Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
arXiv preprint arXiv:2110.09485 , year=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3representative citing papers
TabKDE generates synthetic tabular data using copula transformations followed by kernel density estimation, matching prior accuracy with negligible training time and reduced storage via coresets.
A tractable ensemble distributionally robust Bayesian optimization method achieves improved sublinear regret bounds under context uncertainty.
RG-inspired lattice models for piecewise GLMs provide explicit interpretable partitions and a replica-analysis-derived scaling law for regularization that allows increasing complexity without expected rise in generalization loss.
A new scale-aware diagnostic framework shows that unconstrained diffusion generative models exhibit structural freezing and instability instead of smooth physical responses under multiscale perturbations.
A new framework evaluates utility of synthetic mobility trajectories while a membership inference attack reveals privacy vulnerabilities in generative models thought to be safe.
Orthogonal subspace decomposition via SVD on vision foundation model features preserves high-rank pre-trained knowledge by freezing principal components and adapting residuals, reducing overfitting for better generalization in AI-generated image detection.
Empirical benchmarks show PINNs and operator networks are orders of magnitude slower and less accurate than finite-difference methods outside training intervals, while automatic differentiation through a conventional solver recovers material properties with ~1% error in seconds.
citing papers explorer
-
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
-
TabKDE: Simple and Scalable Tabular Data Generation with Kernel Density Estimates
TabKDE generates synthetic tabular data using copula transformations followed by kernel density estimation, matching prior accuracy with negligible training time and reduced storage via coresets.
-
Ensemble Distributionally Robust Bayesian Optimisation
A tractable ensemble distributionally robust Bayesian optimization method achieves improved sublinear regret bounds under context uncertainty.
-
A renormalization-group inspired lattice-based framework for piecewise generalized linear models
RG-inspired lattice models for piecewise GLMs provide explicit interpretable partitions and a replica-analysis-derived scaling law for regularization that allows increasing complexity without expected rise in generalization loss.
-
Scale-Aware Adversarial Analysis: A Diagnostic for Generative AI in Multiscale Complex Systems
A new scale-aware diagnostic framework shows that unconstrained diffusion generative models exhibit structural freezing and instability instead of smooth physical responses under multiscale perturbations.
-
A Dual Perspective on Synthetic Trajectory Generators: Utility Framework and Privacy Vulnerabilities
A new framework evaluates utility of synthetic mobility trajectories while a membership inference attack reveals privacy vulnerabilities in generative models thought to be safe.
-
Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection
Orthogonal subspace decomposition via SVD on vision foundation model features preserves high-rank pre-trained knowledge by freezing principal components and adapting residuals, reducing overfitting for better generalization in AI-generated image detection.
-
A Critical Assessment of PINNs and Operator Learning for Geotechnical Engineering
Empirical benchmarks show PINNs and operator networks are orders of magnitude slower and less accurate than finite-difference methods outside training intervals, while automatic differentiation through a conventional solver recovers material properties with ~1% error in seconds.