AI Paper Atlas

Research map / Video / Video generation

Hear What You See: Video-to-Audio Generation with Diffusion Transformer and Semantic-Temporal Alignment-Ranked Direct Preference Optimization

Kai Wang, Tao Zhou, Jiayi Lei, Jing Wang, Jinman Zhao, Weiguo Pian, Yuan Cheng, Yapeng Tian, Peng Gao, Bin Fu, Yihao Liu, Dimitrios Hatzinakos and 1 more

CVPR 2026 · Video › Video generation · approach: Video-to-audio synthesis

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
apply STAR-DPO preference optimization to VisioSonic Base (ablation)VisioSonic Base · VGGSound testFD PaSST: 58.27 -> 55.48Improved
apply STAR-DPO preference optimization to VisioSonic Base (ablation)VisioSonic Base · VGGSound testDeSync: 0.45 -> 0.41Improved
use co-attention with concatenated audio-video latents instead of MMDiT blocks (ablation)VisioSonic Base · VGGSound testFD PaSST: 60.14 -> 58.27Improved
use Flux-like blocks instead of shared co-attention (ablation)VisioSonic Base · VGGSound testFD PaSST: 58.27 -> 66.76Hurt
use descriptive captions instead of class labels as text (ablation)VisioSonic Base · VGGSound testFD PaSST: 62.72 -> 58.27Improved
fuse audio and video first (AV) then text, rather than separate streams (ablation)VisioSonic Base · VGGSound testIB-score: 31.0 -> 32.8Improved
fuse audio and video first (AV) rather than text-video then audio (ablation)VisioSonic Base · VGGSound testDeSync: 0.48 -> 0.45Improved
use IB-AV + DeSync joint reward instead of CAVP + AV-Align (ablation)STAR-DPO · VGGSound testFD PaSST: 58.34 -> 55.48Improved
use DeSync (Synchformer) instead of AV-Align as temporal reward (ablation)STAR-DPO · VGGSound testDeSync: 0.44 -> 0.41Improved
run a third DPO iteration after the second (ablation)STAR-DPO · VGGSound testFD PaSST: 55.48 -> 56.65Hurt
rank jointly on semantic and temporal reward instead of cascading DeSync then IB-AV (ablation)STAR-DPO · VGGSound testFD PaSST: 68.57 -> 56.09Improved
cascaded DeSync-first ranking (ablation)STAR-DPO · VGGSound testDeSync: 0.44 -> 0.38Mixed

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