AI Paper Atlas

Research map / Video / Video generation

IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment

Yinan Chen, Jiangning Zhang, Teng Hu, Yuxiang Zeng, Zhucun Xue, Qingdong He, Chengjie Wang, Yong Liu, Xiaobin Hu, Shuicheng YAN

ICLR 2026 · Video › Video generation · approach: Trajectory-guided motion control

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
Evaluate on long videos (129-1024 frames) instead of short (32-128 frames)Ditto · IVEBenchTotal Score: 0.67 -> 0.66No clear effect
Evaluate on long videos instead of short videosAnyV2V · IVEBenchTotal Score: 0.58 -> 0.55Hurt
Evaluate on long instead of short videosVACE · IVEBenchInstruction Compliance: 0.25 -> 0.27No clear effect
Chunked inference with latent overlap (InsV2V) for long sequencesInsV2V · IVEBenchTotal Score: 0.67 -> 0.66No clear effect
First-frame propagation editing instead of native instruction editingIVE models · IVEBenchInstruction ComplianceHurt

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