Musicians commonly communicate music through scores and performances. Scores encode musical intent, while performances realize it in sound. To investigate whether models can meaningfully engage with both modalities, we introduce MuSP-Bench, a human-authored benchmark of 490 questions targeting understanding across Musi...
Milan Liessens Dujardin, Song Yu, Kevin Miao· 0 citations
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...
Song Yu, Fang-Duo Tsai, Yi-Hsuan Yang· 0 citations
MuNo-SP (Music Notation unifying Score and Performance), a text-based representation that jointly encodes score content and performance information, is introduced and an automatic training-data generation pipeline is developed that uses aligned scores and performances to produce long-form auditory analyses and musicall...
Milan Liessens Dujardin, Song Yu, Kevin Miao· 0 citations
Anamnesis produces opinion distributions that more closely match real-world survey data than standard persona-prompting baselines, offering a transparent, reproducible, and open-source alternative to proprietary simulation services.
Song Yu, Joseph Suh, Serina Chang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.