# A Factorized Low-Rank RNN Framework for Uncovering Independent Neural Latent Dynamics and Connectivity

arXiv: https://arxiv.org/abs/2511.13899 · HTML: https://mlsanity.com/paper/2511.13899/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 35 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Builds on (most cited first, 12 of 12)

- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Linking connectivity, dynamics and computations in low-rank recurrent neural networks](https://mlsanity.com/paper/1711.09672/) (2017)
- [The interplay between randomness and structure during learning in RNNs](https://mlsanity.com/paper/2006.11036/) (2020)
- [Inferring stochastic low-rank recurrent neural networks from neural data](https://mlsanity.com/paper/2406.16749/) (2024)
- [Neural Dynamics Discovery via Gaussian Process Recurrent Neural Networks](https://mlsanity.com/paper/1907.00650/) (2019)
- [Dynamics of random recurrent networks with correlated low-rank structure](https://mlsanity.com/paper/1909.04358/) (2019)
- [Shaping dynamics with multiple populations in low-rank recurrent networks](https://mlsanity.com/paper/2007.02062/) (2020)
- [Bayesian latent structure discovery from multi-neuron recordings](https://mlsanity.com/paper/1610.08465/) (2016)
- [A Revisit of Total Correlation in Disentangled Variational Auto-Encoder with Partial Disentanglement](https://mlsanity.com/paper/2502.02279/) (2025)
- [One-hot Generalized Linear Model for Switching Brain State Discovery](https://mlsanity.com/paper/2310.15263/) (2023)

## Built on by (most cited first, 1 of 1)

- [Identifying Connectivity Distributions from Neural Dynamics Using Flows](https://mlsanity.com/paper/2603.26506/) (2026)

## Abstract (arXiv)

Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population activity. Although their functional connectivity is low-rank, it lacks independence interpretations, making it difficult to assign distinct computational roles to different latent dimensions. To address this, we propose the Factored Recurrent Neural Network (FacRNN), a generative lrRNN framework that assumes group-wise independence among latent dynamics while allowing flexible within-group entanglement. These independent latent groups allow latent dynamics to evolve separately, but are internally rich for complex computation. We reformulate the lrRNN under a variational autoencoder (VAE) framework, enabling us to introduce a partial correlation penalty that encourages independence between groups of latent dimensions. Experiments on synthetic, monkey M1, and mouse voltage imaging data show that FacRNN consistently improves the disentanglement and interpretability of learned neural latent trajectories in low-dimensional space and low-rank connectivity over baseline lrRNNs that do not encourage group-wise independence.