mlsanityData to 14 Oct 2026

Neural Latents Benchmark '21: Evaluating latent variable models of neural population activity

arXiv 2109.04463 ↗First posted 9 Sep 2021cs.LG q-bio.NCcited by 60

Not on the map. Why?

Abstract (arXiv)

Advances in neural recording present increasing opportunities to study neural activity in unprecedented detail. Latent variable models (LVMs) are promising tools for analyzing this rich activity across diverse neural systems and behaviors, as LVMs do not depend on known relationships between the activity and external experimental variables. However, progress with LVMs for neuronal population activity is currently impeded by a lack of standardization, resulting in methods being developed and compared in an ad hoc manner. To coordinate these modeling efforts, we introduce a benchmark suite for latent variable modeling of neural population activity. We curate four datasets of neural spiking activity from cognitive, sensory, and motor areas to promote models that apply to the wide variety of activity seen across these areas. We identify unsupervised evaluation as a common framework for evaluating models across datasets, and apply several baselines that demonstrate benchmark diversity. We release this benchmark through EvalAI. http://neurallatents.github.io

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). Builds on 21 of its 99 references that are in the map. First posted on arXiv 9 Sep 2021.

Builds on

21 of 99 references.

References · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
  3. 2021Representation learning for neural population activity with Neural Data Transformerscited by 50
  4. 2020Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAEcited by 48
  5. 2017Machine learning for neural decodingcited by 45
  6. 2019Hierarchical Optimal Transport for Multimodal Distribution Alignmentcited by 38
  7. 2016Linear dynamical neural population models through nonlinear embeddingscited by 36
  8. 2019EvalAI: Towards Better Evaluation Systems for AI Agentscited by 34
  9. 2018Adversarial Domain Adaptation for Stable Brain-Machine Interfacescited by 27
  10. 2018Tree-Structured Recurrent Switching Linear Dynamical Systems for Multi-Scale Modelingcited by 27
  11. 2016Variational Latent Gaussian Process for Recovering Single-Trial Dynamics from Population Spike Trainscited by 22
  12. 2019Enabling hyperparameter optimization in sequential autoencoders for spiking neural datacited by 18
9 more
  1. 2015On Simplicity and Complexity in the Brave New World of Large-Scale Neurosciencecited by 15
  2. 2020Manifold GPLVMs for discovering non-Euclidean latent structure in neural datacited by 14
  3. 2019Neural Dynamics Discovery via Gaussian Process Recurrent Neural Networkscited by 13
  4. 2019Poisson-Randomized Gamma Dynamical Systemscited by 12
  5. 2021Building population models for large-scale neural recordings: opportunities and pitfallscited by 9
  6. 2019Deep Random Splines for Point Process Intensity Estimation of Neural Population Datacited by 8
  7. 2019Efficient non-conjugate Gaussian process factor models for spike count data using polynomial approximationscited by 8
  8. 2017Extracting low-dimensional dynamics from multiple large-scale neural population recordings by learning to predict correlationscited by 4
  9. 2020Incorporating structured assumptions with probabilistic graphical models in fMRI data analysiscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 13; 2024: 11; 2025: 15; 2026: 14.

60 papers.

Sort:

By area:

  1. 2022Learnable latent embeddings for joint behavioral and neural analysiscited by 117
  2. 2023A Unified, Scalable Framework for Neural Population Decodingcited by 61
  3. 2024Towards a "universal translator" for neural dynamics at single-cell, single-spike resolutioncited by 28
  4. 2022STNDT: Modeling Neural Population Activity with a Spatiotemporal Transformercited by 23
  5. 2025Neural Encoding and Decoding at Scalecited by 20
  6. 2022Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformerscited by 18
  7. 2024Inferring stochastic low-rank recurrent neural networks from neural datacited by 15
  8. 2022The Sensorium competition on predicting large-scale mouse primary visual cortex activitycited by 14
  9. 2024Latent Diffusion for Neural Spiking Datacited by 12
  10. 2025ZAPBench: A Benchmark for Whole-Brain Activity Prediction in Zebrafishcited by 10
  11. 2023Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral Datacited by 9
  12. 2025Generalizable, real-time neural decoding with hybrid state-space modelscited by 9
38 more
  1. 2023lfads-torch: A modular and extensible implementation of latent factor analysis via dynamical systemscited by 8
  2. 2023Learning Time-Invariant Representations for Individual Neurons from Population Dynamicscited by 8
  3. 2024Brain-to-Text Benchmark '24: Lessons Learnedcited by 8
  4. 2024eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modelingcited by 7
  5. 2025POCO: Scalable Neural Forecasting through Population Conditioningcited by 7
  6. 2025BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activitycited by 7
  7. 2022Expressive architectures enhance interpretability of dynamics-based neural population modelscited by 6
  8. 2023Recurrences reveal shared causal drivers of complex time seriescited by 5
  9. 2023Linear Time GPs for Inferring Latent Trajectories from Neural Spike Trainscited by 5
  10. 2023SiBBlInGS: Similarity-driven Building-Block Inference using Graphs across Statescited by 5
  11. 2023Neural Latent Aligner: Cross-trial Alignment for Learning Representations of Complex, Naturalistic Neural Datacited by 5
  12. 2024Multi-Region Markovian Gaussian Process: An Efficient Method to Discover Directional Communications Across Multiple Brain Regionscited by 5
  13. 2025Animal behavioral analysis and neural encoding with transformer-based self-supervised pretrainingcited by 5
  14. 2024BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge Distillationcited by 4
  15. 2024Generative Modeling of Neural Dynamics via Latent Stochastic Differential Equationscited by 4
  16. 2022Understanding Neural Coding on Latent Manifolds by Sharing Features and Dividing Ensemblescited by 3
  17. 2023Real-Time Variational Method for Learning Neural Trajectory and its Dynamicscited by 3
  18. 2023Graph Laplacian Learning with Exponential Family Noisecited by 3
  19. 2025Neuroprobe: Evaluating Intracranial Brain Responses to Naturalistic Stimulicited by 3
  20. 2025Contrastive Diffusion Alignment: Learning Structured Latents for Controllable Generationcited by 2
  21. 2025Energy-based Autoregressive Generation for Neural Population Dynamicscited by 2
  22. 2026SpikeProphecy: A Large-Scale Benchmark for Autoregressive Neural Population Forecastingcited by 2
  23. 2023Inferring Population Dynamics in Macaque Cortexcited by 1
  24. 2023Predictive variational autoencoder for learning robust representations of time-series datacited by 1
  25. 2024QuantFormer: Learning to Quantize for Neural Activity Forecasting in Mouse Visual Cortexcited by 1
  26. 2025Modeling Neural Activity with Conditionally Linear Dynamical Systemscited by 1
  27. 2025Benchmarking Probabilistic Time Series Forecasting Models on Neural Activitycited by 1
  28. 2026BEAST3D: Animal behavioral analysis and neural encoding from multi-view video via Gaussian splattingcited by 1
  29. 2026Leveraging unlabelled data for generalizable neural population decodingcited by 1
  30. 2021Overcoming the Domain Gap in Neural Action Representationscited by 0
  31. 2023Latent Dynamical Implicit Diffusion Processescited by 0
  32. 2024When predict can also explain: few-shot prediction to select better neural latentscited by 0
  33. 2024Learning Coupled Subspaces for Multi-Condition Spike Datacited by 0
  34. 2025Langevin Flows for Modeling Neural Latent Dynamicscited by 0
  35. 2025Hierarchical Stochastic Differential Equation Models for Latent Manifold Learning in Neural Time Seriescited by 0
  36. 2025Revealing Neurocognitive and Behavioral Patterns by Unsupervised Manifold Learning from Dynamic Brain Datacited by 0
  37. 2025A Scalable, Causal, and Energy Efficient Framework for Neural Decoding with Spiking Neural Networkscited by 0
  38. 2026RPNT: Robust Pre-trained Neural Transformer -- A Pathway for Generalized Motor Decodingcited by 0

50 most cited of 60 All 60 (JSON)