Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation
By Junhao Chen · Paper · cs.SD
Text-to-music language models begin with a choice usually made by default: how to tokenize music. Normally entangled with backbone, data, and recipe, its effect has never been measured in isolation. We fix pretrained Qwen3.5 (0.8B-27B), data, budget, and decoding, and swap only t