AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

WF-Bench: A Benchmark for Neural-Network WaveFunction Expressivity and Scaling Laws

Lixing Zhang, Guijing Duan, Di Luo

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Scalable approximation and equivariant compute · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use Psiformer instead of Ferminet at comparable parameter countNN wavefunction architecture · WF-Bench, all 31 target wavefunctions, F(8)fidelity: Laughlin m5: 0.8737 -> 0.9966Improved
Increase number of determinants Ndet beyond about 32 (ablation)Ferminet and Psiformer · bcs s and moore m2fidelityNo clear effect
Increase number of determinants Ndet at small values (ablation)Ferminet and Psiformer · bcs s and moore m2fidelityImproved
Increase number of layers from 1 to 2 (ablation)Ferminet and Psiformer · bcs s and moore m2fidelityImproved
Increase number of layers beyond 2 (ablation)Ferminet and Psiformer · bcs s and moore m2fidelityNo clear effect
Use only one layer for the network (ablation)Ferminet and Psiformer · moore m2fidelityHurt
Increase electron number NeFerminet and Psiformer · all WF-Bench wavefunctionsfidelityHurt
Target a chiral triplet superconducting state (bcs fp tp) instead of a singlet stateFerminet and Psiformer · BCS wavefunctionsfidelity decay: Ferminet F(8): 0.9925 (bcs s) -> 0.8902 (bcs fp tp)Hurt
Add quasiholes to the Laughlin m=3 stateFerminet and Psiformer · topological statesfidelityHurt
Mix target and network distributions in the probability-matching loss (pmix) as pretrainingtopological state training · WF-Bench topological statestraining stabilityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy