Fully convolutional diffusion models trained on small lattices transfer to unseen larger volumes for 2D/3D phi^4 sampling across phases, matching or beating same-size training on most observables.
32 decompose the recorded denois- ing score-matching loss according to the diffusion time sampled for each training configuration
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
hep-lat 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Diffusion Models for Sampling Near Criticality in Lattice Field Theories
Fully convolutional diffusion models trained on small lattices transfer to unseen larger volumes for 2D/3D phi^4 sampling across phases, matching or beating same-size training on most observables.