YuE: Scaling Open Foundation Models for Long-Form Music Generation · HackerPapers discussions

YuE: Scaling Open Foundation Models for Long-Form Music Generation — mentioned by efskap

Tue, 28 Oct 2025 03:17:45 GMT

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

Paper and discussion history. A mention is not an endorsement.

YuE: Scaling Open Foundation Models for Long-Form Music Generation — mentioned by someothherguyy

Thu, 07 Aug 2025 21:16:54 GMT

> Additionally, our memorization-effect experiments in Section 11 demonstrate that our design maintains creativity without plagiarizing, even under strong training set conditioning. https://arxiv.org/html/2503.08638v1#S11

Paper and discussion history. A mention is not an endorsement.