# Customizing Sequence Generation with Multi-Task Dynamical Systems

arXiv: https://arxiv.org/abs/1910.05026 · HTML: https://mlsanity.com/paper/1910.05026/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2019.

## Built on by (most cited first, 5 of 5)

- [Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases](https://mlsanity.com/paper/2201.04439/) (2022)
- [Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data](https://mlsanity.com/paper/2410.04814/) (2024)
- [Disentangled Generative Models for Robust Prediction of System Dynamics](https://mlsanity.com/paper/2108.11684/) (2021)
- [Hamiltonian latent operators for content and motion disentanglement in image sequences](https://mlsanity.com/paper/2112.01641/) (2021)
- [Rethinking Molecular Design: Integrating Latent Variable and Auto-Regressive Models for Goal Directed Generation](https://mlsanity.com/paper/2409.00046/) (2024)

## Abstract (arXiv)

Dynamical system models (including RNNs) often lack the ability to adapt the sequence generation or prediction to a given context, limiting their real-world application. In this paper we show that hierarchical multi-task dynamical systems (MTDSs) provide direct user control over sequence generation, via use of a latent code z that specifies the customization to the individual data sequence. This enables style transfer, interpolation and morphing within generated sequences. We show the MTDS can improve predictions via latent code interpolation, and avoid the long-term performance degradation of standard RNN approaches.