# Auto-Regressive vs Flow-Matching: a Comparative Study of Modeling Paradigms for Text-to-Music Generation

arXiv: https://arxiv.org/abs/2506.08570 · HTML: https://mlsanity.com/paper/2506.08570/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 28 of its 39 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [MusicLM: Generating Music From Text](https://mlsanity.com/paper/2301.11325/) (2023)
- [InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation](https://mlsanity.com/paper/2309.06380/) (2023)
- [Efficient Training of Language Models to Fill in the Middle](https://mlsanity.com/paper/2207.14255/) (2022)
- [Fr'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms](https://mlsanity.com/paper/1812.08466/) (2018)
- [Stable Audio Open](https://mlsanity.com/paper/2407.14358/) (2024)
- [Noise2Music: Text-conditioned Music Generation with Diffusion Models](https://mlsanity.com/paper/2302.03917/) (2023)
- [Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound](https://mlsanity.com/paper/2502.05139/) (2025)
- [Audiobox: Unified Audio Generation with Natural Language Prompts](https://mlsanity.com/paper/2312.15821/) (2023)
- [MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies](https://mlsanity.com/paper/2308.01546/) (2023)
- [Music ControlNet: Multiple Time-varying Controls for Music Generation](https://mlsanity.com/paper/2311.07069/) (2023)
- [Efficient Neural Music Generation](https://mlsanity.com/paper/2305.15719/) (2023)
- [JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models](https://mlsanity.com/paper/2308.04729/) (2023)
- [Joint Audio and Symbolic Conditioning for Temporally Controlled Text-to-Music Generation](https://mlsanity.com/paper/2406.10970/) (2024)
- [Seed-Music: A Unified Framework for High Quality and Controlled Music Generation](https://mlsanity.com/paper/2409.09214/) (2024)
- [High Fidelity Text-Guided Music Editing via Single-Stage Flow Matching](https://mlsanity.com/paper/2407.03648/) (2024)
- [DeepJ: Style-Specific Music Generation](https://mlsanity.com/paper/1801.00887/) (2018)
- [A Survey of AI Music Generation Tools and Models](https://mlsanity.com/paper/2308.12982/) (2023)
- [Deep Learning for Music](https://mlsanity.com/paper/1606.04930/) (2016)
- [A Survey on Cross-Modal Interaction Between Music and Multimodal Data](https://mlsanity.com/paper/2504.12796/) (2025)

## Built on by (most cited first, 2 of 2)

- [V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation](https://mlsanity.com/paper/2603.11042/) (2026)
- [Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators](https://mlsanity.com/paper/2605.22717/) (2026)

## Abstract (arXiv)

Recent progress in text-to-music generation has enabled models to synthesize high-quality musical segments, full compositions, and even respond to fine-grained control signals, e.g. chord progressions. State-of-the-art (SOTA) systems differ significantly in many dimensions, such as training datasets, modeling paradigms, and architectural choices. This diversity complicates efforts to evaluate models fairly and identify which design choices influence performance the most. While factors like data and architecture are important, in this study we focus exclusively on the modeling paradigm. We conduct a systematic empirical analysis to isolate its effects, offering insights into associated trade-offs and emergent behaviors that can guide future text-to-music generation systems. Specifically, we compare the two arguably most common modeling paradigms: auto-regressive decoding and conditional flow-matching. We conduct a controlled comparison by training all models from scratch using identical datasets, training configurations, and similar backbone architectures. Performance is evaluated across multiple axes, including generation quality, robustness to inference configurations, scalability, adherence to both textual and temporally aligned conditioning, and editing capabilities in the form of audio inpainting. This comparative study sheds light on distinct strengths and limitations of each paradigm, providing actionable insights that can inform future architectural and training decisions in the evolving landscape of text-to-music generation. Audio sampled examples are available at: https://huggingface.co/spaces/ortal1602/ARvsFM