Gated QKAN-FWP combines fast weight programming with quantum-inspired Kolmogorov-Arnold networks via single-qubit DARUAN activations and gated updates to deliver a 12.5k-parameter model that outperforms larger classical RNNs on long-horizon solar forecasting while running on NISQ devices.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
A pre-computation method sets penalization weights for constrained QUBO problems with provable guarantees for Gibbs solvers and polynomial scaling for many problem classes.
Global Bradley-Terry rankings of LLMs are misleading due to structured heterogeneity in user preferences, and small (λ, ν)-portfolios recover coherent subpopulations that cover over 96% of votes with just five rankings.
PIDN replaces repeated multi-noise ZNE evaluations with a trained network that denoises expectation values and gradients from noisy data plus history, achieving comparable optimization on quantum models with 4-6x fewer circuits.
citing papers explorer
-
Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning
Gated QKAN-FWP combines fast weight programming with quantum-inspired Kolmogorov-Arnold networks via single-qubit DARUAN activations and gated updates to deliver a 12.5k-parameter model that outperforms larger classical RNNs on long-horizon solar forecasting while running on NISQ devices.
-
Scalable Determination of Penalization Weights for Constrained Optimizations on Approximate Solvers
A pre-computation method sets penalization weights for constrained QUBO problems with provable guarantees for Gibbs solvers and polynomial scaling for many problem classes.
-
Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML
Global Bradley-Terry rankings of LLMs are misleading due to structured heterogeneity in user preferences, and small (λ, ν)-portfolios recover coherent subpopulations that cover over 96% of votes with just five rankings.
-
Accelerating Noisy Variational Quantum Algorithms with Physics-Informed Denoising Networks
PIDN replaces repeated multi-noise ZNE evaluations with a trained network that denoises expectation values and gradients from noisy data plus history, achieving comparable optimization on quantum models with 4-6x fewer circuits.