AI Paper Atlas

Research map / Video / Video generation

Composing Concepts from Images and Videos via Concept-prompt Binding

Xianghao Kong, Zeyu Zhang, Yuwei Guo, Zhuoran Zhao, Songchun Zhang, Anyi Rao

CVPR 2026 · Video › Video generation · approach: Trajectory-guided motion control · 0 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 hierarchical binder (global plus per-block) (ablation)global binder baseline · Concept composition ablation (user study)Overall Quality: 2.34 -> 2.81Improved
add prompt diversification (ablation)hierarchical binder · Concept composition ablation (user study)Overall Quality: 2.81 -> 3.26Improved
add absorbent token (ablation)Hrc+Div · Concept composition ablation (user study)Overall Quality: 3.26 -> 3.47Improved
add temporal disentanglement strategy (ablation)Hrc+Div · Concept composition ablation (user study)Overall Quality: 3.26 -> 3.82Improved
add temporal disentanglement strategy (ablation)Hrc+Div+Abs · Concept composition ablation (user study)Overall Quality: 3.47 -> 4.40Improved
add absorbent token (ablation)Hrc+Div+TDS · Concept composition ablation (user study)Overall Quality: 3.82 -> 4.40Improved
add two-stage inverted training (ablation)BiCo · Concept composition ablation (user study)Overall Quality: 2.58 -> 4.40Improved
add two-stage training without inversion (ablation)BiCo · Concept composition ablation (user study)Overall Quality: 2.58 -> 3.61Improved
add inversion toward high noise levels in first stage (ablation)two-stage BiCo · Concept composition ablation (user study)Overall Quality: 3.61 -> 4.40Improved
full BiCo vs DualReal on human overall qualityDualReal · Concept composition (40 test cases)Overall Quality: 3.00 -> 4.64Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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