SCALE and ACE are new convolutional backflow architectures for Neural Quantum States that deliver O(N^3) scaling with high accuracy and over 40x speedup on Hubbard and t-J models up to 32x32 lattices.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cond-mat.str-el 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Three Transformer backflow fermionic wave functions for the finite-doping Hubbard model converge, after accuracy improvements, to the same state with coexisting superconducting and stripe orders, demonstrating that variational energy is insufficient to identify the ground state.
citing papers explorer
-
Pareto Frontier of Neural Quantum States: Scalable, Affordable, and Accurate Convolutional Backflow for Strongly Correlated Lattice Fermions
SCALE and ACE are new convolutional backflow architectures for Neural Quantum States that deliver O(N^3) scaling with high accuracy and over 40x speedup on Hubbard and t-J models up to 32x32 lattices.
-
Beyond Variational Bias: Resolving Intertwined Orders in the Hubbard Model
Three Transformer backflow fermionic wave functions for the finite-doping Hubbard model converge, after accuracy improvements, to the same state with coexisting superconducting and stripe orders, demonstrating that variational energy is insufficient to identify the ground state.