Sparse autoencoders applied to Neural Quantum States extract unsupervised features correlating with and causally steering physical observables such as order parameters while preserving variational energy.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
PWO is a trust-region optimizer for autoregressive NQS that improves stability over Adam and stochastic reconfiguration methods while scaling to 1.5B-parameter models on spin systems.
Canonical mapping of quantum-dot-superconductor clusters enables neural quantum-state calculations that reveal trivial singlet, Heisenberg-like, and critical regimes with 1D gaplessness and 2D triplet states.
citing papers explorer
-
Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders
Sparse autoencoders applied to Neural Quantum States extract unsupervised features correlating with and causally steering physical observables such as order parameters while preserving variational energy.
-
One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective
PWO is a trust-region optimizer for autoregressive NQS that improves stability over Adam and stochastic reconfiguration methods while scaling to 1.5B-parameter models on spin systems.
-
Correlated States in Quantum Dot Clusters Coupled to a Common Superconductor
Canonical mapping of quantum-dot-superconductor clusters enables neural quantum-state calculations that reveal trivial singlet, Heisenberg-like, and critical regimes with 1D gaplessness and 2D triplet states.