Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.
Title resolution pending
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
years
2026 16representative citing papers
Gaussian Processes enable efficient conditioning for batch selection in Bayesian optimization, unifying pseudo-observation methods and outperforming or matching explicit penalization on benchmarks.
AB-SID-iVAR enables Gaussian process active learning for self-induced Boltzmann distributions by closed-form approximation of the target, with high-probability error vanishing guarantees and empirical gains on PES and drug discovery tasks.
A myopic MINMPC framework learns a value function offline via inverse optimization from expert data, allowing short horizons with near-optimal performance and strict integer feasibility online for hybrid systems.
ARCH is a hierarchical flow-based generative model that enables tractable conditional intensity computation and arbitrary conditioning for spatiotemporal event distributions.
The impact-aware MPC reduces post-impact deflection by 86.2% in experiments by predicting discontinuous velocities with an embedded restitution model.
The generalization advantage of SGD over random sampling diminishes with growing training set size in binary networks, as measured by joint density of states over train and test accuracy.
TOI-1533 is confirmed as a rare compact system hosting an inner sub-Neptune and an outer hot super-Neptune-mass giant with nearly equal masses and very different radii.
An augmented kernel ridge regression estimator separates linear and nonlinear components to achieve sharp oracle inequalities and minimax optimal prediction risk under general kernels.
A deep kernel learning architecture with transformer feature extraction on clinical-BERT embeddings and Gaussian process backend identifies three glaucoma subgroups by decoupling progression trajectories from current visual acuity in multimodal EHR data.
LLM OOD detectors are length-confounded; a two-pathway embedding-plus-trajectory framework detects covert OOD inputs at 0.721 average AUROC and 0.850 on jailbreaks.
A semi-parametric framework decouples discrepancy functions from physics-based components via orthogonal Gaussian process regression for interpretable nonlinear system identification from incomplete physics.
A generative framework using latent heteroscedastic Gaussian process approximated via Hilbert space methods plus optimal transport to model population trends and infer trajectories in temporal scRNA-seq data.
TOI-1710 b has a true obliquity of 149 degrees indicating retrograde motion, favoring high-eccentricity migration via planet-planet scattering and Kozai-Lidov cycles for this tidally detached super-Neptune.
Frontal and fronto-central EEG regions show the most consistent predictive utility for cognitive workload in subject-independent settings, outperforming full-scalp baselines by 15-20% in relative rank across datasets.
TOI-159 b is confirmed as the hottest known eccentric hot Jupiter (e = 0.24) with a 13-sigma Keplerian detection around a young gamma Doradus star, including a preliminary low-resolution transmission spectrum.
citing papers explorer
-
Mat\'ern Noise for Triangulation-Agnostic Flow Matching on Meshes
Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.
-
Efficient Conditioning Why Pseudo Observation Batch Bayesian Optimization Works When It Does not
Gaussian Processes enable efficient conditioning for batch selection in Bayesian optimization, unifying pseudo-observation methods and outperforming or matching explicit penalization on benchmarks.
-
Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights
AB-SID-iVAR enables Gaussian process active learning for self-induced Boltzmann distributions by closed-form approximation of the target, with high-probability error vanishing guarantees and empirical gains on PES and drug discovery tasks.
-
Learning myopic mixed-integer nonlinear model predictive control from expert demonstrations
A myopic MINMPC framework learns a value function offline via inverse optimization from expert data, allowing short horizons with near-optimal performance and strict integer feasibility online for hybrid systems.
-
Arbitrarily Conditioned Hierarchical Flows for Spatiotemporal Events
ARCH is a hierarchical flow-based generative model that enables tractable conditional intensity computation and arbitrary conditioning for spatiotemporal event distributions.
-
Impact-Aware Model Predictive Control for UAV Landing on a Heaving Platform
The impact-aware MPC reduces post-impact deflection by 86.2% in experiments by predicting discontinuous velocities with an embedded restitution model.
-
Revisiting the Volume Hypothesis
The generalization advantage of SGD over random sampling diminishes with growing training set size in binary networks, as measured by joint density of states over train and test accuracy.
-
The GAPS programme at TNG: LXXVI. TOI-1533: a compact system hosting a super-Neptune-mass pair with disparate radii
TOI-1533 is confirmed as a rare compact system hosting an inner sub-Neptune and an outer hot super-Neptune-mass giant with nearly equal masses and very different radii.
-
Adaptive Kernel Ridge Regression with Linear Structure: Sharp Oracle Inequalities and Minimax Optimality
An augmented kernel ridge regression estimator separates linear and nonlinear components to achieve sharp oracle inequalities and minimax optimal prediction risk under general kernels.
-
Deep Kernel Learning for Stratifying Glaucoma Trajectories
A deep kernel learning architecture with transformer feature extraction on clinical-BERT embeddings and Gaussian process backend identifies three glaucoma subgroups by decoupling progression trajectories from current visual acuity in multimodal EHR data.
-
How Language Models Process Out-of-Distribution Inputs: A Two-Pathway Framework
LLM OOD detectors are length-confounded; a two-pathway embedding-plus-trajectory framework detects covert OOD inputs at 0.721 average AUROC and 0.850 on jailbreaks.
-
Orthogonal Discrepancy Kernels for Learning with Partial Physics
A semi-parametric framework decouples discrepancy functions from physics-based components via orthogonal Gaussian process regression for interpretable nonlinear system identification from incomplete physics.
-
Modeling Temporal scRNA-seq Data with Latent Gaussian Process and Optimal Transport
A generative framework using latent heteroscedastic Gaussian process approximated via Hilbert space methods plus optimal transport to model population trends and infer trajectories in temporal scRNA-seq data.
-
A tidally detached super Neptune on a strongly misaligned retrograde orbit
TOI-1710 b has a true obliquity of 149 degrees indicating retrograde motion, favoring high-eccentricity migration via planet-planet scattering and Kozai-Lidov cycles for this tidally detached super-Neptune.
-
Assessing Region-Level EEG Contributions to Cognitive Workload Prediction
Frontal and fronto-central EEG regions show the most consistent predictive utility for cognitive workload in subject-independent settings, outperforming full-scalp baselines by 15-20% in relative rank across datasets.
-
TOI-159 b: an eccentric hot-Jupiter planet around a young, pulsating $\gamma$ Doradus star
TOI-159 b is confirmed as the hottest known eccentric hot Jupiter (e = 0.24) with a 13-sigma Keplerian detection around a young gamma Doradus star, including a preliminary low-resolution transmission spectrum.