João Augusto Sobral
@joaosds.bsky.social
Physicist. Interested in deep learning and (quasi)particles. PhD student at @Uni_Stuttgart
Happy to finally get this one out! We introduce a framework where effective theories (relative to a target Hamiltonian H) can be tested on how they influence (i) the training and (ii) the quality of ground state representations with Transformers.
arxiv.org/abs/2412.12248
arxiv.org/abs/2412.12248
Physics-informed Transformers for Electronic Quantum States
Neural-network-based variational quantum states in general, and more recently autoregressive models in particular, have proven to be powerful tools to describe complex many-body wave functions. Howeve...
arxiv.org
December 18, 2024 at 7:44 PM
Happy to finally get this one out! We introduce a framework where effective theories (relative to a target Hamiltonian H) can be tested on how they influence (i) the training and (ii) the quality of ground state representations with Transformers.
arxiv.org/abs/2412.12248
arxiv.org/abs/2412.12248
Reposted by João Augusto Sobral
We are organizing a workshop on ML for quantum matter in Dresden in February 2025. The application deadline is Nov. 30, apply! www.pks.mpg.de/mlqmat25
Max Planck Institute for the Physics of Complex Systems Machine Learning for Quantum Matter
www.pks.mpg.de
November 27, 2024 at 12:44 PM
We are organizing a workshop on ML for quantum matter in Dresden in February 2025. The application deadline is Nov. 30, apply! www.pks.mpg.de/mlqmat25