# CMA-OT: Hierarchical Expert Supervision for Dance-to-Music Generation

arXiv: https://arxiv.org/abs/2609.13118 · HTML: https://mlsanity.com/paper/2609.13118/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 53 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Builds on (most cited first, 30 of 33)

- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [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)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training](https://mlsanity.com/paper/2306.00107/) (2023)
- [Optimal Transport for structured data with application on graphs](https://mlsanity.com/paper/1805.09114/) (2018)
- [JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2411.07975/) (2024)
- [Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound](https://mlsanity.com/paper/2502.05139/) (2025)
- [VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models](https://mlsanity.com/paper/2505.23656/) (2025)
- [Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning](https://mlsanity.com/paper/2006.06119/) (2020)
- [DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion](https://mlsanity.com/paper/2503.01183/) (2025)
- [HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation](https://mlsanity.com/paper/2508.16930/) (2025)
- [Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation](https://mlsanity.com/paper/2206.07771/) (2022)
- [Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation](https://mlsanity.com/paper/2404.01518/) (2024)
- [Quantized GAN for Complex Music Generation from Dance Videos](https://mlsanity.com/paper/2204.00604/) (2022)
- [Curriculum Direct Preference Optimization for Diffusion and Consistency Models](https://mlsanity.com/paper/2405.13637/) (2024)
- [SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learning](https://mlsanity.com/paper/2504.15900/) (2025)
- [Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation](https://mlsanity.com/paper/2404.11998/) (2024)
- [Long-Term Rhythmic Video Soundtracker](https://mlsanity.com/paper/2305.01319/) (2023)
- [Boost Your Human Image Generation Model via Direct Preference Optimization](https://mlsanity.com/paper/2405.20216/) (2024)
- [Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications](https://mlsanity.com/paper/2306.15963/) (2023)
- [Dance-to-Music Generation with Encoder-based Textual Inversion](https://mlsanity.com/paper/2401.17800/) (2024)
- [TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis](https://mlsanity.com/paper/2504.05684/) (2025)
- [Enhancing Dance-to-Music Generation via Negative Conditioning Latent Diffusion Model](https://mlsanity.com/paper/2503.22138/) (2025)

## Abstract (arXiv)

Dance-to-music (D2M) generation aims to synthesize music that is rhythmically and stylistically aligned with dance videos. A key challenge arises from the semantic mismatch between sparse dance cues, such as rhythm and style, and the dense information required for music composition, including structure, instrumentation, and expressive dynamics. Existing methods typically rely on these sparse cues and supervise only the final audio output, resulting in poorly learned music representations and generated music with limited musicality and structural coherence. To address these issues, we propose Curriculum-guided Multi-scale representation Alignment with scale-aware Optimal Transport (CMA-OT), a novel paradigm that leverages an external music expert to provide hierarchical supervision for the generator's latent features, bridging the semantic gap and enhancing representation learning. To effectively incorporate hierarchical supervision, we introduce a curriculum-guided multi-scale learning strategy that progressively transfers musical knowledge from the expert to the music generator, enabling stable and effective representation learning. Moreover, to accommodate the semantic and structural variations across different expert scales and achieve fine-grained alignment under temporal mismatch, we propose a scale-aware optimal transport alignment mechanism, which models soft correspondences between hierarchical expert representations and the generator's latent features. Extensive experiments on two datasets demonstrate that CMA-OT achieves state-of-the-art performance in rhythmic synchronization, perceptual quality, and overall music generation.