AI Paper Atlas

Research map / Video / Video generation

VABench: A Comprehensive Benchmark for Audio-Video Generation

Daili Hua, Xizhi Wang, Bohan Zeng, Xinyi Huang, Hao Liang, Junbo Niu, Xinlong Chen, Quanqing Xu, Wentao Zhang

CVPR 2026 · Video › Video generation · approach: Video-to-audio synthesis · 23 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
end-to-end AV models vs decoupled V+A pipelines (T2AV)Veo3/Sora2/Wan2.5 · VABench T2AVAudio QA: 0.7999 (Veo3) vs 0.7300 (Kling+MMAudio, best V+A)Improved
combine strongest video model with MMAudio instead of ThinkSoundKling · VABench T2AVAudio QA: 0.6932 -> 0.7300Improved
use image conditioning (I2AV) instead of text onlyAV models · VABenchQA gap between modelsImproved
use ThinkSound instead of MMAudioV+A pipelines · VABench T2AVLip-SyncMixed
stereo generation from text promptsSora2/Veo3/Wan2.5 · VABench stereohuman checkNo clear effect
compare VABench scores with human win ratesVABench · user studyPearson correlationImproved

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