AI Paper Atlas

Research map / Video / Video generation

JoVA: Unified Multimodal Learning for Joint Video-Audio Generation and Editing

Xiaohu Huang, Haoyang He, Hao Zhou, Qiangpeng Yang, Min Zheng, Kai Han

ECCV 2026 · Video › Video generation · approach: Video-to-audio synthesis · 19 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 mouth-area loss (lambda 0.0 to 2.0) (ablation)JoVA · JoVABench-GenLSE-C: 1.39 -> 6.53Improved
raise mouth-area loss weight from 2.0 to 5.0 (ablation)JoVA · JoVABench-GenLSE-C: 6.53 -> 6.70Improved
raise mouth-area loss weight from 5.0 to 8.0 (ablation)JoVA · JoVABench-GenLSE-C: 6.70 -> 6.65Hurt
vary mouth-area loss weight lambda (ablation)JoVA · JoVABench-GenPQ: 6.44, 6.47, 6.49, 6.40No clear effect
use joint self-attention instead of sequential Ovi-style cross-attention (ablation)JoVA · JoVABench-GenLSE-C: 6.51 -> 6.70Improved
use joint self-attention instead of sequential Ovi-style cross-attention (ablation)JoVA · JoVABench-GenWER: 0.24 -> 0.19Improved
use joint self-attention instead of parallel cross-attention with linear adaptation (ablation)JoVA · JoVABench-GenLSE-C: 1.59 -> 6.70Improved
use joint self-attention instead of parallel cross-attention without linear (ablation)JoVA · JoVABench-GenPQ: 6.14 -> 6.49Improved
use JoVA unified model instead of Ovi on Verse-BenchJoVA · Verse-BenchDeSync: 0.49 -> 0.16Improved
use JoVA instead of best cascaded editing baseline (Ditto + Wav2Lip)JoVA · JoVABench-EditLSE-D: 2.83 -> 1.66Improved
use JoVA instead of Ditto + Wav2Lip in human studyJoVA · Video-audio editing MOSInstruction-Following: 3.30 -> 3.85Improved
use JoVA instead of Gen-3 on pure video generationJoVA · VBenchTotal Score: 82.32 -> 82.61Improved

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