Fang-Duo Tsai

MIDI-REPA: Improving Text-to-Music Generation with Symbolic Representation Alignment

State-of-the-art text-to-music models increasingly rely on scaling model capacity, data, and compute, while still learning musical structure directly from dense audio. Yet melody, rhythm, harmony, and structure can be represented compactly in symbolic form. We introduce MIDI-REPA, a representation-alignment framework t...