AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning

Yiwen Shao, Wei Liu, Jiahong Li, Tianzi Wang, Kun Wei, Meng Yu, Dong YuarXiv 2026 · DOI

BibTeX
@misc{shao2026azeros,
  author = {Yiwen Shao and Wei Liu and Jiahong Li and Tianzi Wang and Kun Wei and Meng Yu and Dong Yu},
  title = {{AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning}},
  year = {2026},
  eprint = {2601.06086},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.06086},
}

Loading related content...

Figure