Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 21 min ago
Peer-reviewedCC BY 4.0SciPost Physics

Attention-based foundation model for quantum states

  • Timothy Zaklama1
  • Daniele Guerci1
  • Liang Fu1
  1. 1Massachusetts Institute of Technology
Open at sourcePDFDOICite

Abstract

We present an attention-based foundation model architecture for learning and predicting quantum states across Hamiltonian parameters, system sizes, and physical systems. Using only basis configurations and physical parameters as inputs, our trained neural network is able to produce highly accurate ground state wavefunctions. For example, we build the phase diagram for the 2D square-lattice t t – V V model with N N particles, from only 18 training points in parameter space (V/t,N) ( V / t , N ) . Thus, our architecture provides a basis for building a universal foundation model for quantum matter.

Related

  1. Foundation Neural-Network Quantum States for Molecular Potential Energy Surfaces in Second Quantization
    Lizhong Fu, Jianan Wei, Wenguan Wang +1
    arXivPreprintCC BY 4.0Full textPhysical chemistryQuantum physics & quantum informationarXiv
  2. Designing Strongly Correlated Quantum Phases of Matter with Foundation Neural-Network Quantum States
    Alessandro Sinibaldi, Luciano Loris Viteritti, Riccardo Rende +2
    arXivPreprintarXiv licenceFull textCondensed matterarXiv
  3. Topology Obstructs Pure Foundation Neural Quantum States
    Timothy Heightman, Elena Orlova, Philip Mantrov +1
    arXivPreprintarXiv licenceFull textMathematical physicsCondensed matterarXiv
  4. QSoftCore: A Conceptual Foundation for Quantum Software Engineering
    Tao Yue, Yuechen Li, Man Zhang
    arXivPreprintCC BY 4.0Full textQuantum physics & quantum informationarXiv
  5. Toward a Quantum Information Foundation for Neutron Scattering
    Michael J. Landry, Yongqiang Cheng, Daniel Pajerowski +2
    arXivPreprintCC BY 4.0Full textCondensed matterHigh-energy & particle physicsarXiv

Cite

BibTeXRIS
BibTeX
@article{zaklama2026attentionbased,
  title = {{Attention-based foundation model for quantum states}},
  author = {Timothy Zaklama and Daniele Guerci and Liang Fu},
  journal = {SciPost Physics},
  year = {2026},
  month = oct,
  doi = {10.21468/scipostphys.21.4.084},
  url = {https://scipost.org/10.21468/SciPostPhys.21.4.084},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Attention-based foundation model for quantum states
AU  - Timothy Zaklama
AU  - Daniele Guerci
AU  - Liang Fu
PY  - 2026
DA  - 2026/10/08
JO  - SciPost Physics
DO  - 10.21468/scipostphys.21.4.084
UR  - https://scipost.org/10.21468/SciPostPhys.21.4.084
AB  - We present an attention-based foundation model architecture for learning and predicting quantum states across Hamiltonian parameters, system sizes, and physical systems. Using only basis configurations and physical parameters as inputs, our trained neural network is able to produce highly accurate ground state wavefunctions. For example, we build the phase diagram for the 2D square-lattice t t – V V model with N N particles, from only 18 training points in parameter space (V/t,N) ( V / t , N ) . Thus, our architecture provides a basis for building a universal foundation model for quantum matter.
SN  - 2542-4653
ER  -