Machine Learning Methods for Studying Latent Neural Activity Dynamics
Not on the map. Why?
Abstract (arXiv)
Recent developments in brain recording are driving a demand for machine learning tools capable of decoding the latent structure of large populations of neurons. In this paper, we provide a comprehensive survey that outlines the trajectory of Latent Variable Models (LVMs) from early state-space models to more recent deep generative models. We organize the literature into three closely related domains: (1) Single-Region Latent Dynamics, which includes models such as linear dynamical systems to more complex dynamics represented by Recurrent Neural Networks (RNNs) and Neural Ordinary Differential Equations (ODEs); (2) Multi-Region Communication, which employs probabilistic as well as subspace methods to study how information is transferred across different brain areas considering synaptic propagation delays and network connectivity; and (3) Behavior-Aligned Modeling, which seeks to disentangle neural activity related to task performance from other internal states via supervised or contrastive learning. This survey also includes large-scale neural foundation models, such as Transformers and diffusion models, that rely on large-scale pre-training for optimal performance across subjects. Finally, we conclude and discuss benchmarks, evaluation criteria, and open challenges, such as the ability to identify causal links or directionality of communication, to facilitate future research for bridging interpretable brain dynamics with reliable neural decoding.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 68 references that are in the map. First posted on arXiv 9 Jun 2026.
Builds on
32 of 68 references.
References · 32
- 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 503
- 2022Learnable latent embeddings for joint behavioral and neural analysiscited by 117
- 2023A Unified, Scalable Framework for Neural Population Decodingcited by 61
- 2021Neural Latents Benchmark '21: Evaluating latent variable models of neural population activitycited by 60
- 2021Representation learning for neural population activity with Neural Data Transformerscited by 50
- 2021Large-scale neural recordings call for new insights to link brain and behaviorcited by 28
- 2024Towards a "universal translator" for neural dynamics at single-cell, single-spike resolutioncited by 28
- 2016Variational Latent Gaussian Process for Recovering Single-Trial Dynamics from Population Spike Trainscited by 22
- 2025Brain Foundation Models: A Survey on Advancements in Neural Signal Processing and Brain Discoverycited by 22
- 2025Neural Encoding and Decoding at Scalecited by 20
- 2017full-FORCE: A Target-Based Method for Training Recurrent Networkscited by 16
- 2024Inferring stochastic low-rank recurrent neural networks from neural datacited by 15
20 more
- 2022Robust alignment of cross-session recordings of neural population activity by behaviour via unsupervised domain adaptationcited by 13
- 2023Interpretable statistical representations of neural population dynamics and geometrycited by 12
- 2024Latent Diffusion for Neural Spiking Datacited by 12
- 2024Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systemscited by 11
- 2024Exploring Behavior-Relevant and Disentangled Neural Dynamics with Generative Diffusion Modelscited by 9
- 2024Self-supervised contrastive learning performs non-linear system identificationcited by 9
- 2025Generalizable, real-time neural decoding with hybrid state-space modelscited by 9
- 2025BRAID: Input-Driven Nonlinear Dynamical Modeling of Neural-Behavioral Datacited by 8
- 2023Expressive dynamics models with nonlinear injective readouts enable reliable recovery of latent features from neural activitycited by 6
- 2023Neural Latent Aligner: Cross-trial Alignment for Learning Representations of Complex, Naturalistic Neural Datacited by 5
- 2024Multi-Region Markovian Gaussian Process: An Efficient Method to Discover Directional Communications Across Multiple Brain Regionscited by 5
- 2025Animal behavioral analysis and neural encoding with transformer-based self-supervised pretrainingcited by 5
- 2024CREIMBO: Cross-Regional Ensemble Interactions in Multi-view Brain Observationscited by 4
- 2024Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processescited by 4
- 2025Accurate identification of communication between multiple interacting neural populationscited by 2
- 2025Energy-based Autoregressive Generation for Neural Population Dynamicscited by 2
- 2024Diffusion-Based Generation of Neural Activity from Disentangled Latent Codescited by 1
- 2025Identifying interactions across brain areas while accounting for individual-neuron dynamics with a Transformer-based variational autoencodercited by 1
- 2025Characterizing Neural Manifolds' Properties and Curvatures using Normalizing Flowscited by 1
- 2025Disentangling Shared and Private Neural Dynamics with SPIRE: A Latent Modeling Framework for Deep Brain Stimulationcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics
- 2024Meta-Dynamical State Space Models for Integrative Neural Data Analysis
- 2022Neural State-Space Modeling with Latent Causal-Effect Disentanglement
- 2022Expressive architectures enhance interpretability of dynamics-based neural population models
- 2026Probabilistic Prediction of Neural Dynamics via Autoregressive Flow Matching
- 2024A Review of Latent Representation Models in Neuroimaging
- 2023Latent Dynamical Implicit Diffusion Processes
- 2023Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion Models