@article{fateframelevelaudiovisualtemporalembeddi, title = {FATE: Frame-Level Audio-Visual Temporal Embedding}, author = {Kaisi Guan and Bingzi Zhang and Xihua Wang and Ying Ba and Xin Cheng and Yijing Chen and Ruihua Song}, year = {2026}, eprint = {2608.01310}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.01310}, }