neural process family.
Work that followed Conditional Neural Processes and Neural Processes: papers that propose or extend an NP-family model, analyse NPs, or use one as their core method. A likely incomplete list that I put together, newest first.
- papers
- 460
- method themes
- 7
- application domains
- 21
- years
- 2018–2026
> about this list
What counts
- Included: the paper proposes or extends an NP-family model (CNP, NP, ANP, ConvCNP, Gaussian NP, TNP, CNAPs, CNMP and their descendants), analyses NPs, or uses one as its core method.
- Excluded: papers that only compare against NPs, use them as one baseline among several, or cite them in passing. Adjacent amortized-inference lines that position themselves against NPs (PFNs, VERSA, GQN, energy-based and generic exchangeable models) are also out. Earlier versions of the same paper are collapsed into one entry.
How the list was built
- Keyword searches of arXiv, OpenReview, PMLR, NeurIPS, ICLR, ICML, CVF and Crossref, plus the reference lists of the NP survey (Jha et al.) and NP PhD theses.
- Semantic Scholar citation sweeps of CNP (all 920 citers), NP, ANP, ConvCNP, ConvNP, TNP, AR-CNP, CNAPs, CNMP and 21 second-generation NP papers. The second sweep added one paper, so the list is close to saturated.
- Every entry was checked against arXiv, Crossref, OpenReview or the venue's accepted-paper list. Twelve OpenReview-only entries could not be checked automatically.
- Coverage is about 90 to 95 percent for ML venues and arXiv. The likeliest gaps are applied journal papers that Semantic Scholar does not index, and non-English venues. Years are first public appearance.
01Latent variables, objectives and inference
52 papers change what the latent variable captures, how NPs are trained, or how inference and context aggregation work.
2026
- Amortising Inference and Meta-Learning Priors in Neural Networks
NP whose latent is BNN weights, enabling amortized inference and learned weight priors.
- APIC: Amortized Physics-Informed Calibration using Neural Processes
Two-branch latent NP amortizing Kennedy-O'Hagan calibration across physical systems.
- DnNP: Denoising Input Uncertainty in Neural Processes
NP variant modelling and denoising uncertainty in input locations.
- Improving Neural Processes in the Low-Data Regime via Context-Subset Training and Self-Distillation
Context-subset training with self-distillation improves NPs when few tasks are available.
- Latent Space Robust Optimization of Neural Processes with Aligned Stratified Order-Statistic Loss Reduction
Stratified order-statistic loss counters latent particle imbalance in importance-weighted NPs.
- Modeling task uncertainty for neural processes to meta-learn with fewer tasks
Explicit task-uncertainty modelling lets NPs meta-learn from fewer training tasks.
- Neural Mixture Density Processes
Mixture-density latent structure and conditioning for more expressive NPs.
2025
- Distance-informed Neural Processes
Distance-aware latent with bi-Lipschitz encoder yields input-distance-sensitive NP uncertainty.
- Geometric Neural Process Fields
Probabilistic neural-field generalization using geometric bases and hierarchical latent NP inference.
- Learning Robust Neural Processes with Risk-Averse Stochastic Optimization
Risk-averse (tail-risk) training objective improving worst-case NP adaptation.
- MemoryINP: Memory Enhanced Neural Processes for Understanding-Based Informed Meta-Learning
Memory-augmented Informed NP for knowledge-conditioned meta-learning.
- Privacy-Preserving Neural Processes for Probabilistic User Modeling
Differentially private training of NPs for user modelling.
- Sparse Gaussian Neural Processes
Amortizes sparse GP inference with an NP, giving interpretable, prior-specifiable meta-learned models.
- Test Time Scaling for Neural Processes
Test-time sampling/refinement of miscalibrated NP global latent posteriors.
2024
- Combined Global and Local Information Diffusion of Neural Processes
Combines global and local context information diffusion to improve NP latent representations.
- Robust Neural Processes for Noisy Data
Studies NP behaviour under context noise and proposes training making NPs robust to it.
- Rényi Neural Processes
Rényi-divergence objective mitigates prior misspecification from coupled NP prior/posterior parameterization.
- Towards Automated Knowledge Integration From Human-Interpretable Representations
Informed Neural Process conditions NP priors on human-interpretable knowledge such as text.
2023
- Accurate Bayesian Meta-Learning by Accurate Task Posterior Inference
Replaces amortized Gaussian NP task posteriors with expressive non-amortized GMM variational inference.
- Adaptive Conditional Quantile Neural Processes
Quantile-regression CNP decoder with adaptive quantiles for multimodal predictive distributions.
- Adversarially Contrastive Estimation of Conditional Neural Processes
Adds an adversarial noise-contrastive objective to calibrate CNP predictive distributions beyond Gaussian likelihoods.
- Amortised Inference in Neural Networks for Small-Scale Probabilistic Meta-Learning
Amortized pseudo-likelihood BNN inference viewed as an NP whose latent is network weights.
- Autoencoding Conditional Neural Processes for Representation Learning
Partial Pixel Space VAE: treats CNP context-pixel selection as a latent variable for representation learning.
- Bridge the Inference Gaps of Neural Processes via Expectation Maximization
EM-style surrogate objective that tightens NP inference and reduces underfitting of latent NPs.
- Generalizable Neural Fields as Partially Observed Neural Processes
Casts neural-field generalization as a partially observed NP problem, outperforming gradient meta-learning.
- Global Perception Based Autoregressive Neural Processes
Autoregressive stacking with sliding-window positional refinement to enrich NP latent representations.
- Martingale Posterior Neural Processes
Replaces the NP latent prior with a martingale posterior built from generated pseudo-data.
- Neural Processes with Stability
Algorithmic-stability regularization makes NPs robust to noisy context points, with theoretical guarantees.
- Random Grid Neural Processes for Parametric Partial Differential Equations
Physics-informed latent NP with random collocation grids for probabilistic parametric PDE solutions.
- Research on neural processes with multiple latent variables
Uses multiple latent variables to relieve NP latent-dimensionality bottleneck and underfitting.
- Versatile Neural Processes for Learning Implicit Neural Representations
Bottleneck encoder plus hierarchical latent decoder lets NPs model complex implicit neural representations.
2022
- Contrastive Conditional Neural Processes
Adds in-instance and cross-instance contrastive losses to CNP training for robustness on high-dimensional data.
- Evidential Conditional Neural Processes
Replaces CNP Gaussian output with evidential hierarchy, separating epistemic and aleatoric uncertainty.
- Exploiting Inferential Structure in Neural Processes
Injects graphical-model structure into NP aggregation, yielding weighted neural sufficient statistics.
- Neural Variational Dropout Processes
Bayesian meta-learner that infers task-specific dropout rates from context, evaluated on NP-style regression and inpainting.
2021
- Bayesian Context Aggregation for Neural Processes
Replaces mean pooling with Bayesian aggregation of latent observations, weighting context points by confidence.
- Contrastive Neural Processes for Self-Supervised Learning
Self-supervised time-series learning: NP forecasting generates augmentations, trained with a new contrastive loss.
- Evidential Turing Processes
Combines evidential deep learning, NPs and neural Turing memory for calibrated classification and OOD rejection.
- Learning Neural Processes on the Fly
Anytime NP that gates between deep and shallow models via product-of-experts for low-and high-data regimes.
- Neural Bootstrapping Attention for Neural Processes
Parallel, memory-efficient bootstrap for attentive NPs by injecting random weights into encoder and loss.
- Neural Stochastic Differential Equations with Neural Processes Family Members for Uncertainty Estimation in Deep Learning
Combines neural SDE networks with NP-family components to estimate predictive uncertainty.
2020
- Bootstrapping Neural Processes
Replaces Gaussian latents with residual bootstrap over contexts to model functional uncertainty robustly.
- Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables
Hierarchical NP with global and per-point local latents trained by doubly stochastic variational inference.
- Function Contrastive Learning of Transferable Meta-Representations
Trains a CNP-style set encoder with a function-level contrastive loss, decoupled from the decoder.
- Meta Learning as Bayes Risk Minimization
Frames meta-learning as Bayes risk minimisation; proposes Gaussian NP variant whose posterior updates behave correctly.
- NP-PROV: Neural Processes with Position-Relevant-Only Variances
Derives predictive variance from a position-only latent space so uncertainty stays bounded under value drift.
- Residual Neural Processes
Adds a Bayesian last layer with residual NP correction, speeding convergence and fixing underfitting on simple tasks.
- Uncertainty in Neural Processes
Studies pooling operators and variational families for better NP posterior predictive quality with tiny contexts.
2019
- Meta-Learning without Memorization
Identifies task memorisation in MAML and CNPs; proposes information-theoretic meta-regularisation (e.g., MR-CNP).
- Wasserstein Neural Processes
Replaces likelihood-based NP training with sliced Wasserstein distance to handle misspecified likelihoods.
2018
- Conditional BRUNO: A Neural Process for Exchangeable Labelled Data
Exchangeable recurrent latent model conditioned on labels, giving an NP with exact conditional updates.
- Empirical Evaluation of Neural Process Objectives
Compares ELBO, conditional-ELBO and maximum-likelihood style objectives for training latent NPs.
02Attention and transformer NPs
23 papers replace mean pooling with attention, from attentive NPs to transformer NPs and their memory-efficient variants.
2026
- Incremental Transformer Neural Processes
Causal-masked TNP with cached updates for efficient streaming context.
- OANP: Operator Attentive Neural Processes for Detecting Unreliable Predictions and Covariate Shift
Operator-attentive NP flags unreliable predictions and covariate shift.
- Spectral Transformer Neural Processes
Spectral representations within TNP attention for improved function modelling.
- Transformer Neural Processes with growing receptive field for uncertainty prediction over clustered observations
Growing-receptive-field TNP attention for clustered, non-uniform observations.
2025
- Dimension Agnostic Neural Processes
Dimension-aggregator transformer lets one NP handle tasks with varying input/output dimensionality.
- Exploring Pseudo-Token Approaches in Transformer Neural Processes
Induced Set Attentive NPs: pseudo-token TNPs trading compute and accuracy.
- Scalable Spatiotemporal Inference with Biased Scan Attention Transformer Neural Processes
Biased scan attention TNP (successor to TNP-KR) scales to large spatiotemporal context sets.
2024
- Amortized Probabilistic Conditioning for Optimization, Simulation and Inference
Amortized Conditioning Engine: TNP that conditions on and predicts interpretable latents and data.
- Gridded Transformer Neural Processes for Spatio-Temporal Data
Maps unstructured observations to a grid and applies efficient grid transformers for large-scale NPs.
- In-Context In-Context Learning with Transformer Neural Processes
TNP conditions on multiple related datasets in context, not just one context set.
- Spatial multi-attention conditional neural processes
CNP variant with multiple spatial attention mechanisms for spatial prediction.
- Transformer Neural Processes - Kernel Regression
TNP-KR: kernel-regression attention blocks for scalable spatiotemporal TNPs; precursor of BSA-TNP.
2023
- End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes
TNP-based acquisition function trained end-to-end with RL for meta-Bayesian optimisation.
- Memory Efficient Neural Processes via Constant Memory Attention Block
Constant Memory Attention Block enables NPs with constant memory and efficient context updates.
2022
- Efficient Queries Transformer Neural Processes
Restructures TNP attention so query cost no longer scales quadratically with context size.
- Latent Bottlenecked Attentive Neural Processes
Compresses context into fixed latent tokens, giving sub-quadratic NPs with near-TNP accuracy.
- Research on Patch Attentive Neural Process
ANP variant operating on image patches (ViT/MAE-inspired) for cheaper, more accurate image completion.
- Semi-Parametric Inducing Point Networks and Neural Processes
Linear-cost cross-attention with inducing points; yields Inducing Point NP handling very large contexts.
- Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling
Casts NP prediction as masked transformer sequence modelling; includes autoregressive and Gaussian-output variants.
2021
- Neural Processes with Stochastic Attention: Paying more attention to the context dataset
Treats attention weights as latent variables with an information-theoretic objective so predictions use context better.
2020
- Cost-effective Interactive Attention Learning with Neural Attention Processes
NP-based stochastic attention generator that absorbs human attention feedback without retraining.
2019
- Attentive Neural Processes
Adds self- and cross-attention over context points to fix NP underfitting.
- Improved Attentive Neural Processes
Adds attention-based local latents per context point and decoder self-attention to ANPs.
03Convolutional and equivariant NPs
20 papers build translation equivariance or other symmetries into NPs, starting from ConvCNPs.
2026
- Bias-Spectrum Neural Processes for Parametric PDEs: Architecture Priors Meet PDE Constraints
Spectral-bias NP architecture with PDE constraints for calibrated parametric PDE surrogates.
- Latent Twin Operator
ConvCNP-style encoder/decoder with latent evolution for resolution-free PDE surrogates.
- Neural Operator Processes for Probabilistic Operator Learning under Partial Observations
Unifies NP conditioning with neural-operator decoding for fields from sparse observations.
- Revisiting Neural Processes via Fourier Transform and Volterra Series
Spectral/Volterra-series view of NP encoders yielding new nonlinear spectral NP architectures.
- Wavelet Conditional Neural Processes
Wavelet-domain context representation for multi-resolution CNPs.
2024
- Approximately Equivariant Neural Processes
Relaxes strict equivariance in ConvCNPs/TNPs via learned symmetry-breaking inputs.
- FNP: Fourier Neural Processes for Arbitrary-Resolution Data Assimilation
Fourier-domain NP handling arbitrary-resolution observations for data assimilation.
- Noise-Aware Differentially Private Regression via Meta-Learning
DPConvCNP combines ConvCNP with functional DP mechanism, meta-trained to output private predictors.
- Spectral Convolutional Conditional Neural Processes
Fourier neural operator layers in ConvCNPs capture long-range dependencies efficiently.
- Translation Equivariant Transformer Neural Processes
Translation-equivariant attention in TNPs, improving generalization in spatio-temporal tasks.
- Warped Convolutional Conditional Neural Processes
Input warping extends ConvCNPs to non-stationary inputs.
2023
- Bayesian Convolutional Deep Sets with Task-Dependent Stationary Prior
Random ConvDeepSet representations with task-dependent stationary priors for ConvCNP-type models.
- Geometric Neural Diffusion Processes
Extends neural diffusion processes to manifolds and tensor fields with group equivariance.
- Practical Equivariances via Relational Conditional Neural Processes
Relational encoding gives scalable translation/rotation-equivariant CNPs in higher input dimensions.
2021
- Global Convolutional Neural Processes
Convolutional latent NP with global uncertainty representation aggregated over discretised inputs; strong latent-NP likelihoods.
- GP-ConvCNP: Better Generalization for Convolutional Conditional Neural Processes on Time Series Data
Adds a GP to the ConvCNP pipeline for better time-series generalisation and sample-based predictions.
- Group Equivariant Conditional Neural Processes
EquivCNP: decomposition theorem enabling CNPs equivariant to Lie groups such as rotation and scaling.
2020
- Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processes
Characterises equivariant stochastic fields and builds steerable CNPs equivariant to rotations/reflections of vector fields.
- Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes
ConvNP: latent-variable ConvCNP extension with translation-equivariant latent function; studies ML vs ELBO training.
2019
- Convolutional Conditional Neural Processes
Translation-equivariant CNP via functional SetConv embedding and CNN processing; proves representation theorem.
05Sequential, temporal and dynamical NPs
17 papers extend NPs to sequences, dynamics and continuous-time processes.
2026
- Amortized Variational Inference of Latent Intensities from Replicated Point Patterns
NP-based amortized variational inference of shared point-process intensities.
- Reinforced Neural Processes: Memory-Efficient Time-Series Forecasting with a World-Feedback-Trained Memory Policy
RL-trained memory policy selects which observations NPs retain under bounded context.
2025
- KooNPro: A Variance-Aware Koopman Probabilistic Model Enhanced by Neural Process for Time Series Forecasting
Koopman probabilistic forecaster with NP-based variance modelling.
- Meta-Learning Contextual Time Series Forecasting with Neural Processes
NP architecture conditioning forecasts on context from multiple related time series.
2024
- Learning continuous network emerging dynamics from scarce observations via data-adaptive stochastic processes
NDP4ND extends neural ODE processes to network dynamics learned from sparse observations.
- Neural processes with event triggers for fast adaptation to changes
Event-triggered context updating lets CNPs detect and adapt to changing dynamical systems online.
2023
- Meta Temporal Point Processes
Frames temporal point processes as NPs with context sets and attentive local history matching.
2022
- Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphs
Combines sequential NPs, neural ODEs and graph encoders for link prediction on sparse dynamic graphs.
2021
- Deep Bayesian Active Learning for Accelerating Stochastic Simulation
Interactive NP: spatiotemporal NP surrogate plus latent-information-gain acquisition for active learning of simulators.
- Meta-learning using privileged information for dynamics
Extends Neural ODE Processes to use privileged side information during training via flexible aggregation.
- Neural ODE Processes
Merges neural ODEs with NPs: latent ODE dynamics conditioned on context for adaptive time series.
- Social Processes: Self-Supervised Meta-Learning over Conversational Groups for Forecasting Nonverbal Social Cues
NP-family sequence model (incl. attentive variant) forecasting future window distributions per conversation group.
- When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting
EpiFNP: functional-NP-style model with stochastic correlation graphs over past sequences for calibrated forecasts.
2020
- Robustifying Sequential Neural Processes
Recurrent memory reconstruction attention for SNPs using imaginary context to fix underfitting in meta-transfer learning.
2019
- Recurrent Attentive Neural Process for Sequential Data
Embeds an attentive NP within a recurrent network to capture temporal order in sequential data.
- Recurrent Neural Processes
Conditional state-space models built from NPs, inferring slow latent time scales in fast time series.
- Sequential Neural Processes
State-space model whose latent transitions evolve NP latents over time, modelling dynamic stochastic processes.
06Structured settings: graphs, multi-task, mixtures
33 papers adapt NPs to graphs, multiple tasks, mixtures of experts, heterogeneous data and causal structure.
2026
- Amortized Counterfactual Prediction with Graph Neural Networks
Counterfactual Graph NP answers counterfactual queries without estimating a causal graph.
- Multi-Fidelity PDE Learning with Adaptive Spectral Neural Processes
Physics-informed spectral NP with autoregressive multi-fidelity corrections.
- NPBoost: Neural Processes with Gradient-Boosted Fixed Effects
Mixed-effects NP: gradient-boosted fixed effects plus NP random effects.
2025
- Continual learning via probabilistic exchangeable sequence modelling
CL-BRUNO: NP-based exchangeable generative model for tractable Bayesian continual learning.
- Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning
MACE-TNP predicts Bayesian model-averaged interventional distributions end-to-end.
- Graph Transformer Neural Processes
Represents NP inputs as graphs with similarity-labelled edges for data-efficient uncertainty.
- Multi-task Neural Diffusion Processes
Task encoder conditions neural diffusion processes for multi-task few-shot regression.
- Resolving Node Identifiability in Graph Neural Processes via Laplacian Spectral Encodings
Laplacian positional encodings with theory resolving node identifiability in graph NPs.
2024
- A Meta-Learning Approach to Bayesian Causal Discovery
Bayesian causal NP: meta-learned transformer approximating posteriors over causal graphs.
- Hierarchical Linear Symbolized Tree-Structured Neural Processes
Tree-structured hierarchical NP with linear symbolization of context relationships.
- Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modeling
Models residuals between fidelity levels within NPs for scalable multi-fidelity surrogate modelling.
- Topology of Neural Processes
Vietoris-Rips topological structure among context points to inform NP representations.
- Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process
Graph functional NP over latent rationales for calibrated, interpretable graph classification.
2023
- Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation
Multimodal NP aggregates multiple input modalities with dynamic context memory and calibrated uncertainty.
- Disentangled Multi-Fidelity Deep Bayesian Active Learning
Multi-fidelity NP-style model with disentangled per-fidelity latents for deep Bayesian active learning.
- Episodic Multi-Task Learning with Heterogeneous Neural Processes
Heterogeneous NPs share meta-knowledge across heterogeneous tasks and episodes via hierarchical latents.
- Graph Neural Processes for Spatio-Temporal Extrapolation
Spatio-temporal graph NP with cross-set convolution and uncertainty-aware aggregation for extrapolation.
- NPCL: Neural Processes for Uncertainty-Aware Continual Learning
Hierarchical task-specific NP latents for continual learning with uncertainty-guided forgetting control.
2022
- Compositional Law Parsing with Latent Random Functions
CLAP: concept-specific latent random functions instantiated with NPs to parse compositional scene laws.
- Learning Expressive Meta-Representations with Mixture of Expert Neural Processes
Mixture of expert latent NPs with assignment latents for multimodal task distributions.
- Multi-fidelity Hierarchical Neural Processes
Hierarchical latent NP for multi-fidelity surrogate modelling, sharing info across fidelity levels.
- Uncertainty Estimation With Neural Processes for Meta-Continual Learning
NP-based meta-continual learner estimating uncertainty under evolving data streams.
2021
- Bayesian Relational Generative Model for Scalable Multi-modal Learning
Multi-modal relational NP learning a dependency graph across modalities, extending functional NPs.
- How Neural Processes Improve Graph Link Prediction
NPGNN: NP built on graph neural networks for transductive and inductive link prediction.
- Multi-Task Neural Processes
Hierarchical Bayesian NP sharing function-space priors across tasks for multi-task learning.
- Multi-Task Processes
MTNP (arXiv title 'Multi-Task Neural Processes'): hierarchical latents jointly inferring correlated tasks.
2020
- Factorized Neural Processes for Neural Processes: K-Shot Prediction of Neural Responses
NP with latent split into receptive-field location and tuning properties for K-shot neuron response prediction.
- Message Passing Neural Processes
Incorporates graph message passing into NPs to exploit relational structure among data points.
- MFPC-Net: Multi-fidelity Physics-Constrained Neural Process
NP surrogate fusing low-and high-fidelity simulation data with physics-law constraints.
2019
- Graph Neural Processes: Towards Bayesian Graph Neural Networks
CNP over graph-structured data using spectral edge features for uncertainty-aware edge imputation.
- The Functional Neural Process
Exchangeable model learning a dependency graph over latent point representations instead of a global latent.
2018
- Conditional Graph Neural Processes: A Functional Autoencoder Approach
Applies CNPs on graphs as a functional autoencoder for edge imputation.
- Neural Processes Mixed-Effect Models for Deep Normative Modeling of Clinical Neuroimaging Data
NP-based mixed-effects model capturing site/subject random effects for normative modelling.
07Theory, evaluation, surveys and theses
12 papers analyse, benchmark, survey or package the family. The theses and resources below them are listed for reference but not counted.
2026
- Characterizing the Representational Capacity of Neural Processes
Proves a strict expressivity hierarchy among CNP, ANP, TNP and latent variants.
- On the Conditioning Consistency Gap in Conditional Neural Processes
Defines and bounds a KL conditioning-consistency gap quantifying CNP Kolmogorov inconsistency.
- Three Costs of Amortizing Gaussian Process Inference with Neural Processes
Analyses approximation costs when NPs amortize GP posterior inference.
2025
- Learning to Generalize: An Information Perspective on Neural Processes
Information-theoretic generalization bounds for NPs and sharpness-reducing stability regularization.
2024
- On Neural Process Pooling Operator Choice and Posterior Calibration
Studies how context-aggregation pooling choice affects NP latent posterior calibration.
2023
- NP-SSL: A Modular and Extensible Self-supervised Learning Library with Neural Processes
Unified modular library for building, benchmarking and self-supervised extension of NP variants.
2022
- The Neural Process Family: Survey, Applications and Perspectives
Survey of NP variants, theory, applications and open problems.
- What Matters For Meta-Learning Vision Regression Tasks?
New vision regression meta-learning benchmarks; analyses augmentation and regularisation; adds functional contrastive learning to CNPs.
2020
- Frequency Decomposition in Neural Processes
Shows deterministic NPs act like Fourier decompositions; bounds representable frequency by latent size.
2019
- Probing Uncertainty Estimates of Neural Processes
Proposes interpretable metrics probing the inductive biases of NP uncertainty estimates.
2018
- On the Connection between Neural Processes and Gaussian Processes with Deep Kernels
Shows NPs can be equivalent to GPs with deep kernels under certain conditions.
- Verification of deep probabilistic models
Verification framework for probabilistic models, demonstrated on certifying properties such as monotonicity of (C)NPs.
Theses and resources17 · not counted
2025
- Modelling data on and off the grid using Neural Processes with applications in weather prediction
PhD thesis on NPs for gridded and off-grid data, applied to weather prediction.
- On Transformer Neural Processes
PhD thesis on transformer NPs (TE-TNP, gridded TNPs, approximate equivariance).
2024
- {On, Off}-The-Grid Data Modelling Using Transformer Neural Processes
MPhil dissertation on TNPs for mixed gridded/off-grid data.
2023
- Amortised Inference in Bayesian Neural Networks
Amortized pseudo-observation BNN inference framed as a new NP-family member.
- Autoregressive Diffusion Neural Processes
MPhil dissertation combining diffusion models with autoregressive NPs.
- DeepSensor (Python package for environmental neural processes)
Open-source toolkit for ConvNP-based environmental interpolation, downscaling and sensor placement.
- Towards Data-Efficient Deep Learning with Meta-Learning and Symmetries
DPhil thesis covering MetaFun and Markov Neural Processes.
2022
- Approximate Inference in Bayesian Neural Networks and Translation Equivariant Neural Processes
BNN approximate-inference limits plus convolutional (translation-equivariant) NPs.
- Better Encoders for Neural Process Family Models
MPhil dissertation studying improved encoder architectures for NPF models.
- Convolutional Conditional Neural Processes (PhD thesis)
Thesis on ConvCNPs, Gaussian NPs and autoregressive CNPs; posted to arXiv in 2024.
- Functional representation learning for uncertainty quantification and fast skill transfer
Thesis on hierarchical (DSVNP), mixture-of-experts and graph NPs plus SI-NP objective.
- The Neural Processes Family: Translation Equivariance and Output Dependencies
Thesis on ConvCNP, ConvLNP, ConvGNP and AR CNPs with climate/medical applications.
2021
- Advances in Probabilistic Meta-Learning and the Neural Process Family
NPF tutorial, expressivity analysis, translation-equivariant DeepSets/ConvCNPs, and CNAPs.
2020
- Geometric Extensions of Neural Processes
Thesis covering graph NPs via Laplacian spectra and Wasserstein-trained NPs.
- Neural Process Family (website and library)
Tutorial-style overview and unified PyTorch implementations of CNP, NP, ANP, ConvCNP and ConvNP.
2019
- Interpretable Models in Probabilistic Machine Learning
DPhil thesis whose final part covers attention-based stochastic process models (ANPs).
- Spatiotemporal Modeling using Recurrent Neural Processes
Recurrent neural processes for spatiotemporal forecasting with learned kernels and structured uncertainty.
08Applications by domain
286 papers use an NP-family model as their core method. Energy and engineering and robotics lead with 38 each, followed by general ML problems (28) and climate, weather and environment (24).
Energy & engineering38
2026
- Accelerating Load-Pull Measurements Using Attentive Neural Processes
ANP predicts RF load-pull contours from few measurements to speed device characterization.
- ASAP: Accelerating Corner-Based Timing Analysis With Bayesian Active Self-Attention Neural Process
Self-attention NP with active learning gives confidence-aware multi-corner static timing predictions for chip design.
- Automatic Tuning and Matching for NMR Probes Based on Physics-Informed Conditional Neural Processes
Physics-informed CNP enables automatic tuning and matching of NMR probes.
- Behaviour-Conditioned Neural Processes for Adaptive Residential Short-Term Load Forecasting
ANP with inferred discrete behavioural latent conditions household load forecasts.
- Collaborative Probabilistic Wind Power Forecasting Using Adaptive Flow Matching Enhanced Neural Process
Flow-matching-enhanced NP produces collaborative probabilistic wind power forecasts across farms.
- Few-Shot Emergency Response Equipment Fault Diagnosis for Coal Electricity Integrated Enterprises Based on Structure-Aware Neural Processes
Structure-aware NPs for few-shot equipment fault diagnosis.
- Meta-Adaptive Neural Processes for Cross-Chemistry SOH Probabilistic Prediction: Robust to Noise and Incomplete Charging Data
Meta-adaptive NP predicts lithium-ion battery state of health across chemistries with uncertainty.
- Physics-guided neural process with adaptive learning for uncertainty quantification of aero-engine remaining useful life
Physics-guided adaptive NP quantifies uncertainty in aero-engine RUL prediction.
- Physics-informed autoregressive neural processes for wear degradation prognostics with application to magnetic head
Physics-informed autoregressive NP forecasts wear degradation of magnetic heads.
- Physics-informed conditional neural processes for reconstructing transient temperature fields of turbine blades from sparse maximum temperature data
Physics-informed CNP reconstructs transient turbine-blade temperature fields from sparse measurements.
- Regime-aware conditional neural processes with multi-criteria decision support for operational electricity price forecasting
Regime-specific CNP mixture forecasts German day-ahead hourly electricity prices.
- Resilient Load Forecasting under Climate Change: Adaptive Conditional Neural Processes for Few-Shot Extreme Load Forecasting
AdaCNP gives calibrated few-shot electricity load forecasts during extreme-weather regime shifts.
- Unbiased estimation attentive neural processes for state assessment of multi-working condition industrial robots
Unbiased-estimation ANP assesses industrial robot health state under varying working conditions.
2025
- Adaptive LCI Data Completion: Integrating Neural Processes and Active Learning for Enhanced Life Cycle Assessment
NPs with active learning complete missing life-cycle-inventory data for environmental assessment.
- Attentive neural processes based on reliable inferences for industrial equipment anomaly detection
Reliable-inference ANP detects anomalies in industrial equipment signals.
- Meta-model Neural Process for Probabilistic Power Flow under Varying N-1 System Topologies
Topology-adaptive NP solves probabilistic power flow across N-1 contingencies without retraining.
- Physics-informed multi-source data fusion for inferencing residual stress field of rotary parts
Treats residual stress fields as an NP fusing deformation-force and local stress measurements.
- Real-time adaptation for time-series signal prediction using label-aware neural processes
Label-aware NP rapidly adapts condition-monitoring signal predictions online for engineering units.
- Scalable and reliable deep transfer learning for intelligent fault detection via multi-scale neural processes embedded with prior knowledge
Knowledge-embedded multi-scale NPs for cross-domain industrial fault detection with uncertainty.
- Short-Term Load Forecasting with Attentive Neural Processes: Adaptivity and Uncertainty Estimation
ANP gives adaptive, uncertainty-aware short-term electricity load forecasts.
- The Research of Industrial Robot Anomaly Detection Based on Kinematic Model-Guided IMU Attitude Error Calibration
ANP fits normal IMU acceleration data; reconstruction error flags industrial robot anomalies.
- Weighted sequence neural processes based uncertainty-aware machinery failure prognostic for mineral manufacturing equipment
Weighted sequence NP gives uncertainty-aware failure prognostics for mineral-processing machinery.
2024
- An improved multi-task approach for SHM missing data reconstruction using attentive neural process and meta-learning
Multi-task ANP with meta-learning reconstructs missing structural health monitoring data.
- ANP-Net: attention neural processes network for semi-supervised pavement defect semantic segmentation
ANP-based semi-supervised network segments pavement defects for road inspection.
- Deep Wavelet Neural Process: Modeling Stochastic Variation of Non-Euclidean Functional Data for Manufacturing Quality Inference
Wavelet NP models stochastic surface variation for manufacturing quality inference.
- Multidomain neural process model based on source attention for industrial robot anomaly detection
Source-attention multi-domain NP detects anomalies in industrial robots across working conditions.
2023
- A Deep Generative Active Learning-based Scheme for the Efficient Development of Transient Stability Predictor
NP predicts power-system transient stability within a generative active-learning data scheme.
- Neural Process for Health Prognostics With Uncertainty Estimations
NP-based health prognostics of degrading machinery with uncertainty estimates.
- Towards a population-informed approach to the definition of data-driven models for structural dynamics
CNP and MAML learn structural-dynamics models from populations of similar structures.
- Uncertainty Quantification Based Health Diagnosis for Lithium-Ion Batteries Under Different Operating Conditions
NP combined with LSTM models battery degradation paths with uncertainty across operating conditions.
2022
- Calibrating building simulation models using multi-source datasets and meta-learned Bayesian optimization
ANP meta-learned surrogate speeds Bayesian-optimisation calibration of building energy simulators.
- High-Speed Adder Design Space Exploration via Graph Neural Processes
Graph NP surrogate guides Bayesian-optimisation exploration of high-speed adder circuit designs.
- Neural Process Enhanced Machining Error Evaluation for Coordinate Measuring Machines
NP improves machining-error evaluation from sparse coordinate-measuring-machine points.
- Relation-Aware Attentive Neural Processes Model for Remaining Useful Life Prediction
Relation-aware ANP models sensor relations for probabilistic RUL prognostics.
2021
- Anomalous Sound Detection Using Attentive Neural Processes
ANP reconstructs masked spectrogram regions to detect anomalous machine sounds for condition monitoring.
- Attentive Neural Processes and Batch Bayesian Optimization for Scalable Calibration of Physics-Informed Digital Twins
ANP surrogate with batch Bayesian optimisation calibrates building-energy digital twins.
- Scenario Uncertainty Modeling for Predictive Maintenance with Recurrent Neural Adaptive Processes (RNAPs)
Recurrent NP-based meta-learner for scenario-adaptive, uncertainty-aware vehicle predictive maintenance.
2020
- Predicting Remaining Useful Life with Uncertainty Using Recurrent Neural Process
Recurrent NP predicts equipment remaining useful life with uncertainty.
Robotics38
2026
- Exploring Temporal Representation in Neural Processes for Multimodal Action Prediction
Studies temporal representations in CNPs for multimodal action prediction.
- Neural Process-Based Reactive Controller for Autonomous Racing
Attentive and physics-informed NP reactive controller for autonomous racing.
- POMDP-based Object Search with Growing State Space and Hybrid Action Domain
POMDP object search using an NP network to filter primitive actions.
- Safe human–robot interaction via Attentive Neural Movement Primitives and control barrier functions
Attentive neural movement primitives combined with control barrier functions for safe HRI.
- State estimation using physics informed attentive neural processes for vehicle tracking
Physics-informed attentive NPs for vehicle state estimation and tracking.
- Task Parameter Extrapolation via Learning Inverse Tasks From Forward Demonstrations
Joint CNP/DMBN representation of forward and inverse tasks for extrapolation.
- The Impact of Trajectory Segmentation on Learning Performance in the C-CNMP Architecture
Studies trajectory segmentation effects on coupled CNMP learning.
- Trajectory Learning with Graph Representations for Social Robot Navigation
Graph-representation extension of CNMP for social robot navigation.
- Uncertainty-Quantified Pseudo-GNSS via GANP for Robust INS/GNSS Navigation of UAVs During GNSS Outages
GRU-attention neural process generates pseudo-GNSS measurements with covariance to bridge UAV GNSS outages.
2025
- Artificial Pain Representation with Tactile and Vision Blending
Adapts CNMP-derived Deep Modality Blending Networks to predict touch from vision for pain anticipation.
- Learning Attentive Neural Processes for Planning with Pushing Actions
ANP infers latent physical properties for planning pushing actions.
- MetaVLA: Unified Meta Co-training For Efficient Embodied Adaption
ANP-derived meta co-training for efficient vision-language-action model adaptation.
- Mobil Robotlarda Sosyal Navigasyon Öğrenme / Learning Social Navigation in Mobile Robots
Graph attention for spatial and CNPs for temporal structure of demonstrated social navigation.
- Real-Time Performance Analysis of Multi-Fidelity Residual Physics-Informed Neural Process-Based State Estimation for Robotic Systems
Multi-fidelity residual physics-informed NP for real-time robot state estimation.
- Uncertainty-aware Accurate Elevation Modeling for Off-road Navigation via Neural Processes
NP-based terrain elevation modeling with uncertainty for off-road navigation.
2024
- Conditional Neural Expert Processes for Learning Movement Primitives From Demonstration
Mixture-of-experts CNP for multimodal movement primitives from demonstration.
- Correspondence Learning Between Morphologically Different Robots via Task Demonstrations
Blends latents of coupled CNMPs to learn correspondences across robot morphologies.
- Coupled Conditional Neural Movement Primitives
Coupled CNMPs that link multiple movement primitives via shared latents.
- Cross-Embodied Affordance Transfer through Learning Affordance Equivalences
CNMP-backbone shared affordance space for cross-embodiment affordance transfer.
- Learning a Terrain- and Robot-Aware Dynamics Model for Autonomous Mobile Robot Navigation
NP-based terrain- and robot-aware dynamics model for mobile robot navigation.
- Learning Early Social Maneuvers for Enhanced Social Navigation
CNP-based LfD for social navigation using pedestrian path predictions.
- Multi-step planning with learned effects of partial action executions
CNP-based affordance model predicting effects of partial actions for multi-step planning.
- Semi-Supervised Neural Processes for Articulated Object Interactions
Semi-supervised NP reward model for articulated object interactions.
2023
- Bimanual Rope Manipulation Skill Synthesis through Context Dependent Correction Policy Learning from Human Demonstration
CNMP-learned correction policies for bimanual rope manipulation.
- Conditional Neural Processes for Self-Supervised Goal Discovery in Action Imitation
CNPs for self-supervised discovery of action goals in imitation.
- Context-Conditional Navigation with a Learning-Based Terrain-and Robot-Aware Dynamics Model
NP-based context-conditional terrain-and robot-aware dynamics model for navigation.
- Deep Probabilistic Movement Primitives with a Bayesian Aggregator
Replaces CNMP mean aggregation with Bayesian context aggregation for conditioning and blending.
- Image-based Outdoor Navigation in Static Environments via Conditional Neural Movement Primitive
Image-conditioned CNMP for outdoor mobile robot navigation.
2022
- Imitation and mirror systems in robots through Deep Modality Blending Networks
Deep modality blending networks extend CNPs to multimodal action understanding and imitation.
- Learning social navigation from demonstrations with conditional neural processes
CNP-based global and local controllers for social navigation from demonstrations.
- Meta-Learning Regrasping Strategies for Physical-Agnostic Objects
ConDex: CNP combined with DexNet to infer physical properties for regrasping.
2021
- Generative Adversarial Networks with Conditional Neural Movement Primitives for An Interactive Generative Drawing Tool
Adds adversarial loss to CNMP for smooth, consistent interactive sketch generation.
- Learning Social Navigation from Demonstrations with Deep Neural Networks
CNP models for global and local social navigation planning learned from demonstrations.
- Learning System Dynamics via Deep Recurrent and Conditional Neural Systems
Compares LSTM and CNMP-based conditional models for learning system dynamics from time series.
2020
- ACNMP: Skill Transfer and Task Extrapolation through Learning from Demonstration and Reinforcement Learning via Representation Sharing
Adaptive CNMP: shares CNP latent between supervised demos and RL for skill extrapolation.
- Predicting Whole Body Motion Trajectories using Conditional Neural Movement Primitives
Extends CNMPs to generate whole-body human motion conditioned on desired body configurations.
- Towards a Mirror Neuron System via Dual Channel Conditional Neural Movement Primitives
Two CNMPs (image and joint channels) sharing a latent space for mirror-neuron-like transfer.
2019
- Conditional Neural Movement Primitives
CNMP: CNP-based movement primitives conditioned on arbitrary via-points and sensory inputs.
Other ML28
2026
- Hamiltonian monte carlo based neural process for few-shot knowledge graph completion
Hamiltonian Monte Carlo NP for few-shot knowledge graph completion.
- PRIM: Meta-Learned Bayesian Root Cause Analysis
MACE-TNP-based amortized Bayesian root cause analysis.
- Source Localization in Continuous-Time Propagation via Spectral ODE Modeling
Graph-VAE neural process encodes latent propagation patterns conditioning a spectral neural ODE.
- Sum-Rate Optimization for Multi-User Fluid Antenna MISO Systems via ConvCNP-Assisted D3QN Port Selection
ConvCNP infers unobserved fluid-antenna port CSI from pilots, guiding D3QN port selection.
- Unit-level aggregation breaks coverage in causal foundation models
NP heads on causal foundation models to fix CATE coverage.
2025
- Combat Misinformation: Dynamic User Credibility Prediction via State-Aware Neural Processes
State-aware NPs for dynamic user credibility prediction against misinformation.
- Enhancing Real Estate Valuation through Deep Modeling of Spatiotemporal Dependencies and Feature Interactions
TabularCNP conditions property value predictions on nearby recent transactions via a CNP.
- Graph Stochastic Neural Process for Inductive Few-shot Knowledge Graph Completion
Graph stochastic NP for inductive few-shot KG completion.
- Hybrid State Estimation of Uncertain Nonlinear Dynamics Using Neural Processes
Physics-informed attentive NP for hybrid state estimation of nonlinear dynamics.
- Machine learning approach to synthetic data generation: Uncertainty generative model with neural attention
Combines attentive NPs with Heston stochastic volatility SDEs to generate synthetic data under scarcity.
- Meta Learner-Based Transfer Learning: Bridging Simulation and Actual Router Metrics
NP meta-learner plus PLS bridges simulated and real router metrics for packet multiplexing.
- MockiFi: CSI Imitation using Context-Aware Conditional Neural Process for Zero-shot Learning
Context-aware CNP imitating Wi-Fi CSI for zero-shot learning.
- Neural Processes-Based Node Modeling to Extrapolate Router Metrics
NP-based node modeling to extrapolate router metrics.
- Robust Simulation-Based Inference under Missing Data via Neural Processes
NP-based imputation jointly trained with neural posterior estimation for SBI under missing data.
- Spreader Behavior Forecasting: Intent-aware Neural Processes for Intervening Misinformation
Intent-aware NPs forecasting misinformation spreader behavior.
- User-Side Retraining-Free Learning for High-Precision 5G Positioning
Neural-process regressor learns NLOS ranging-bias distributions directly from received 5G signals.
2024
- NAEP: Neighborhood Multihead Attention with Evidential Conditional Neural Processes for Few-Shot Knowledge Graph Completion
Evidential CNPs with neighborhood attention for few-shot KG completion.
- Structure-Aware Prototypical Neural Process for Few-Shot Graph Classification
Structure-aware prototypical NP for few-shot graph classification.
- Trend Encoder with Attentive Neural Process: Node Performance Extrapolation for Non-Time-Series Datasets
Trend encoder with ANP to extrapolate network node performance.
2023
- Community Search: A Meta-Learning Approach
Conditional graph NP for meta-learned community search.
- Multiple Extended Target Tracking Using PHD Filter and Convolutional Conditional Neural Process
PHD filter with ConvCNP for multiple extended target tracking.
- Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion
Normalizing-flow NP for few-shot knowledge graph completion.
- Towards Few-shot Inductive Link Prediction on Knowledge Graphs: A Relational Anonymous Walk-guided Neural Process Approach
Relational anonymous-walk-guided NP for few-shot inductive KG link prediction.
- VNP: A Weak-Supervised and Retraining-Free Learning Approach for Online Positioning
Variational neural processes infer NLOS ranging bias without precise labels or retraining.
2022
- Online Learning Based NLOS Ranging Error Mitigation in 5G Positioning
NP regressor for NLOS ranging-error mitigation in 5G positioning.
2020
- Feature embedding and conditional neural processes for data imputation
Feature embedding with CNPs for missing-data imputation.
- Improving Query Efficiency of Black-box Adversarial Attack
NP-Attack: NP-modeled adversarial distribution for query-efficient black-box attacks.
2019
- An Uncertainty-Incorporated Approach to Predict the Winner in StarCraft II Using Neural Processes
NPs for uncertainty-aware StarCraft II winner prediction.
Climate, weather & environment24
2026
- A deep learning framework for gridding daily climate variables from a sparse station network
Localized spatial multi-attention CNP grids Romanian daily temperature/precipitation, beating regression kriging; compares ConvCNP, GriddedTNP.
- Data-driven Optimal Sensor Placement for Aerosol Monitoring in the UK
Convolutional Gaussian NP inside DeepSensor with genetic optimisation selects UK aerosol monitoring stations.
- Earth observation embeddings are effective sub-grid descriptors for probabilistic weather downscaling
Augments ConvCNP downscaler with Earth-observation foundation-model embeddings as sub-grid surface descriptors.
- Exploring Convolutional Neural Processes for Weather Downscaling
Adapts Vaughan-style ConvCNP to downscale ERA5-Land maximum temperature to 1 km over complex Swiss terrain.
- From Drops to Grid: Noise-Aware Spatio-Temporal Neural Process for Rainfall Estimation
Noise-aware spatio-temporal NP fuses private weather stations and radar into dense rainfall maps.
- Learning Spatiotemporal Precipitation Fields with Probabilistic Neural Processes
Frames gauge-based precipitation field reconstruction as probabilistic NP context-to-target prediction.
- Neural Stochastic Processes for Satellite Precipitation Refinement
NP encoder over gauge sets plus latent neural SDE corrects biased satellite precipitation through time.
- Observation Assimilation Transformer: Probabilistic Weather Analysis from Sparse Station Observations
Geometry-aware transformer neural process corrects NWP priors by assimilating thousands of sparse station observations.
- OmniPMNet: Bridging discrete and gridded PM10 forecasts via omni-query neural processes
ConvCNP-based fusion of station GNN forecasts and chemical-transport grids for PM10 dust-storm forecasting.
- Sensor Placement with Neural Processes by Mixture Component Disagreement
Sensor placement acquisition from disagreement between NP mixture components as an epistemic-uncertainty proxy.
2025
- Development of Gridded Climate Data for CONUS using Neural Processes
Builds a 5 km daily temperature/precipitation dataset for CONUS with NP predictions and uncertainty.
- End-to-end data-driven weather prediction
Neural-process weather model with SetConv encoders ingesting raw observations, replacing the full NWP pipeline end to end.
- Fast Risk Awareness of Wildfires with Partially Observable Dataset
Selective CNPs complete global wildfire-risk fields from a few partial observations.
- Optimal Sensor Placement for Aerosol Absorption Optical Depth with Convolutional Neural Processes
Uses ConvNPs (DeepSensor) to propose new aerosol absorption optical depth monitoring sites.
- Where to Measure: Epistemic Uncertainty-Based Sensor Placement with ConvCNPs
Mixture-density ConvCNP separates epistemic uncertainty for better environmental sensor placement acquisition.
2024
- Neural Processes for Short-Term Forecasting of Weather Attributes
Compares multi-task and single-task NPs against GP ensembles for short-horizon coastal weather forecasting.
- Using Convolutional Neural Processes to Produce High-Resolution Weather Datasets Over New Zealand
ConvNPs fuse stations and coarse data into 1 km hourly temperature/precipitation datasets with uncertainty.
2023
- A two-stage downscaling hydrological modeling approach via convolutional conditional neural process and geostatistical bias correction
ConvCNP downscales hydrological variables, followed by geostatistical bias correction.
- Environmental sensor placement with convolutional Gaussian neural processes
ConvGNP models Antarctic temperature and drives active-learning sensor placement via predictive uncertainty.
- Sim2Real for Environmental Neural Processes
Pre-train ConvCNP on reanalysis, fine-tune on sparse station data; improves German temperature interpolation.
2022
- Active Learning with Convolutional Gaussian Neural Processes for Environmental Sensor Placement
Workshop precursor using ConvGNPs for active sensor placement.
- Characterization of Subsurface Hydrogeological Structures With Convolutional Conditional Neural Processes on Limited Training Data
ConvCNP infers subsurface hydrogeological structure from sparse measurements with little training data.
- Convolutional conditional neural processes for local climate downscaling
ConvCNP downscales reanalysis to arbitrary station locations for temperature and precipitation, outperforming standard statistical downscaling.
2021
- Multivariate climate downscaling with latent neural processes
Convolutional latent NP jointly downscales maximum temperature and precipitation with spatially coherent samples at unseen locations.
Computer vision & INRs16
2026
- Few-Shot Personalized Age Estimation
Conditional attentive NP baseline for few-shot personalized age estimation.
- NeuralVisionNet: a probabilistic neural process model for continuous visual anticipation
Video Swin features plus attentive NPs for continuous-time video anticipation.
2025
- A memory-based conditional neural process for video instance segmentation
Memory-augmented CNP for video instance segmentation.
- Continuous conditional video synthesis by neural processes
NP-based continuous conditional video synthesis.
- Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes
Hierarchical NPs for probabilistic interactive 3D segmentation.
2024
- Beyond Kalman filters: deep learning-based filters for improved object tracking
Learned motion models for multi-object tracking, including CNP-based filters.
- Meta-Learning Empowered Meta-Face: Personalized Speaking Style Adaptation for Audio-Driven 3D Talking Face Animation
Dynamic relation mining NP for personalized audio-driven 3D talking faces.
2023
- A unified model for continuous conditional video prediction
Formulates continuous conditional video prediction as an NP over spatio-temporal coordinates.
2022
- Category-Agnostic 6D Pose Estimation with Conditional Neural Processes
CNP meta-learning for category-agnostic 6D pose estimation.
- ExReg: Wide-range Photo Exposure Correction via a Multi-dimensional Regressor with Attention
Encoder-decoder ANP regressor for wide-range photo exposure correction.
- Fast Point Clouds Upsampling with Uncertainty Quantification for Autonomous Vehicles
CNP-based real-time LiDAR upsampling that drops high-uncertainty generated points.
- Super-Pixel Guided Low-Light Images Enhancement with Features Restoration
ANPs learn a local enhancement function per super-pixel for low-light image restoration.
2021
- A Compact Representation of Measured BRDFs Using Neural Processes
NP-based compact representation of measured BRDFs.
- Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognition
Affective processes: NP-based temporal context modeling for emotion recognition.
- Uncertainty-Aware Fast Curb Detection Using Convolutional Networks in Point Clouds
Autoencoder curb proposals are rectified by a CNP that also outputs uncertainty.
2020
- Neural Physicist: Learning Physical Dynamics from Image Sequences
VAE plus NP inferring global physical parameters to learn dynamics from image sequences.
Transportation16
2026
- Metropolis-Scale Resilient and Trustworthy Traffic Flow Inference Using Multi-Source Data
Task-aware ANP fuses floating-car and sensor data for city-scale traffic state inference.
- Passenger Flow Estimation for Urban Rail: Meta-Learning Approach with Mobile Network Data
Attentive NP refines and imputes origin-destination rail flows from mobile-network context edges.
2025
- Enhancing Hybrid Bike-Sharing Systems Through Long-Term Inventory Management: A Generative-Model-Informed Reinforcement Learning Approach
Recurrent-attentive NP forecasts hourly bike demand that informs an RL inventory optimiser.
- STAC-Net: A hierarchical framework for modeling and predicting urban traffic flow with uncertainty quantification
Hierarchical attention traffic-flow forecaster with a neural process module generating samples for uncertainty quantification.
2024
- A Memory-augmented Conditional Neural Process model for traffic prediction
Memory-augmented CNP for probabilistic road traffic prediction.
- Accurate and Interpretable Driving Style Recognition with Unbalanced Data: A Diffusion Ft Transformer with Attentive Neural Process
ANP combined with diffusion FT-transformer recognises driving styles from imbalanced data.
- An Offline Meta Black-box Optimization Framework for Adaptive Design of Urban Traffic Light Management Systems
ANP surrogate predicts congestion across traffic patterns for offline traffic-light design optimisation.
- Demand forecasting and predictability identification of ride-sourcing via bidirectional spatial-temporal transformer neural processes
Bidirectional spatio-temporal TNP forecasts ride-sourcing demand and quantifies predictability.
- GRANP: A Graph Recurrent Attentive Neural Process Model for Vehicle Trajectory Prediction
Graph recurrent ANP gives fast probabilistic vehicle trajectory prediction.
2023
- AGNP: Network-wide short-term probabilistic traffic speed prediction and imputation
Attentive graph NP predicts and imputes network-wide traffic speeds with reliability estimates.
- Multi-task supply-demand prediction and reliability analysis for docked bike-sharing systems via transformer-encoder-based neural processes
Transformer-encoder NP jointly forecasts bike-sharing supply and demand with reliability analysis.
- Robust Meta-Learning of Vehicle Yaw Rate Dynamics via Conditional Neural Processes
CNP meta-learns vehicle yaw-rate dynamics for trajectory planning.
2022
- A Generative Car-following Model Conditioned On Driving Styles
NP-based generative car-following model infers time-varying driver styles.
2021
- Real-Time Fine-Grained Freeway Traffic State Estimation Under Sparse Observation
Residual attention CNP (RA-CNP) estimates fine-grained freeway traffic states from sparse sensors.
2019
- Interactive Trajectory Prediction for Autonomous Driving via Recurrent Meta Induction Neural Network
Replaces CNP's permutation-invariant encoder with a recurrent cell to predict interacting drivers.
- Probabilistic Trajectory Prediction for Autonomous Vehicles with Attentive Recurrent Neural Process
Attentive recurrent NP predicts multi-vehicle interaction trajectories with uncertainty.
Healthcare & medicine14
2026
- Diffusion modelling of polarimetric cervical tissue properties
Extends neural diffusion processes to infill and flag anomalous regions in polarimetric cervical tissue maps.
- Normalizing flow based neural processes for Alzheimer's disease progression prediction
Normalizing-flow NP models Alzheimer's progression trajectories with richer predictive distributions.
- Optimising antibiotic switching via forecasting of patient physiology
NPs forecast vital-sign trajectories to judge readiness to switch from IV to oral antibiotics.
- Picking the Right Specialist: Attentive Neural Process-based Selection of Task-Specialized Models as Tools for Agentic Healthcare Systems
ANP-based ToolSelect picks the best specialist clinical model per query for healthcare agents.
2025
- A Novel Approach to the Prediction of Alzheimer's Disease Progression by Leveraging Neural Processes and a Transformer Encoder Model
NP with transformer encoder predicts Alzheimer's disease progression from longitudinal data.
- A Switched Neural Process for Long-Term Postprandial Glucose Trajectory Prediction Based on Insulin Sensitivity Estimation
Switched NP predicts long-term postprandial glucose trajectories using insulin-sensitivity estimates.
- Conditional Neural Processes for Generalizable TOF-PET Timing Enhancement
CNP improves time-of-flight PET detector timing resolution, generalising across detector configurations.
- Semi-supervised segmentation on medical images with pseudo label calibration and neural process
NP-calibrated pseudo-labels for semi-supervised 3D medical image segmentation.
- Spatiotemporal graph neural process for reconstruction, extrapolation, and classification of cardiac trajectories
Graph neural ODE process reconstructs and extrapolates cardiac motion and classifies disease.
2024
- Data-Driven Simulator for Mechanical Circulatory Support with Domain Adversarial Neural Process
Domain-adversarial NP simulates aortic pressure response to mechanical circulatory support pump levels.
- Predicting interstitial lung disease progression in patients with systemic sclerosis using attentive neural processes - a EUSTAR study
ANP forecasts interstitial lung disease progression in systemic sclerosis registry patients.
2022
- Data Pre-Processing Using Neural Processes for Modeling Personalized Vital-Sign Time-Series Data
NPs impute and smooth personalized patient vital-sign time series.
2021
- Continuous-Time Deep Glioma Growth Models
Hierarchical multi-scale NP models continuous-time glioma growth from irregular MRI sequences.
2020
- Personalized acute stress classification from physiological signals with neural processes
NPs contextualized on a person's wearable data personalize acute stress classification.
Recommender systems14
2026
- NP-MiSR: Neural Process-based Multi-Interest Learning for Session-Based Recommendation
NP-based multi-interest learning for session-based recommendation.
- Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start Users
Normalizing-flow-enhanced NP for multi-interest cross-domain cold-start recommendation.
- RIDRec: Retrieval-Enhanced Intent Diffusion for Anonymous Short-Session Recommendation
Models session intent as an NP latent distribution, combined with retrieval-conditioned diffusion.
2025
- Auto Encoding Neural Process for Multi-interest Recommendation
Auto-encoding NP for multi-interest recommendation.
- CDSRNP: Cross-Domain Sequential Recommendation via Neural Process
NP for cross-domain sequential recommendation.
2024
- CDRNP: Cross-Domain Recommendation to Cold-Start Users via Neural Process
NP for cross-domain recommendation to cold-start users.
- Learning Hierarchical Preferences for Recommendation With Mixture Intention Neural Stochastic Processes
Mixture-of-intentions neural stochastic process (MINSP) captures hierarchical user preferences.
- Towards Flexible and Adaptive Neural Process for Cold-Start Recommendation
Flow-based adaptive NP with hypernetwork decoder for cold-start recommendation.
2023
- Doubly Intention Learning for Cold-start Recommendation with Uncertainty-aware Stochastic Meta Process
Stochastic meta process with doubly-distinguished intention latents for uncertainty-aware cold-start recommendation.
- IDNP: Interest Dynamics Modeling Using Generative Neural Processes for Sequential Recommendation
Generative NP modeling interest dynamics for sequential recommendation.
- Modeling Preference as Weighted Distribution over Functions for User Cold-start Recommendation
NP with multinomial likelihood and curriculum weighting models per-user preference functions for cold start.
2022
- Conditional Collaborative Filtering Process for Top-K Recommender System (Student Abstract)
Conditional collaborative filtering process for top-K recommendation.
- Learning Intrinsic and Extrinsic Intentions for Cold-start Recommendation with Neural Stochastic Processes
Intention neural process (INP) extends NP family with intrinsic/extrinsic intention latents for cold start.
2021
- Task-adaptive Neural Process for User Cold-Start Recommendation
TaNP: task-adaptive NP for user cold-start recommendation.
Bayesian optimization & HPO11
2026
- AdaNP-BO: Adaptive Neural Process Bayesian Optimization with Learnable Stochastic Activations
Neural-process Bayesian optimization with learnable stochastic activations.
- From Regression to Inference: Meta-Learning Predictors for Neural Architecture Search
ConvNP meta-learned predictor for architecture performance in neural architecture search.
- Meta-Learning-Based Surrogate Models for Efficient Hyperparameter Optimization
ConvCNP-inspired meta-learned surrogate transfers hyperparameter response surfaces across historical tasks.
2025
- AQETuner: Reliable Query-level Configuration Tuning for Analytical Query Engines
Dual-task NP predicts query performance and failures to guide database configuration tuning.
- PABBO: Preferential Amortized Black-Box Optimization
Transformer NP surrogate+acquisition trained with RL for amortized preferential BO.
2024
- RLBOF: Reinforcement Learning from Bayesian Optimization Feedback
Pre-trains an NP surrogate, then fine-tunes it with RL from real Bayesian-optimisation feedback.
2021
- Meta-learning Hyperparameter Performance Prediction with Neural Processes
NP-based meta surrogate with dataset-aware representations for hyperparameter performance prediction.
- Neural Process for Black-Box Model Optimization Under Bayesian Framework
Replaces GP surrogate with an NP for scalable black-box Bayesian optimization (NPBO).
2020
- Novel Multitask Conditional Neural-Network Surrogate Models for Expensive Optimization
Multi-task CNP surrogates for expensive optimisation problems.
2019
- Meta-Learning surrogate models for sequential decision making
Uses NPs as meta-learned probabilistic surrogates for Bayesian optimisation, bandits and model-based RL.
- Transferable Neural Processes for Hyperparameter Optimization
NP surrogate transferring HPO trial history across datasets to warm-start sequential model-based optimisation.
Biology & chemistry11
2026
- A Multi-Scale Graph Neural Process with Cross-Drug Co-Attention for Drug-Drug Interactions Prediction
Multi-scale graph NP with cross-drug co-attention predicts drug-drug interactions with confidence.
- Integrating Transformer Neural Processes and Deep Kernel Learning for High-Throughput Screening and Uncertainty Quantification for Water-Splitting Electrocatalysts Across Perovskites and Metal Alloys
TNPs with deep kernel learning screen perovskite and alloy electrocatalysts with uncertainty.
- Neural Processes with Normalizing Flows for Wheat Height Estimation
Flow-augmented NPs model irregularly sampled wheat height growth trajectories across genotypes.
- SpatialNP: Gridded Transformer Neural Processes for Probabilistic Spatial Proteomics in Multiplexed Tissue Imaging
Gridded transformer NP maps irregular single-cell protein-marker observations to continuous probabilistic spatial expression fields.
2024
- Calibrated prediction of scarce adverse drug reaction labels with conditional neural processes
CNPs give calibrated predictions of sparsely labelled adverse drug reactions.
- Graph neural processes for molecules: an evaluation on docking scores and strategies to improve generalization
Graph NPs for few-shot molecular property (docking score) prediction and generalisation strategies.
- Predicting time-varying flux and balance in metabolic systems using structured neural-ODE processes
Structured neural ODE process with non-Gaussian latents predicts metabolic flux from gene expression.
2023
- Embracing assay heterogeneity with neural processes for markedly improved bioactivity predictions
Hierarchical NP meta-learning across heterogeneous assays improves ligand bioactivity prediction.
- Inferring direction of associations between histone modifications using a neural processes-based framework
NPs impute single-cell histone modification abundances and infer directional associations.
2022
- Conditional Neural Processes for Molecules
Benchmarks CNPs for few-shot transfer learning on molecular docking-score prediction.
- MetaDTA: Meta-learning-based drug-target binding affinity prediction
Attentive NP treats each target's binding affinities as a function of compounds for few-shot drug-target affinity prediction.
Earth observation & geospatial11
2026
- A neural-process framework for stochastic simulation of spatially dependent geoscientific fields
NP replaces variogram-based sequential Gaussian simulation for stochastic geoscientific field realizations.
- Comparing Gaussian Processes, Neural Processes and Neural Networks for Interpolation of Ionospheric ROTI
Benchmarks NPs against GPs and NNs for interpolating sparse GNSS ionospheric irregularity indices.
- Interpolation of GEDI Biomass Estimates with Calibrated Uncertainty Quantification
ANPs with geospatial embeddings interpolate sparse GEDI lidar biomass with calibrated uncertainty across biomes.
- Neural Processes Maintain Calibrated Biomass Estimates Across Spatiotemporal Gaps and Disturbance
Extends ANP biomass interpolation to joint space-time gaps, including GEDI hibernation and deforestation events.
2025
- Coupled geological modeling using multi-source data: A K-dimensional tree-graph convolutional neural process approach
KD-tree graph-convolutional NP fuses multi-source data for coupled 3D geological modelling.
- Reservoir parameter prediction based on spatial attentive neural processes
Geostatistics-inspired dual-attention NP maps seismic attributes to reservoir parameters from sparse well logs.
2024
- A two-stage spatial prediction modeling approach based on graph neural networks and neural processes
Combines GNN trend modelling with NP residual modelling for spatial prediction with uncertainty.
- GACNPs: Fine-Grained Drought Monitoring Using Remote Sensing Data Based on Conditional Neural Processes
CNP variant produces fine-grained drought monitoring maps from remote-sensing inputs.
- Neural process for uncertainty-aware geospatial modeling
Applies NPs to geospatial regression to provide uncertainty-aware spatial predictions.
2022
- Convolutional Neural Processes for Inpainting Satellite Images: Application to Water Body Segmentation
ConvCNP inpaints cloud-occluded satellite imagery to improve downstream water-body segmentation.
2021
- A neural process approach for probabilistic reconstruction of no-data gaps in lunar digital elevation maps
ANP probabilistically fills voids in lunar NAC digital elevation maps with uncertainty.
Reinforcement learning11
2026
- Neural process model predictive control
Combines neural-process models with model predictive control (details from title/metadata only).
2025
- Model-Based Offline Reinforcement Learning for AUV Path-Following Under Unknown Ocean Currents with Limited Data
Improved CNP dynamics/kinematics models enable offline model-based RL for AUV path following.
2024
- Development of an AI framework using neural process continuous reinforcement learning to optimize highly volatile financial portfolios
Neural-process continuous RL framework for volatile portfolio optimization.
- Unsupervised Meta-Testing With Conditional Neural Processes for Hybrid Meta-Reinforcement Learning
Hybrid meta-RL using CNPs for unsupervised meta-testing task inference.
2023
- Conditional neural processes for model-based reinforcement learning with stability guarantees
CNP dynamics models for model-based RL with stability guarantees.
- Meta-World Conditional Neural Processes
CNP world-model generator for sample-efficient meta-RL via hallucinated environments.
2022
- A Meta Reinforcement Learning Approach for Predictive Autoscaling in the Cloud
Model-based meta-RL with embedded NP for predictive cloud autoscaling.
- Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search
Extends NP-style latent task identification with graph-structured surrogates for model-based meta-RL.
2021
- Context-Aware Safe Reinforcement Learning for Non-Stationary Environments
ANP disturbance-dynamics model enables fast posterior adaptation for safe RL under non-stationarity.
- Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Models
NP-style context-conditional dynamics models with information-optimal exploration.
- Reward Conditioned Neural Movement Primitives for Population-Based Variational Policy Optimization
NP-based reward-conditioned movement primitives for population-based policy optimization.
Astronomy9
2026
- A Meta-Learning Framework for Multitask Reverberation Mapping in Active Galactic Nuclei
Attentive latent NPs perform photometric AGN reverberation mapping at LSST scale.
- Modeling Multi-band Active Galactic Nuclei Lightcurves Using an Self-supervised Attentive Neural Process Network
Self-supervised ANP jointly reconstructs six-band quasar light curves and infers AGN physical parameters.
- NAPTIME: A Neural-process Framework for Rubin Alert Classification
NP framework classifies sparse multiband Rubin alerts, e.g. tidal disruption events.
- Probabilistic Data-Driven Modelling of Astrophysical Transients: The Neural Process Family for Ultrafast and Class-Agnostic Light Curve Reconstruction with NightLANP
Meta-learned ANPs reconstruct sparse multiband Rubin transient light curves, beating GP baselines.
2024
- Modeling quasar variability through self-organizing map-based neural process
SOM clustering before CNP modelling improves quasar light-curve fits.
2023
- Deep learning of quasar lightcurves in the LSST era
Upgraded CNP pipeline models large samples of quasar light curves for LSST.
- Harnessing Deep Learning for Quasar Light Curve Modeling with QNPy
Presents QNPy, a Python package for CNP-based quasar light curve modelling.
2021
- Conditional Neural Process for nonparametric modeling of active galactic nuclei light curves
CNP models and interpolates AGN optical light curves from ASAS-SN data.
- Inferring Black Hole Properties from Astronomical Multivariate Time Series with Bayesian Attentive Neural Processes
Bayesian ANP reconstructs multiband AGN light curves and infers black hole mass posteriors.
Physics & simulation9
2026
- Density-Guided Conditional Neural Processes for Detector Efficiency Estimation
Density-guided CNP estimates detector selection efficiency on MAJORANA calibration data.
2025
- Context-aware Learned Mesh-based Simulation via Trajectory-Level Meta-Learning
CNP trajectory-level meta-learning adapts mesh-based simulators to new scenarios from limited data.
- MaNGO - Adaptable Graph Network Simulators via Meta-Learning
CNP-encoded latent with neural operator adapts graph-network physics simulators to new material parameters.
- NP-Optimized Inversion Model for High-Precision Thickness of SiC Epilayers using Infrared Interferometry
Meta-learned NP surrogate with multi-start optimisation inverts IR interference spectra for epilayer thickness.
2024
- An attention-neural-processes approach to reconstructing unsteady water load for seaplanes
ANP reconstructs full unsteady hydrodynamic water-load distributions on seaplane hulls from sparse sensors.
- RESuM: Rare Event Surrogate Model for Physics Detector Design
Pretrained CNP informs multi-fidelity GP surrogate optimising neutrinoless double-beta-decay detector moderators.
- Sound field reconstruction using neural processes with dynamic kernels
NP with learned dynamic kernels reconstructs acoustic sound fields from few microphones.
2023
- Peri-Net-Pro: the neural processes with quantified uncertainty for crack patterns
NPs with peridynamics data predict and classify crack patterns with uncertainty.
2021
- NP-ODE: Neural process aided ordinary differential equations for uncertainty quantification of finite element analysis
NP-aided ODE surrogate emulates finite element simulations with input and output uncertainty.
Few-shot classification8
2025
- Perspectives of Calibrated Adaptation for Few-Shot Cross-Domain Classification
Upgrades CNAPs' conditioning for calibrated cross-domain amortisation on Meta-Dataset.
2022
- Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning
Extends Simple CNAPs to multi-domain, active and continual few-shot learning.
- Canonical Mean Filter for Almost Zero-Shot Multi-Task classification
Canonical mean filter improving CNAPs robustness for near zero-shot multi-task classification.
2021
- Meta-Learning for Few-Shot Plant Disease Detection
LFM-CNAPS adds local feature matching to CNAPs for few-shot plant disease recognition.
2020
- Enhancing Few-Shot Image Classification with Unlabelled Examples
Transductive CNAPS: uses unlabelled queries via soft k-means with the CNAPs adaptation backbone.
2019
- Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes
CNAPs: CNP-inspired adaptation networks producing FiLM parameters for few-shot classification.
- Improved Few-Shot Visual Classification
Simple CNAPS: adds class-covariance Mahalanobis distance classifier to CNAPs for few-shot classification.
- MetaFun: Meta-Learning with Iterative Functional Updates
CNP-style encoder-decoder with infinite-dimensional functional representation refined by learned functional-gradient updates.
NLP, speech & LLMs7
2026
- LLM Flow Processes for Text-Conditioned Regression
Combines LLM process densities with a diffusion NP for calibrated text-conditioned regression.
2024
- Dynamic Speech Emotion Recognition using a Conditional Neural Process
CNP for time-continuous speech emotion recognition.
- Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes
NP-based few-shot steerable reward models and LLM policies.
- LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language
Elicits NP-like numerical predictive distributions from LLMs conditioned on data and text.
2021
- Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation
CNP-based few-shot text classifier representing tasks with base-model gradients.
- Multimodal Emergent Fake News Detection via Meta Neural Process Networks
Meta neural process networks for multimodal emergent fake news detection.
- Stochastic Process Regression for Cross-Cultural Speech Emotion Recognition
Recurrent NP variant infers latent from noisy backbone predictions for emotion label regression.
Semi-supervised & continual learning6
2026
- Semi-supervised time series classification via sequence neural process
Sequence NP for semi-supervised time series classification.
2023
- NP-Match: Towards a New Probabilistic Model for Semi-Supervised Learning
Extended NP-Match with uncertainty-guided skew-geometric JS divergence.
- NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation
NP-SemiSeg: NPs for uncertainty-aware semi-supervised semantic segmentation.
- Semi-Supervised Anomaly Detection Via Neural Process
NP-based semi-supervised anomaly detection.
2022
- NP-Match: When Neural Processes meet Semi-Supervised Learning
Adapts NPs to semi-supervised image classification, using NP uncertainty to select reliable pseudo-labels.
- SNPD: Semi-Supervised Neural Process Dehazing Network with Asymmetry Pseudo Labels
Semi-supervised NP dehazing network with asymmetric pseudo labels.
Other science5
2026
- Attentive Neural Processes for Fast Trajectory Prediction in Underwater Acoustic Networks
ANP predicts node trajectories quickly in underwater acoustic sensor networks.
2025
- Attentive Neural Processes for Few-Shot Learning Anomaly-Based Vessel Localization Using Magnetic Sensor Data
ANP localizes underwater vessels from magnetic anomaly measurements in few-shot settings.
- Meta-Learning Neural Process for Implied Volatility Surfaces with SABR-induced Priors
Attention NP pre-trained on SABR surfaces reconstructs option implied volatility surfaces from sparse quotes.
- Mode-informed complex-valued neural processes for matched field processing
Complex-valued NP with ocean modal depth functions reconstructs acoustic fields for underwater source localization.
2024
- HRTF Interpolation Using a Spherical Neural Process Meta-Learner
Spherical ConvCNP meta-learner corrects individualized head-related transfer function estimates from few measurements.
Active learning & experimental design4
2025
- ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition
Transformer NP-style engine jointly amortizing posterior inference and active data acquisition.
2024
- Amortized Bayesian Experimental Design for Decision-Making
Transformer Neural Decision Process amortizes decision-aware experimental design and prediction.
2023
- ExPT: Synthetic Pretraining for Few-Shot Experimental Design
TNP-style in-context transformer pretrained on synthetic functions generates optimal designs from few labels.
- Learning Objective-Specific Active Learning Strategies with Attentive Neural Processes
Attentive conditional NP learns objective-specific active learning acquisition strategies.
Time series3
2025
- Social Processes: Probabilistic Meta-learning for Adaptive Multiparty Interaction Forecasting
Extends Social Process NPs to adaptive group-level conversation behaviour forecasting.
2023
- Conditional Neural ODE Processes for Individual Disease Progression Forecasting: A Case Study on COVID-19
Conditional neural ODE processes for individual disease progression forecasting.
2021
- Unsupervised clustering of series using dynamic programming and neural processes
NPs within dynamic programming for unsupervised time series clustering.
Neuroscience3
2025
- Decoding Emotions from Missing-Channel EEG Signals via Uncertainty-Aware Modeling with Neural Processes
FC-EEGNP: NP framework for emotion recognition from incomplete EEG channels.
2022
- Increasing the Stability of EEG-based Emotion Recognition with a Variant of Neural Processes
Robust NP variant for stable EEG emotion recognition under data corruption.
2020
- A Robust Approach to Estimating Vigilance from EEG with Neural Processes
NPs estimate vigilance levels from EEG robustly across subjects.
> no papers match. try fewer words.