SOURCE-LINKED INTELLIGENCE

AVENUE: Audio-Video EditiNg Understanding and Evaluation

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Audio-video (AV) editing aims to modify audio and video content according to a target prompt. Unlike single-modality editing, AV editing requires models to infer a modality-selective edit scope from the prompt alone: determining not only what should change, but also which modality should be preserved. Faithfully evaluating such models therefore requires both (i) benchmarks that span diverse edit types and modality categories, and (ii) evaluation that is itself modality-aware and sample-specific. However, existing AV editing benchmarks provide limited coverage of edit types and modality combina

Read original source ↗ Open in workspace

recordType

paper

region

Global