Across 19 multimodal LLMs, local Feynman-diagram recognition stays high while topological reconstruction and full amplitude derivation collapse.
Understanding Diffusion Models by Feynman's Path Integral
2 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
abstract
Score-based diffusion models have proven effective in image generation and have gained widespread usage; however, the underlying factors contributing to the performance disparity between stochastic and deterministic (i.e., the probability flow ODEs) sampling schemes remain unclear. We introduce a novel formulation of diffusion models using Feynman's path integral, which is a formulation originally developed for quantum physics. We find this formulation providing comprehensive descriptions of score-based generative models, and demonstrate the derivation of backward stochastic differential equations and loss functions.The formulation accommodates an interpolating parameter connecting stochastic and deterministic sampling schemes, and we identify this parameter as a counterpart of Planck's constant in quantum physics. This analogy enables us to apply the Wentzel-Kramers-Brillouin (WKB) expansion, a well-established technique in quantum physics, for evaluating the negative log-likelihood to assess the performance disparity between stochastic and deterministic sampling schemes.
citation-role summary
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
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.
citing papers explorer
-
FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning
Across 19 multimodal LLMs, local Feynman-diagram recognition stays high while topological reconstruction and full amplitude derivation collapse.
-
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.