2 citations · 5 across the 9 of their papers we have counts for
3 papers · 1 filter
PANEL: An Open-Source, Self-Hosted Web Platform for Human Evaluation of Generative Models
Matteo Spanio, Andrea Poltronieri, Mart\'ın Rocamora
Human judgement is the reference measure for evaluating generative models, yet the software used to collect it lags behing the methodology. Researchers adapt listening-test framewo…
Can LLMs understand LilyPond? A benchmark for symbolic music generation and understanding
Matteo Spanio, Mohammad Torabi, Andrea Poltronieri +1
Symbolic music evaluation for large language models remains fragmented across representations, datasets, and metrics. We introduce LilyBench, a LilyPond-based benchmark that jointl…
Evaluating Disentangled Representations for Controllable Music Generation
Laura Ibáñez-Martínez, Chukwuemeka Nkama, Andrea Poltronieri +2
Recent approaches in music generation rely on disentangled representations, often labeled as structure and timbre or local and global, to enable controllable synthesis. Yet the und…