Pith. sign in

Is attention all you need to solve the correlated electron problem?

3 Pith papers cite this work. Polarity classification is still indexing.

3 Pith papers citing it
abstract

The attention mechanism has transformed artificial intelligence research by its ability to learn relations between objects. In this work, we explore how a many-body wavefunction ansatz constructed from a large-parameter self-attention neural network can be used to solve the interacting electron problem in solids. By a systematic neural-network variational Monte Carlo study on a moir\'e quantum material, we demonstrate that the self-attention ansatz provides an accurate and efficient solution without human bias. Moreover, our numerical study finds that the required number of variational parameters scales roughly as $N^2$ with the number of electrons, which opens a path towards efficient large-scale simulations.

years

2026 3

representative citing papers

Accurate Self-Attention Wavefunctions at Large Scale

cond-mat.str-el · 2026-07-09 · conditional · novelty 6.0

Self-attention variational wavefunctions for the 2D homogeneous electron gas up to N=169 yield energies below DMC and a converged collective-mode dispersion including a roton-like minimum.

Simulating quantum circuits with a neural statebank

quant-ph · 2026-06-07 · unverdicted · novelty 6.0

A compact neural statebank based on autoregressive Transformers simulates 34-qubit quantum circuits with ~0.01 infidelity using 0.3 million parameters, outperforming tested approximate simulators.

Quantum Electron Quasicrystal

cond-mat.str-el · 2026-05-07 · unverdicted · novelty 6.0

Zero-point energy corrections from quantum fluctuations destabilize the classical honeycomb bilayer Wigner crystal and stabilize the 30-degree quasicrystalline state over a broad parameter range.

citing papers explorer

Showing 3 of 3 citing papers.

  • Accurate Self-Attention Wavefunctions at Large Scale cond-mat.str-el · 2026-07-09 · conditional · none · ref 14 · internal anchor

    Self-attention variational wavefunctions for the 2D homogeneous electron gas up to N=169 yield energies below DMC and a converged collective-mode dispersion including a roton-like minimum.

  • Simulating quantum circuits with a neural statebank quant-ph · 2026-06-07 · unverdicted · none · ref 34

    A compact neural statebank based on autoregressive Transformers simulates 34-qubit quantum circuits with ~0.01 infidelity using 0.3 million parameters, outperforming tested approximate simulators.

  • Quantum Electron Quasicrystal cond-mat.str-el · 2026-05-07 · unverdicted · none · ref 27

    Zero-point energy corrections from quantum fluctuations destabilize the classical honeycomb bilayer Wigner crystal and stabilize the 30-degree quasicrystalline state over a broad parameter range.