@article{desta25audiotowardgeneralpurposelarge,
  title = {DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment},
  author = {Ke-Han Lu and Zhehuai Chen and Szu-Wei Fu and Chao-Han Huck Yang and Sung-Feng Huang and Chih-Kai Yang and Chee-En Yu and Chun-Wei Chen and Wei-Chih Chen and Chien-yu Huang and Yi-Cheng Lin and Yu-Xiang Lin and Chi-An Fu and Chun-Yi Kuan and Wenze Ren and Xuanjun Chen and Wei-Ping Huang and En-Pei Hu and Tzu-Quan Lin and Yuan-Kuei Wu and Kuan-Po Huang and Hsiao-Ying Huang and Huang-Cheng Chou and Kai-Wei Chang and Cheng-Han Chiang and Boris Ginsburg and Yu-Chiang Frank Wang and Hung-Yi Lee},
  year = {2025},
  eprint = {2507.02768},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.02768v1},
}