# Beyond Imitation: Generative and Variational Choreography via Machine Learning

arXiv: https://arxiv.org/abs/1907.05297 · HTML: https://mlsanity.com/paper/1907.05297/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2019.

## Built on by (most cited first, 6 of 6)

- [Disentangling Variational Autoencoders](https://mlsanity.com/paper/2211.07700/) (2022)
- [PirouNet: Creating Dance through Artist-Centric Deep Learning](https://mlsanity.com/paper/2207.12126/) (2022)
- [Intentional Choreography with Semi-Supervised Recurrent VAEs](https://mlsanity.com/paper/2209.10010/) (2022)
- [Dyads: Artist-Centric, AI-Generated Dance Duets](https://mlsanity.com/paper/2503.03954/) (2025)
- [Invisible Strings: Revealing Latent Dancer-to-Dancer Interactions with Graph Neural Networks](https://mlsanity.com/paper/2503.04816/) (2025)
- [Generative human motion mimicking through feature extraction in denoising diffusion settings](https://mlsanity.com/paper/2511.00011/) (2025)

## Abstract (arXiv)

Our team of dance artists, physicists, and machine learning researchers has collectively developed several original, configurable machine-learning tools to generate novel sequences of choreography as well as tunable variations on input choreographic sequences. We use recurrent neural network and autoencoder architectures from a training dataset of movements captured as 53 three-dimensional points at each timestep. Sample animations of generated sequences and an interactive version of our model can be found at http: //www.beyondimitation.com.