AI Paper Atlas

Research map / Video / Video-language understanding

VideoCoF: Unified Video Editing with Temporal Reasoner

Xiangpeng Yang, Ji Xie, Yiyuan Yang, Yue Ma, Yan Huang, Min Xu, Qiang Wu

CVPR 2026 · Video › Video-language understanding · approach: Long video understanding · 25 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 chain-of-frames reasoning frames with RoPE [1-F,0,1-F] instead of naive temporal in-context (ablation)VideoCoF Wan-14B · VideoCoF-BenchInstruct Follow (GPT-4o): 8.109 -> 8.973Improved
add chain-of-frames reasoning frames with RoPE [1-F,0,1-F] instead of naive temporal in-context (ablation)VideoCoF Wan-14B · VideoCoF-BenchSuccess Ratio: 72.41% -> 76.36%Improved
add chain-of-frames reasoning frames with RoPE [1-F,0,1-F] instead of naive temporal in-context (ablation)VideoCoF Wan-14B · VideoCoF-BenchCLIP-T: 26.880 -> 28.000Improved
set reasoning frame RoPE index to 0 and source/target to 1..F instead of 0-F-1 for all (ablation)VideoCoF Wan-14B · VideoCoF-BenchSuccess Ratio: 65.52% -> 76.36%Improved
reset RoPE indices to avoid index collision (repeat indices) rather than sequential 0-2F-1 (ablation)VideoCoF Wan-14B · VideoCoF-Benchlength extrapolation to 81+ framesImproved
use reasoning frame index 0 colliding with first frame index 0 (ablation)VideoCoF Wan-14B · VideoCoF-BenchSuccess Ratio: 76.36% -> 65.52%Hurt
use gray 50% mask instead of black mask for reasoning frame (ablation)VideoCoF Wan-14B · VideoCoF-BenchSuccess Ratio: 52.17% -> 68.45%Improved
use gray 50% mask instead of red 50% highlight (ablation)VideoCoF Wan-14B · VideoCoF-BenchSuccess Ratio: 60.33% -> 68.45%Improved
use progressive gray transparency 0-75% instead of static 50% gray (ablation)VideoCoF Wan-14B · VideoCoF-BenchSuccess Ratio: 68.45% -> 76.36%Improved
use progressive gray transparency 0-75% instead of static 50% gray (ablation)VideoCoF Wan-14B · VideoCoF-BenchInstruct Follow (GPT-4o): 8.150 -> 8.973Improved
use VideoCoF with 50k pairs versus ICVE trained on 1M plus 150kVideoCoF vs ICVE · VideoCoF-BenchSuccess Ratio: 57.76% -> 76.36%Improved
use VideoCoF versus ICVEVideoCoF vs ICVE · VideoCoF-BenchQuality (GPT-4o): 8.14 -> 7.77Hurt

Later papers that compared with this method

2 later accepted papers report VideoCoF as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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