AI Paper Atlas

Research map / Video / Video generation

RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models

Yijing Lin, Mengqi Huang, Shuhan Zhuang, Zhendong Mao

ICCV 2025 · Video › Video generation · approach: Autoregressive long video generation · 14 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 Unified Conditional Embedding (ablation)RealGeneral · DreamBench customizationCLIP-I: 0.833 -> 0.849Improved
add Separated Condition AdaLN (ablation)RealGeneral · DreamBench customizationCLIP-I: 0.830 -> 0.849Improved
add Frame-Condition Decoupling (ablation)RealGeneral · DreamBench customizationCLIP-I: 0.827 -> 0.849Improved
add Unified Conditional Embedding (ablation)RealGeneral · DreamBench customizationCLIP-T: 0.320 -> 0.314Hurt
add Frame-Condition Decoupling (ablation)RealGeneral · DreamBench customizationDINO: 0.665 -> 0.668Improved
use Mask A (block text-condition image interaction) instead of no mask (ablation)RealGeneral · DreamBench customizationCLIP-I: 0.827 -> 0.849Improved
use Mask A instead of Mask C (ablation)RealGeneral · DreamBench customizationCLIP-I: 0.779 -> 0.849Improved
use Mask A instead of Mask B (ablation)RealGeneral · DreamBench customizationCLIP-T: 0.321 -> 0.314Hurt
use CogVideoX video base instead of SDXL image base (vs EMU2)RealGeneral · DreamBench customizationDINO: 0.583 -> 0.668Improved
use RealGeneral instead of OminiControlRealGeneral · COCO2017 canny-to-imageFID: 20.63 -> 17.50Improved
use RealGeneral instead of OmniGenRealGeneral · COCO2017 depth-to-imageFID: 21.62 -> 23.40Hurt

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