NLI autonomously discovers a vocabulary of primitive operations and interprets variable-length programs via a neural executor, allowing end-to-end training and gradient-based test-time adaptation that outperforms prior methods on combinatorial generalization tasks.
hub
Neural Processes
22 Pith papers cite this work, alongside 28 external citations. Polarity classification is still indexing.
22
Pith papers citing it
28
external citations · Pith
abstract
A neural network (NN) is a parameterised function that can be tuned via gradient descent to approximate a labelled collection of data with high precision. A Gaussian process (GP), on the other hand, is a probabilistic model that defines a distribution over possible functions, and is updated in light of data via the rules of probabilistic inference. GPs are probabilistic, data-efficient and flexible, however they are also computationally intensive and thus limited in their applicability. We introduce a class of neural latent variable models which we call Neural Processes (NPs), combining the best of both worlds. Like GPs, NPs define distributions over functions, are capable of rapid adaptation to new observations, and can estimate the uncertainty in their predictions. Like NNs, NPs are computationally efficient during training and evaluation but also learn to adapt their priors to data. We demonstrate the performance of NPs on a range of learning tasks, including regression and optimisation, and compare and contrast with related models in the literature.
hub tools
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
Behavioral INR adapts INRs to behavior by mapping states to actions with FiLM-modulated episode latents for self-supervised policy inference in unlabeled data, with new policy OOD definitions.
The paper defines computational identifiability as success of a finite search procedure in finding an empirical estimator for a causal query within error tolerance, conditional on the search assumptions and procedure.
CoMetaPNS combines meta-learned neural surrogates with a continual Bayesian Gaussian Mixture Model to adapt cardiac electrophysiology simulations to new data while avoiding catastrophic forgetting.
APIC applies Neural Processes in a two-branch latent model to amortize Kennedy-O'Hagan-style calibration, separating instance-specific parameters from shared structural discrepancies for fast inference on new realizations.
Set Fourier convolutions plus a Volterra cascade yield scalable, translation-equivariant CNPs that handle irregular inputs with global receptive fields and beat strong baselines.
GPS trains a small model on optimization history to predict prompt difficulty and select intermediate-difficulty diverse batches, yielding better training efficiency, final performance, and test-time allocation than baselines on reasoning benchmarks.
TNP-KR adds a kernel regression transformer block, kernel attention bias, scan attention for translation invariance, and deep kernel attention to achieve lower complexity and state-of-the-art results on meta-regression and related benchmarks.
NEO is a probabilistic neural model that induces compositional programs as a learned Language of Thought from non-textual observations and executes them via a shared transition model to enable explanation-driven generalization.
NF-NPCDR enhances neural processes with normalizing flows to model personalized multi-interest preferences and uses a preference pool plus adaptive decoder to improve cross-domain recommendations for cold-start users.
Neural Operator Processes (NOPs) unify neural-process conditioning with neural-operator decoding for probabilistic full-field prediction from sparse joint input-output observations.
Attentive Neural Processes outperform Gaussian Processes and neural networks on light curve interpolation quality, feature recovery, calibration, and speed for 15 transient classes under realistic Rubin cadences.
DeRegiME uses a sparse variational GP with nonstationary regime-mixing kernel to decompose forecasts into mean, residual regimes, and noise for improved probabilistic forecasting under distribution shift.
STNPs extend TNPs with a spectral aggregator that estimates context spectra, forms spectral mixtures, and injects task-adaptive frequency features to better handle periodicity.
Earth-o1 learns continuous atmospheric dynamics from ungridded observations and matches operational IFS forecast skill in hindcasts.
NSP model fuses satellite and gauge data with neural processes and SDEs, outperforming 13 baselines and JAXA's operational product on a new 43k-sample US benchmark across six metrics.
A meta-learning framework with ALNP, SOM clustering, and mixture density models improves AGN light-curve reconstruction by 60-70% and parameter recovery on simulated and ZTF data.
TA-ANP is a task-aware attentive neural process that performs global traffic state inference by fusing multi-source data, jointly solving three sub-tasks, and providing calibrated uncertainty estimates with resilience to changing sensor configurations.
OptBias meta-learns optimization bias via Gaussian process synthetic tasks to boost surrogate performance for small-data offline black-box optimization across benchmarks.
R-NP model uses DS-HDP-HMM regime detection plus per-regime CNPs to produce regime-weighted price forecasts that rank as the most balanced option under TOPSIS across 2021-2023 when tested in battery arbitrage and grid-service tasks.
A revised DMBN with positional time encoding improves temporal representation and generalization in neural processes for multimodal robotic action prediction.
citing papers explorer
-
Gradient-Based Program Synthesis with Neurally Interpreted Languages
NLI autonomously discovers a vocabulary of primitive operations and interprets variable-length programs via a neural executor, allowing end-to-end training and gradient-based test-time adaptation that outperforms prior methods on combinatorial generalization tasks.
-
Implicit Neural Representations of Individual Behavior
Behavioral INR adapts INRs to behavior by mapping states to actions with FiLM-modulated episode latents for self-supervised policy inference in unlabeled data, with new policy OOD definitions.
-
Computational Identifiability
The paper defines computational identifiability as success of a finite search procedure in finding an empirical estimator for a causal query within error tolerance, conditional on the search assumptions and procedure.
-
CoMetaPNS: Continually Meta-learning Personalized Neural Surrogates for Cardiac Electrophysiology Simulations
CoMetaPNS combines meta-learned neural surrogates with a continual Bayesian Gaussian Mixture Model to adapt cardiac electrophysiology simulations to new data while avoiding catastrophic forgetting.
-
APIC: Amortized Physics-Informed Calibration using Neural Processes
APIC applies Neural Processes in a two-branch latent model to amortize Kennedy-O'Hagan-style calibration, separating instance-specific parameters from shared structural discrepancies for fast inference on new realizations.
-
Revisiting Neural Processes via Fourier Transform and Volterra Series
Set Fourier convolutions plus a Volterra cascade yield scalable, translation-equivariant CNPs that handle irregular inputs with global receptive fields and beat strong baselines.
-
Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
GPS trains a small model on optimization history to predict prompt difficulty and select intermediate-difficulty diverse batches, yielding better training efficiency, final performance, and test-time allocation than baselines on reasoning benchmarks.
-
Transformer Neural Processes - Kernel Regression
TNP-KR adds a kernel regression transformer block, kernel attention bias, scan attention for translation invariance, and deep kernel attention to achieve lower complexity and state-of-the-art results on meta-regression and related benchmarks.
-
Learning to Theorize the World from Observation
NEO is a probabilistic neural model that induces compositional programs as a learned Language of Thought from non-textual observations and executes them via a shared transition model to enable explanation-driven generalization.
-
Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start Users
NF-NPCDR enhances neural processes with normalizing flows to model personalized multi-interest preferences and uses a preference pool plus adaptive decoder to improve cross-domain recommendations for cold-start users.
-
Neural Operator Processes for Probabilistic Operator Learning under Partial Observations
Neural Operator Processes (NOPs) unify neural-process conditioning with neural-operator decoding for probabilistic full-field prediction from sparse joint input-output observations.
-
Probabilistic Data-Driven Modelling of Astrophysical Transients: The Neural Process Family for Ultrafast and Class-Agnostic Light Curve Reconstruction with NightLANP
Attentive Neural Processes outperform Gaussian Processes and neural networks on light curve interpolation quality, feature recovery, calibration, and speed for 15 transient classes under realistic Rubin cadences.
-
DeRegiME: Deep Regime Mixtures for Probabilistic Forecasting under Distribution Shift
DeRegiME uses a sparse variational GP with nonstationary regime-mixing kernel to decompose forecasts into mean, residual regimes, and noise for improved probabilistic forecasting under distribution shift.
-
Spectral Transformer Neural Processes
STNPs extend TNPs with a spectral aggregator that estimates context spectra, forms spectral mixtures, and injects task-adaptive frequency features to better handle periodicity.
-
Earth-o1: A Grid-free Observation-native Atmospheric World Model
Earth-o1 learns continuous atmospheric dynamics from ungridded observations and matches operational IFS forecast skill in hindcasts.
-
Neural Stochastic Processes for Satellite Precipitation Refinement
NSP model fuses satellite and gauge data with neural processes and SDEs, outperforming 13 baselines and JAXA's operational product on a new 43k-sample US benchmark across six metrics.
-
A Meta-Learning Framework for Multitask Reverberation Mapping in Active Galactic Nuclei
A meta-learning framework with ALNP, SOM clustering, and mixture density models improves AGN light-curve reconstruction by 60-70% and parameter recovery on simulated and ZTF data.
-
Metropolis-Scale Resilient and Trustworthy Traffic Flow Inference Using Multi-Source Data
TA-ANP is a task-aware attentive neural process that performs global traffic state inference by fusing multi-source data, jointly solving three sub-tasks, and providing calibrated uncertainty estimates with resilience to changing sensor configurations.
-
Black-Box Optimization From Small Offline Datasets via Meta Learning with Synthetic Tasks
OptBias meta-learns optimization bias via Gaussian process synthetic tasks to boost surrogate performance for small-data offline black-box optimization across benchmarks.
-
Regime-Aware Conditional Neural Processes with Multi-Criteria Decision Support for Operational Electricity Price Forecasting
R-NP model uses DS-HDP-HMM regime detection plus per-regime CNPs to produce regime-weighted price forecasts that rank as the most balanced option under TOPSIS across 2021-2023 when tested in battery arbitrage and grid-service tasks.
-
Exploring Temporal Representation in Neural Processes for Multimodal Action Prediction
A revised DMBN with positional time encoding improves temporal representation and generalization in neural processes for multimodal robotic action prediction.
- Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation