Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 29 min ago
Peer-reviewedCC BYPhysical Review Research

Convolutional transformer wave functions

  • Ao Chen1,2
  • Vighnesh Dattatraya Naik2
  • Markus Heyl2
  1. 1Flatiron Institute
  2. 2University of Augsburg
Open at sourceDOICite

Abstract

Deep neural quantum states have recently achieved remarkable performance in solving challenging quantum many-body problems. While transformer networks appear particularly promising due to their success in computer science, we show that previously reported transformer wave functions have not so far been capable of utilizing their full power. Here, we introduce the convolutional transformer wave function (CTWF). We show that our CTWF exhibits state-of-the-art performance in ground-state search and nonequilibrium dynamics compared to previous results, demonstrating its promising capacity in complex quantum problems.

Related

  1. Embedding Paired Free-Fermion Gaussian States into Gutzwiller-Projected Bardeen--Cooper--Schrieffer Wave Functions
    Ryui Kaneko
    arXivPreprintarXiv licenceFull textCondensed matterQuantum physics & quantum informationarXiv
  2. Singular wave functions and quantum collapse in inverse-power potentials
    Hidetsugu Sakaguchi, Boris Malomed
    arXivPreprintCC BY 4.0Full textMathematical physicsQuantum physics & quantum informationarXiv
  3. Selected Stabilizer Subspaces for Compact Many-Body Wave Functions
    Maria-Andreea Filip, George H. Booth
    arXivPreprintarXiv licenceFull textQuantum physics & quantum informationarXiv
  4. Neural network–augmented Pfaffian wave-functions for scalable simulations of interacting fermions
    Ao Chen, Zhou‐Quan Wan, Anirvan M. Sengupta +2
    Proceedings of the National Academy of SciencesPeer-reviewedCC BY-NC-ND36 citedAtomic, molecular & optical physicsOpenAlex
  5. Free-particle Green's function matrix elements over spherical Gaussian and plane-wave-modulated Gaussian basis functions
    Dibyendu Mahato, Wojciech Skomorowski
    arXivPreprintCC BY 4.0Full textPhysical chemistryAtomic, molecular & optical physicsarXiv

Cite

BibTeXRIS
BibTeX
@article{chen2026convolutional,
  title = {{Convolutional transformer wave functions}},
  author = {Ao Chen and Vighnesh Dattatraya Naik and Markus Heyl},
  journal = {Physical Review Research},
  year = {2026},
  month = may,
  doi = {10.1103/7xwp-25y9},
  url = {https://doi.org/10.1103/7xwp-25y9},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Convolutional transformer wave functions
AU  - Ao Chen
AU  - Vighnesh Dattatraya Naik
AU  - Markus Heyl
PY  - 2026
DA  - 2026/05/15
JO  - Physical Review Research
DO  - 10.1103/7xwp-25y9
UR  - https://doi.org/10.1103/7xwp-25y9
AB  - Deep neural quantum states have recently achieved remarkable performance in solving challenging quantum many-body problems. While transformer networks appear particularly promising due to their success in computer science, we show that previously reported transformer wave functions have not so far been capable of utilizing their full power. Here, we introduce the convolutional transformer wave function (CTWF). We show that our CTWF exhibits state-of-the-art performance in ground-state search and nonequilibrium dynamics compared to previous results, demonstrating its promising capacity in complex quantum problems.
SN  - 2643-1564
ER  -