Mingyang Yao

TASTE: Taxonomy-Aware Symbolic Piano Generation from Textual Description

Text-conditioned symbolic music generation has attracted growing interest with the development of generative models. Yet two questions remain underexplored: what aspects of music the conditioning text should describe, and how the corresponding data should be collected and trained to improve controllability and text-mus...

Analysis of factors affecting fatigue life of aircraft engines based on fracture mechanics

ARIMA: Reconstruction-Grounded Predictive Representation Learning for Symbolic Music

Results show that ARIMA is particularly efficient and effective on tasks involving harmonic, timing, and cross-performance retrieval, while remaining competitive with much larger baselines on other tasks.