mlsanityData to 14 Oct 2026

Temporal Variational Implicit Neural Representations

arXiv 2506.01544 ↗First posted 2 Jun 2025cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

We introduce Temporal Variational Implicit Neural Representations (TV-INRs), a probabilistic framework for modeling irregular multivariate time series that enables efficient and accurate individualized imputation and forecasting. By integrating implicit neural representations with latent variable models, TV-INRs learn distributions over time-continuous generator functions conditioned on signal-specific covariates. Unlike existing INR approaches that require extensive training, fine-tuning or meta-learning, our method achieves accurate individualized predictions through a single forward pass. Our experiments demonstrate that with a single TV-INRs instance, we can accurately solve diverse imputation and forecasting tasks, offering a computationally efficient and scalable solution for real-world applications. TV-INRs performs particularly well in low-data regimes, where on several datasets it achieves substantially lower imputation error, including order-of-magnitude improvements.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 37 of its 51 references that are in the map. First posted on arXiv 2 Jun 2025.

Builds on

37 of 51 references.

References · 37

  1. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  2. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  4. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  5. 2016HyperNetworkscited by 1,027
  6. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  7. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
  8. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  9. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 554
  10. 2022Transformers in Time Series: A Surveycited by 497
  11. 2021Monash Time Series Forecasting Archivecited by 267
  12. 2022From data to functa: Your data point is a function and you can treat it like onecited by 187
25 more
  1. 2019Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directionscited by 172
  2. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 169
  3. 2021Implicit Neural Representations for Image Compressioncited by 162
  4. 2018Inference Suboptimality in Variational Autoencoderscited by 132
  5. 2014Neural Variational Inference and Learning in Belief Networkscited by 117
  6. 2021Generative Models as Distributions of Functionscited by 89
  7. 2022COIN++: Neural Compression Across Modalitiescited by 82
  8. 2022Transformers as Meta-Learners for Implicit Neural Representationscited by 79
  9. 2017Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithmcited by 65
  10. 2024ContiFormer: Continuous-Time Transformer for Irregular Time Series Modelingcited by 63
  11. 2015Gated Feedback Recurrent Neural Networkscited by 54
  12. 2018Deep Learning with Long Short-Term Memory for Time Series Predictioncited by 39
  13. 2021Missing Value Imputation on Multidimensional Time Seriescited by 33
  14. 2022HyperTime: Implicit Neural Representation for Time Seriescited by 24
  15. 2020On the Global Optimality of Model-Agnostic Meta-Learningcited by 21
  16. 2022Learning Deep Time-index Models for Time Series Forecastingcited by 18
  17. 2023Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representationscited by 17
  18. 2024DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representationscited by 16
  19. 2022Time-Series Anomaly Detection with Implicit Neural Representationcited by 10
  20. 2020Variational Hyper-Encoding Networkscited by 5
  21. 2023Variational Mixture of HyperGenerators for Learning Distributions Over Functionscited by 5
  22. 2023On Masked Pre-training and the Marginal Likelihoodcited by 5
  23. 2022NeuralMeshing: Differentiable Meshing of Implicit Neural Representationscited by 3
  24. 2023MADS: Modulated Auto-Decoding SIREN for time series imputationcited by 3
  25. 2025Hyper-Transforming Latent Diffusion Modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Coordinate-Queryable Neural Field Reconstruction for EEG Spatial Super-Resolution with Unseen-Electrode Generationcited by 0