# CPR: Combining global composing, local performing and full-sequence refining in piano rendering with continuous autoregressive modelling

arXiv: https://arxiv.org/abs/2609.18216 · HTML: https://mlsanity.com/paper/2609.18216/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 29 of its 32 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 29 of 29)

- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders](https://mlsanity.com/paper/1704.01279/) (2017)
- [Fr'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms](https://mlsanity.com/paper/1812.08466/) (2018)
- [Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset](https://mlsanity.com/paper/1810.12247/) (2018)
- [Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis](https://mlsanity.com/paper/2306.00814/) (2023)
- [Qwen3-TTS Technical Report](https://mlsanity.com/paper/2601.15621/) (2026)
- [Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity](https://mlsanity.com/paper/1909.08494/) (2019)
- [MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization](https://mlsanity.com/paper/2501.01108/) (2025)
- [DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation](https://mlsanity.com/paper/2502.03930/) (2025)
- [MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder](https://mlsanity.com/paper/2505.07916/) (2025)
- [Autoregressive Diffusion Transformer for Text-to-Speech Synthesis](https://mlsanity.com/paper/2406.05551/) (2024)
- [Making Reconstruction FID Predictive of Diffusion Generation FID](https://mlsanity.com/paper/2603.05630/) (2026)
- [MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling](https://mlsanity.com/paper/2507.08530/) (2025)
- [Use of speaker recognition approaches for learning and evaluating embedding representations of musical instrument sounds](https://mlsanity.com/paper/2107.11506/) (2021)
- [FireRedTTS3: Unified Speech Generation and Editing with Semantically Enriched Speech Representations](https://mlsanity.com/paper/2608.17492/) (2026)
- [MuScriptor: An Open Model for Multi-Instrument Music Transcription](https://mlsanity.com/paper/2607.08168/) (2026)
- [P-MUSE: Prompt-MIDI-Optional Model for Unified Instrumental Music Synthesis and Editing](https://mlsanity.com/paper/2608.01920/) (2026)
- [Anysynth:Zero-Shot Instrument Cloning via In-Context Learning and Asymmetric Hierarchical Guidance](https://mlsanity.com/paper/2607.11143/) (2026)

## Abstract (arXiv)

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 condition-following ability of AR models and distribution-modeling capacity of flow matching but also bypasses the quantization bottleneck with lower computational costs. Building on this principle, we present Composer--Performer--Refiner (CPR) framework. Composer autoregressively predicts continuous hidden states, Performer generates 24kHz acoustic latents through local flow matching and Refiner then upsamples the waveform to 48 kHz. We further introduce Bottlenecked Representation Alignment (BREPA) and Modality--Time RoPE (MT-RoPE) to strengthen musical semantic structure in Composer hidden states and temporal alignments across modalities. Codes are available at https://github.com/FEAfeatherTHER/CPR_official