Our papers are the official record of our discoveries. They allow others to build on and apply our work. Each paper is the result of many months of research, so we make a special effort to make them clear, beautiful and inspirational, and publish them in leading journals.

x10icon
  • Machine-learning the classification of spacetimes

    YHY. HeJI Physics Letters B

    AI classifies space-time

    A neural network learns to classify different types of spacetime in general relativity according to their algebraic Petrov classification.

  • Crystal melting, BPS quivers and plethystics

    JBJ. BaoYHY. HeAZA. Zahabi Journal of High Energy Physics

    Algebra of melting crystals

    Certain states in quantum field theories are described by the geometry and algebra of melting crystals via properties of partition functions.

  • Mahler measure for a quiver symphony

    JBJ. BaoYHY. HeAZA. Zahabi Communications in Mathematical Physics

    Mahler measure for quivers

    The Mahler measure is shown to be at the intersection between number theory, algebraic geometry, combinatorics, and quantum field theory.

  • Hilbert series, machine learning, and applications to physics

    JBJ. BaoYHY. HeEHE. HirstJHA.... Physics Letters B

    Machine learning Hilbert series

    Neural networks find efficient ways to compute the Hilbert series, an important counting function in algebraic geometry and gauge theory.

  • Physical Review D

    Calabi-Yau anomalies

    Unsupervised machine-learning of the Hodge numbers of Calabi-Yau hypersurfaces detects new patterns with an unexpected linear dependence.

  • Physics Letters B

    Line bundle connections

    Neural networks find numerical solutions to Hermitian Yang-Mills equations, a difficult system of PDEs crucial to mathematics and physics.

  • Journal of High Energy Physics

    QFT and kids’ drawings

    Groethendieck's “children’s drawings”, a type of bipartite graph, link number theory, geometry, and the physics of conformal field theory.

  • Journal of Symbolic Computation

    Learning the Sato–Tate conjecture

    Machine-learning methods can distinguish between Sato-Tate groups, promoting a data-driven approach for problems involving Euler factors.

  • International Journal of Modern Physics A

    Universes as big data

    Machine-learning is a powerful tool for sifting through the landscape of possible Universes that could derive from Calabi-Yau manifolds.

  • Arxiv

    Condensing the String Landscape

    The few-shot machine learning technique reduces the vast geometric landscape of string theory vacua to a tiny cluster of representatives.