@article{avditefficientaudiovisualdiffusion, title = {AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation}, author = {Kai Wang and Shijian Deng and Jing Shi and Dimitrios Hatzinakos and Yapeng Tian}, year = {2024}, eprint = {2406.07686}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.07686v1}, }