# Music Flamingo: Scaling Music Understanding in Audio Language Models

arXiv: https://arxiv.org/abs/2511.10289 · HTML: https://mlsanity.com/paper/2511.10289/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2025.

## Built on by (most cited first, 21 of 21)

- [Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music](https://mlsanity.com/paper/2604.10905/) (2026)
- [MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos](https://mlsanity.com/paper/2603.14145/) (2026)
- [AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking](https://mlsanity.com/paper/2601.17645/) (2026)
- [Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions](https://mlsanity.com/paper/2602.05220/) (2026)
- [AutoCut: End-to-end advertisement video editing based on multimodal discretization and controllable generation](https://mlsanity.com/paper/2603.28366/) (2026)
- [Membership Inference Attacks against Large Audio Language Models](https://mlsanity.com/paper/2603.28378/) (2026)
- [Video-Robin: Autoregressive Diffusion Planning for Intent-Grounded Video-to-Music Generation](https://mlsanity.com/paper/2604.17656/) (2026)
- [Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos](https://mlsanity.com/paper/2607.16107/) (2026)
- [HumMusQA: A Human-written Music Understanding QA Benchmark Dataset](https://mlsanity.com/paper/2603.27877/) (2026)
- [USAD 2.0: Scaling Representation Distillation for Universal Audio Understanding](https://mlsanity.com/paper/2606.06444/) (2026)
- [BASS: Benchmarking Audio LMs for Musical Structure and Semantic Reasoning](https://mlsanity.com/paper/2602.04085/) (2026)
- [Speech-Worthy Alignment for Japanese SpeechLLMs via Direct Preference Optimization](https://mlsanity.com/paper/2603.12565/) (2026)
- [VocalParse: Towards Unified and Scalable Singing Voice Transcription with Large Audio Language Models](https://mlsanity.com/paper/2605.04613/) (2026)
- [Auditing Training Data in Generative Music Models via Black-Box Membership Inference](https://mlsanity.com/paper/2605.29202/) (2026)
- [Making the Most of Limited Data: Score-Aware Training for Text-to-Music Generation](https://mlsanity.com/paper/2606.07387/) (2026)
- [Beyond Binary Instrument QA: Probing Instrument Grounding in Music Audio-Language Models](https://mlsanity.com/paper/2606.31338/) (2026)
- [Noisy-Channel Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2607.05198/) (2026)
- [Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations](https://mlsanity.com/paper/2609.34030/) (2026)
- [Extending Music Annotation Schemas: Zero-Shot Prediction or Few-Shot Adaptation?](https://mlsanity.com/paper/2610.06920/) (2026)
- [MIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User Intent](https://mlsanity.com/paper/2610.10355/) (2026)
- [Understanding Machine Taste: Aesthetic Agreement Across Foundation Models in K-pop](https://mlsanity.com/paper/2610.17731/) (2026)

## Abstract (arXiv)

We introduce Music Flamingo, a novel large audio-language model designed to advance music (including song) understanding in foundational audio models. While audio-language research has progressed rapidly, music remains challenging due to its dynamic, layered, and information-dense nature. Progress has been further limited by the difficulty of scaling open audio understanding models, primarily because of the scarcity of high-quality music data and annotations. As a result, prior models are restricted to producing short, high-level captions, answering only surface-level questions, and showing limited generalization across diverse musical cultures. To address these challenges, we curate MF-Skills, a large-scale dataset labeled through a multi-stage pipeline that yields rich captions and question-answer pairs covering harmony, structure, timbre, lyrics, and cultural context. We fine-tune an enhanced Audio Flamingo 3 backbone on MF-Skills and further strengthen multiple skills relevant to music understanding. To improve the model's reasoning abilities, we introduce a post-training recipe: we first cold-start with MF-Think, a novel chain-of-thought dataset grounded in music theory, followed by GRPO-based reinforcement learning with custom rewards. Music Flamingo achieves state-of-the-art results across 10+ benchmarks for music understanding and reasoning, establishing itself as a generalist and musically intelligent audio-language model. Beyond strong empirical results, Music Flamingo sets a new standard for advanced music understanding by demonstrating how models can move from surface-level recognition toward layered, human-like perception of songs. We believe this work provides both a benchmark and a foundation for the community to build the next generation of models that engage with music as meaningfully as humans do.