PGDG generates diverse, successful recovery trajectories from a single demonstration using iterative physics-grounded sampling and zero-shot curation to improve bimanual policy robustness.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Develops safe particle flow for constrained variational inference by applying control barrier functions to probability densities with theoretical guarantees.
Symplectic inductive bias combined with chain policies yields sufficient conditions for target reachability in Hamiltonian systems whose sample complexity depends on recurrence and geometry rather than ambient dimension.
The V-PMB filter is obtained as coordinate-descent KLD minimization that approximates the PMBM posterior while preserving its probability hypothesis density.
A literature review of 18 transformation approaches reveals that none provide systematic guidance for deriving machine learning task specifications from business problems, creating the Analytics Translation Problem.
Two panoramic 3D datasets—one dense static and one sparse dynamic—are released for place categorization, achieving up to 96.42% accuracy in baseline tests.
citing papers explorer
-
PGDG: Physically Grounded Data Generation for Robust Bimanual Policy Learning from a Single Demonstration
PGDG generates diverse, successful recovery trajectories from a single demonstration using iterative physics-grounded sampling and zero-shot curation to improve bimanual policy robustness.
-
Constrained Variational Inference via Safe Particle Flow
Develops safe particle flow for constrained variational inference by applying control barrier functions to probability densities with theoretical guarantees.
-
Symplectic Inductive Bias for Data-Driven Target Reachability in Hamiltonian Systems
Symplectic inductive bias combined with chain policies yields sufficient conditions for target reachability in Hamiltonian systems whose sample complexity depends on recurrence and geometry rather than ambient dimension.
-
Variational PMB filter via coordinate descent Kullback-Leibler divergence minimisation
The V-PMB filter is obtained as coordinate-descent KLD minimization that approximates the PMBM posterior while preserving its probability hypothesis density.
-
From Business Problems to AI Solutions: Where Does Transformation Support Fail
A literature review of 18 transformation approaches reveals that none provide systematic guidance for deriving machine learning task specifications from business problems, creating the Analytics Translation Problem.
-
Multi-modal panoramic 3D outdoor datasets for place categorization
Two panoramic 3D datasets—one dense static and one sparse dynamic—are released for place categorization, achieving up to 96.42% accuracy in baseline tests.