RALP learns string-based chain-of-thought prompts as scoring functions for knowledge graph triples using Bayesian optimization from fewer than 30 examples, improving link prediction MRR by over 5% and achieving over 88% Jaccard similarity on complex OWL reasoning tasks.
Understanding the difficulty of training deep feedforward neural networks
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
φ-DeepONet learns mappings with discontinuities in inputs and outputs by combining multiple branch networks with a nonlinear interface embedding in the trunk, trained via physics- and interface-informed loss, and shows accurate results on 1D/2D benchmarks.
Higher-order LaSDI uses a high-order finite-difference scheme and rollout loss to improve long-term prediction accuracy in reduced-order models for parameterized PDEs, shown on the 2D Burgers equation.
A Voronoi-driven diffusion-based extension of Nadaraya-Watson regression on manifolds that suppresses high frequencies and approximates total-variation minimization for compressed sensing with identity operator.
Leaky RNNs improve grid-cell-like representations and path-integration accuracy by acting as a low-pass filter that stabilizes dynamics against noise.
citing papers explorer
-
Learning Chain Of Thoughts Prompts for Predicting Entities, Relations, and even Literals on Knowledge Graphs
RALP learns string-based chain-of-thought prompts as scoring functions for knowledge graph triples using Bayesian optimization from fewer than 30 examples, improving link prediction MRR by over 5% and achieving over 88% Jaccard similarity on complex OWL reasoning tasks.
-
$\phi-$DeepONet: A Discontinuity Capturing Neural Operator
φ-DeepONet learns mappings with discontinuities in inputs and outputs by combining multiple branch networks with a nonlinear interface embedding in the trunk, trained via physics- and interface-informed loss, and shows accurate results on 1D/2D benchmarks.
-
Higher-Order LaSDI: Reduced Order Modeling with Multiple Time Derivatives
Higher-order LaSDI uses a high-order finite-difference scheme and rollout loss to improve long-term prediction accuracy in reduced-order models for parameterized PDEs, shown on the 2D Burgers equation.
-
A Data-Driven Interpolation Method on Smooth Manifolds via Diffusion Processes and Voronoi Tessellations
A Voronoi-driven diffusion-based extension of Nadaraya-Watson regression on manifolds that suppresses high frequencies and approximates total-variation minimization for compressed sensing with identity operator.
-
Impact of leaky dynamics on predictive path integration accuracy in recurrent neural networks
Leaky RNNs improve grid-cell-like representations and path-integration accuracy by acting as a low-pass filter that stabilizes dynamics against noise.