Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

The current music generators use next token prediction, like LLMs, not image denoising.

[0] https://arxiv.org/abs/2503.08638 (grep for "audio token")

[1] https://arxiv.org/abs/2306.05284



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: