# Skeleton2Stage: Reward-Guided Fine-Tuning for Physically Plausible Dance Generation

arXiv: https://arxiv.org/abs/2602.13778 · HTML: https://mlsanity.com/paper/2602.13778/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 57 of its 86 references that are in the map.
- First posted on arXiv 14 Feb 2026.

## Builds on (most cited first, 30 of 57)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (2023)
- [Aligning Text-to-Image Models using Human Feedback](https://mlsanity.com/paper/2302.12192/) (2023)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [EDGE: Editable Dance Generation From Music](https://mlsanity.com/paper/2211.10658/) (2022)
- [Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset](https://mlsanity.com/paper/2307.00818/) (2023)
- [Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory](https://mlsanity.com/paper/2203.13055/) (2022)
- [Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models](https://mlsanity.com/paper/2211.09707/) (2022)
- [MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model](https://mlsanity.com/paper/2404.19759/) (2024)
- [Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensors](https://mlsanity.com/paper/2203.08528/) (2022)
- [SimPoE: Simulated Character Control for 3D Human Pose Estimation](https://mlsanity.com/paper/2104.00683/) (2021)
- [DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer](https://mlsanity.com/paper/2103.10206/) (2021)
- [Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation](https://mlsanity.com/paper/2106.05969/) (2021)
- [Contact and Human Dynamics from Monocular Video](https://mlsanity.com/paper/2007.11678/) (2020)
- [FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation](https://mlsanity.com/paper/2212.03741/) (2022)
- [Robust Imitation of Diverse Behaviors](https://mlsanity.com/paper/1707.02747/) (2017)
- [MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space](https://mlsanity.com/paper/2503.15451/) (2025)

## Abstract (arXiv)

Despite advances in dance generation, most methods are trained in the skeletal domain and ignore mesh-level physical constraints. As a result, motions that look plausible as joint trajectories often exhibit body self-penetration and Foot-Ground Contact (FGC) anomalies when visualized with a human body mesh, reducing the aesthetic appeal of generated dances and limiting their real-world applications. We address this skeleton-to-mesh gap by deriving physics-based rewards from the body mesh and applying Reinforcement Learning Fine-Tuning (RLFT) to steer the diffusion model toward physically plausible motion synthesis under mesh visualization. Our reward design combines (i) an imitation reward that measures a motion's general plausibility by its imitability in a physical simulator (penalizing penetration and foot skating), and (ii) a Foot-Ground Deviation (FGD) reward with test-time FGD guidance to better capture the dynamic foot-ground interaction in dance. However, we find that the physics-based rewards tend to push the model to generate freezing motions for fewer physical anomalies and better imitability. To mitigate it, we propose an anti-freezing reward to preserve motion dynamics while maintaining physical plausibility. Experiments on multiple dance datasets consistently demonstrate that our method can significantly improve the physical plausibility of generated motions, yielding more realistic and aesthetically pleasing dances. The project page is available at: https://jjd1123.github.io/Skeleton2Stage/