDT · GenEval (Native-UniDDT, by stage)overall: 0.60 -> 0.72Improved
add 4o-style data fine-tuning (ablation)UniDDT · GenEval (Native-UniDDT, by stage)overall: 0.72 -> 0.87Improved
add joint training (ablation)UniDDT · GenEval (Native-UniDDT, by stage)counting: 0.32 -> 0.45Improved
add post-training (ablation)UniDDT · GenEval (Native-UniDDT, by stage)position: 0.41 -> 0.50Improved
add post-training (ablation)UniDDT · GenEval (Native-UniDDT, by stage)color attribution: 0.37 -> 0.61Improved
add understanding loss in joint training (vs w/o und) (ablation)Latent-Native-UniDDT · GenEvalgeneration qualityImproved
add understanding loss in joint training (vs w/o und) (ablation)Pixel-Native-UniDDT-B · GenEvalgeneration qualityImproved
use latent space instead of pixel space as unified visual space (ablation)UniDDT · generationgeneration qualityImproved
use pixel space instead of latent space (ablation)VLM-UniDDT · understandingMLLM benchmarksNo clear effect
use small time-shift instead of large time-shift in Noisy ViT warmup (ablation)Noisy ViT encoder · understanding (OCR)understandingImproved
scale model from Native-UniDDT-L to XLNative-UniDDT · GenEvaloverall: 0.88 -> 0.89Improved

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