AI Paper Atlas

Research map / Video / Video generation

StreamGVE: Training-Free Video Editing via Few-Step Streaming Video Generation

Guanlong Jiao, Chenyangguang Zhang, Jia Xian, Zewei Zhang, Renjie Liao

ECCV 2026 · Video › Video generation · approach: Autoregressive long video generation

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 cross-attention boosting (ablation)StreamEdit (Self Forcing) · FiVE-BenchFiVE-Acc: 39.05 -> 51.94Improved
add cross-attention boosting (ablation)StreamEdit (LongLive) · FiVE-BenchFiVE-Acc: 46.46 -> 55.04Improved
add cross-attention boosting (ablation)StreamEdit (LongLive) + first frame · FiVE-BenchFiVE-Acc: 54.78 -> 61.19Improved
add cross-attention boosting (ablation)StreamEdit (Self Forcing) + first frame · FiVE-BenchFiVE-Acc: 56.29 -> 58.64Improved
add cross-attention boosting (ablation)StreamEdit (Self Forcing) · FiVE-BenchPSNR: 28.99 -> 28.47Hurt
increase boost scale omega from 2 to 5 (ablation)StreamEdit (Self Forcing) · FiVE-BenchFiVE-Acc: 46.46 -> 52.52Improved
increase boost scale omega from 2 to 5 (ablation)StreamEdit (Self Forcing) · FiVE-BenchPSNR: 28.85 -> 28.33Hurt
increase blending exponent rho from 0 to 3 (ablation)StreamEdit (Self Forcing) · FiVE-BenchFiVE-Acc: 25.92 -> 57.99Improved
increase blending exponent rho from 0 to 3 (ablation)StreamEdit (Self Forcing) · FiVE-BenchPSNR: 30.86 -> 27.39Hurt
move source KV injection start t_inj from 0.5 to 0.3 or 0.7 (ablation)StreamEdit (Self Forcing) · FiVE-BenchFiVE-Acc: 51.17 / 51.94 / 52.10No clear effect
remove self-attention bridge (ablation)StreamEdit (Self Forcing) · FiVE-Benchqualitative fidelity to sourceHurt
remove source-oriented guidance (ablation)StreamEdit (Self Forcing) · FiVE-Benchbackground alignmentHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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