AI Paper Atlas

Research map / Video / Video generation

Harmony: Harmonizing Audio and Video Generation through Cross-Task Synergy

Teng Hu, Zhentao Yu, Guozhen Zhang, Zihan Su, Zhengguang Zhou, Youliang Zhang, Yuan Zhou, Qinglin Lu, Ran Yi

CVPR 2026 · Video › Video generation · approach: Video-to-audio synthesis · 24 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 global-local decoupled interaction module (ablation)Harmony baseline · Harmony-Bench speechSync-C: 4.20 -> 4.29Improved
add RoPE alignment (ablation)Harmony · Harmony-Bench speechSync-C: 4.29 -> 4.80Improved
add cross-task synergy training (ablation)Harmony · Harmony-Bench speechSync-C: 4.80 -> 5.09Improved
add SyncCFG at inference (ablation)Harmony · Harmony-Bench speechSync-C: 5.09 -> 6.51Improved
add SyncCFG at inference (ablation)Harmony · Harmony-Bench speechSync-D: 10.16 -> 8.63Improved
use Harmony instead of OviHarmony · Harmony-Bench averageSync-C: 4.04 -> 5.61Improved
use Harmony instead of OviHarmony · Harmony-Bench averageSync-D: 9.62 -> 7.53Improved
use Harmony instead of OviHarmony · Harmony-Bench averageIB: 0.18 -> 0.19No clear effect
use Harmony instead of OviHarmony · Harmony-Bench averageImaging Quality: 0.65 -> 0.65No clear effect
train with audio-driven task (clean audio) vs joint generation only (ablation)Harmony · lip-sync convergenceSync confidenceImproved

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