AI Paper Atlas

Research map / Video / Video generation

VOGUE: Unified Understanding, Generation, and Editing for Videos

Cong Wei, Quande Liu, Zixuan Ye, Qiulin Wang, Xintao Wang, Pengfei Wan, Kun Gai, Wenhu Chen

ICLR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion

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 multi-task training over single-task models (ablation)UniVideo · in-context tasks averageprompt following: 0.64 -> 0.80Improved
add joint multi-task training over single-task models (ablation)UniVideo · in-context tasks averagesubject consistency: 0.67 -> 0.78Improved
add joint multi-task training over single-task models (ablation)UniVideo · in-context tasks averagevideo quality: 0.79 -> 0.85Improved
add joint multi-task training over single-task models (ablation)UniVideo · in-context swapprompt following: 0.53 -> 0.91Improved
add joint multi-task training over single-task models (ablation)UniVideo · in-context multi-id generationprompt following: 0.75 -> 0.75No clear effect
feed visual inputs to MMDiT as well as MLLM (ablation)UniVideo · in-context tasks averagesubject consistency: 0.18 -> 0.78Improved
feed visual inputs to MMDiT as well as MLLM (ablation)UniVideo · in-context tasks averageprompt following: 0.66 -> 0.80Improved
feed visual inputs to MMDiT as well as MLLM (ablation)UniVideo · in-context multi-id generationprompt following: 0.81 -> 0.75Hurt
use MMDiT self-attention conditioning over cross-attention DiT (ablation)UniVideo · video generation (15K steps)prompt alignmentImproved
freeze the MLLM for understandingUniVideo · MMBenchaccuracy: 83.5No clear effect

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