# Do You Have Freestyle? Expressive Humanoid Locomotion via Audio Control

arXiv: https://arxiv.org/abs/2512.23650 · HTML: https://mlsanity.com/paper/2512.23650/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Dec 2025.

## Built on by (most cited first, 7 of 7)

- [VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model](https://mlsanity.com/paper/2605.01194/) (2026)
- [ω-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation](https://mlsanity.com/paper/2608.06375/) (2026)
- [Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2601.01618/) (2026)
- [Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery](https://mlsanity.com/paper/2605.01191/) (2026)
- [PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking](https://mlsanity.com/paper/2603.19305/) (2026)
- [Semantic Audio-driven Understanding for Dynamic Humanoid Whole Body Control](https://mlsanity.com/paper/2607.14182/) (2026)
- [ECHO-G: Embodied Co-speech Humanoid mOtion Generation](https://mlsanity.com/paper/2609.39575/) (2026)

## Abstract (arXiv)

Humans intuitively move to sound, but current humanoid robots lack expressive improvisational capabilities, confined to predefined motions or sparse commands. Generating motion from audio and then retargeting it to robots relies on explicit motion reconstruction, leading to cascaded errors, high latency, and disjointed acoustic-actuation mapping. We propose RoboPerform, the first unified audio-to-locomotion framework that can directly generate music-driven dance and speech-driven co-speech gestures from audio. Guided by the core principle of "motion = content + style", the framework treats audio as implicit style signals and eliminates the need for explicit motion reconstruction. RoboPerform integrates a ResMoE teacher policy for adapting to diverse motion patterns and a diffusion-based student policy for audio style injection. This retargeting-free design ensures low latency and high fidelity. Experimental validation shows that RoboPerform achieves promising results in physical plausibility and audio alignment, successfully transforming robots into responsive performers capable of reacting to audio.