Preprint
Aug 2026
Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation
Text-to-music language models begin with a choice usually made by default: how to tokenize music, and the ordering is clean and surprising: representation, not model size, is the binding variable for distributional fidelity.
Junhao Chen, Ming-Jin Chen, Jingjia Mao et al.
· 1 citation