AI Paper Atlas

Research map / Video / Video generation

Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

Qingyan Bai, Qiuyu Wang, Hao Ouyang, Yue Yu, Hanlin Wang, Wen Wang, Ka Leong Cheng, Shuailei Ma, Yanhong Zeng, Zichen Liu, Yinghao Xu, Yujun Shen and 1 more

CVPR 2026 · Video › Video generation · approach: Autoregressive long video generation · 70 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
train Editto on Ditto-1M with modality curriculum vs best baseline InsViEEditto · Video editing test setCLIP-T: 23.56 -> 25.54Improved
Editto vs InsViE on human-rated instruction followingEditto · Video editing test setEdit-Acc (human): 2.28 -> 3.85Improved
Editto vs InsViE on temporal consistencyEditto · Video editing test setCLIP-F: 98.78 -> 99.03Improved
scale training data from ~60K to ~500K samples (ablation)Editto · qualitative examplesedit quality and fidelityImproved
add modality curriculum learning (anneal reference frame) (ablation)Editto · qualitative examplesinstruction followingImproved
train final model on filtered scaled data vs raw data generatorEditto · qualitative exampleshandling of new contentImproved

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