AI Paper Atlas

Research map / Video / Video generation

Unified In-Context Video Editing

Zixuan Ye, Xuanhua He, Quande Liu, Qiulin Wang, Xintao Wang, Pengfei Wan, Di ZHANG, Kun Gai, Qifeng Chen, Wenhan Luo

ICLR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion

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 task-aware RoPE and condition bias (D4 vs D1) (ablation)UNIC · Re-Camera ControlTransErr: 8.972 -> 5.667Improved
add condition bias only to sequential-RoPE model (ablation)UNIC · Re-Camera ControlRotErr: 2.501 -> 1.428Improved
add task-aware RoPE only (ablation)UNIC · Re-Camera ControlCamMC: 13.119 -> 6.498Improved
add condition bias on top of task-aware RoPE (ablation)UNIC · StylizationArtFID: 32.768 -> 37.619Hurt
add condition bias on top of task-aware RoPE (ablation)UNIC · ID SwapCLIP-I: 0.710 -> 0.725Improved
staged training starting with camera instead of joint training (ablation)UNIC · Re-Camera ControlRotErr: 2.287 -> 1.275Improved
staged training starting with camera instead of joint training (ablation)UNIC · Re-Camera ControlTransErr: 9.694 -> 5.667Improved
easy-to-hard instead of hard-to-easy order (ablation)UNIC · Re-Camera ControlRotErr: 1.275 -> 1.398Hurt
joint training instead of staged (ablation)UNIC · StylizationCSD-Score: 0.259 -> 0.298Mixed
unify tasks instead of task-specific camera model (ablation)UNIC · Re-Camera ControlRotErr: 1.472 -> 1.275Improved
unify tasks instead of task-specific style model (ablation)UNIC · StylizationCSD-Score: 0.234 -> 0.259Improved
unify tasks instead of task-specific style model (ablation)UNIC · StylizationCFSD: 0.096 -> 0.107Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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