DeSTA

@article{lu2025desta2, title={DeSTA2. 5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment}, author={Lu, Ke-Han and Chen, Zhehuai and Fu, Szu-Wei and Yang, Chao-Han Huck and Huang, Sung-Feng and Yang, Chih-Kai and Yu, Chee-En and Chen, Chun-Wei and Chen, Wei-Chih and Huang, Chien-yu and others}, journal={arXiv preprint arXiv:2507.02768}, year={2025} }