AI RESEARCH
Geometry-Induced Long-Range Correlations in Recurrent Neural Network Quantum States
arXiv CS.LG
•
ArXi:2604.08661v1 Announce Type: cross Neural Quantum States based on autoregressive recurrent neural network (RNN) wave functions enable efficient sampling without Marko-chain autocorrelation, but standard RNN architectures are biased toward finite-length correlations and can fail on states with long-range dependencies. A common response is to adopt transformer-style self-attention, but this typically comes with substantially higher computational and memory overhead. Here we