Saved in:
Bibliographic Details
Main Authors: Wu, Jianzong, Lian, Hao, Hao, Dachao, Tian, Ye, Shi, Qingyu, Chen, Biaolong, Jiang, Hao, Tong, Yunhai
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.02457
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Recent audio-video generative systems suggest that coupling modalities benefits not only audio-video synchrony but also the video modality itself. We pose a fundamental question: Does audio-video joint denoising training improve video generation, even when we only care about video quality? To study this, we introduce a parameter-efficient Audio-Video Full DiT (AVFullDiT) architecture that leverages pre-trained text-to-video (T2V) and text-to-audio (T2A) modules for joint denoising. We train (i) a T2AV model with AVFullDiT and (ii) a T2V-only counterpart under identical settings. Our results provide the first systematic evidence that audio-video joint denoising can deliver more than synchrony. We observe consistent improvements on challenging subsets featuring large and object contact motions. We hypothesize that predicting audio acts as a privileged signal, encouraging the model to internalize causal relationships between visual events and their acoustic consequences (e.g., collision $\times$ impact sound), which in turn regularizes video dynamics. Our findings suggest that cross-modal co-training is a promising approach to developing stronger, more physically grounded world models. Code and dataset will be made publicly available.