# Improving Sequential Latent Variable Models with Autoregressive Flows

arXiv: https://arxiv.org/abs/2010.03172 · HTML: https://mlsanity.com/paper/2010.03172/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2020.

## Built on by (most cited first, 8 of 8)

- [Diffusion Probabilistic Modeling for Video Generation](https://mlsanity.com/paper/2203.09481/) (2022)
- [D'ya like DAGs? A Survey on Structure Learning and Causal Discovery](https://mlsanity.com/paper/2103.02582/) (2021)
- [Insights from Generative Modeling for Neural Video Compression](https://mlsanity.com/paper/2107.13136/) (2021)
- [VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts](https://mlsanity.com/paper/2103.07292/) (2021)
- [Sequential Representation Learning via Static-Dynamic Conditional Disentanglement](https://mlsanity.com/paper/2408.05599/) (2024)
- [Motion-aware Dynamic Graph Neural Network for Video Compressive Sensing](https://mlsanity.com/paper/2203.00387/) (2022)
- [Deep Dynamic Probabilistic Canonical Correlation Analysis](https://mlsanity.com/paper/2502.05155/) (2025)
- [Latent Space Perspicacity and Interpretation Enhancement (LS-PIE) Framework](https://mlsanity.com/paper/2307.05620/) (2023)

## Abstract (arXiv)

We propose an approach for improving sequence modeling based on autoregressive normalizing flows. Each autoregressive transform, acting across time, serves as a moving frame of reference, removing temporal correlations, and simplifying the modeling of higher-level dynamics. This technique provides a simple, general-purpose method for improving sequence modeling, with connections to existing and classical techniques. We demonstrate the proposed approach both with standalone flow-based models and as a component within sequential latent variable models. Results are presented on three benchmark video datasets, where autoregressive flow-based dynamics improve log-likelihood performance over baseline models. Finally, we illustrate the decorrelation and improved generalization properties of using flow-based dynamics.