Thinned-data MSE for small-area models is unbiased for a risk that systematically differs from full-data risk; under Fay-Herriot the gap is closed-form in the model's shrinkage, and the thinning fraction faces a sharp bias-variance tradeoff.
Dora: Object affordance-guided reinforcement learning for dexterous robotic manipulation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
Dense spatial modulation of multiple 3D LUTs plus an uncertainty-weighted reconstruction loss improves mixed under/over-exposure correction over global-modulation baselines on four benchmarks.
citing papers explorer
-
On Data Thinning for Model Validation in Small Area Estimation
Thinned-data MSE for small-area models is unbiased for a risk that systematically differs from full-data risk; under Fay-Herriot the gap is closed-form in the model's shrinkage, and the thinning fraction faces a sharp bias-variance tradeoff.
-
Learning Dexterous Grasping from Sparse Taxonomy Guidance
Dense spatial modulation of multiple 3D LUTs plus an uncertainty-weighted reconstruction loss improves mixed under/over-exposure correction over global-modulation baselines on four benchmarks.