5 papers
Note-Level Temporal Grounding of Musical Concepts in Large Audio-Language Models
Kun Fang, Ziyu Wang, Ichiro Fujinaga
Large audio-language models (LALMs) demonstrate growing music-understanding capabilities, but whether their responses are grounded in acoustic evidence remains unclear. Musical lan…
Music-JEPA: Learning a World Model of Sound from Action
Ziyu Wang, Kun Fang, Yann LeCun
Joint Embedding Predictive Architectures (JEPA) have recently emerged as a paradigm for learning world models by predicting latent representations, offering a promising direction f…
Evaluating High-Resolution Piano Sustain Pedal Depth Estimation with Musically Informed Metrics
Hanwen Zhang, Kun Fang, Ziyu Wang +1
Evaluation for continuous piano pedal depth estimation tasks remains incomplete when relying only on conventional frame-level metrics, which overlook musically important features s…
High-Resolution Sustain Pedal Depth Estimation from Piano Audio Across Room Acoustics
Kun Fang, Hanwen Zhang, Ziyu Wang +1
Piano sustain pedal detection has previously been approached as a binary on/off classification task, limiting its application in real-world piano performance scenarios where pedal…
Exploring GPT's Ability as a Judge in Music Understanding
Kun Fang, Ziyu Wang, Gus Xia +1
Recent progress in text-based Large Language Models (LLMs) and their extended ability to process multi-modal sensory data have led us to explore their applicability in addressing m…