SOURCE-LINKED INTELLIGENCE
CPR: Combining global composing, local performing and full-sequence refining in piano rendering with continuous autoregressive modelling
Prompt-conditioned piano MIDI-to-Music rendering aims to faithfully render target notes while reproducing the timbre of a reference recording. Existing approaches primarily follow two paradigms: autoregressive (AR) modeling and flow matching (or diffusion). Discrete-codec AR models provide causal temporal modeling, but quantization can discard acoustic detail. Flow matching better preserves acoustic structure in the cost of full-sequence attention costs and worse semantic structure. Continuous autoregressive models operate directly on continuous representations. It not only combines the condit
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-16T06:46:00.000Z
First collected: 2026-09-20T08:01:03.945Z. This is not the publication date.