Research
Unifying Generative Models with Path Integrals
arXiv:2608.12438v1 Announce Type: new Abstract: We formulate generative modeling as a path integral in which flow-based, diffusion-based, variational, and adversarial models arise as different evaluat
arXiv:2608.12438v1 Announce Type: new Abstract: We formulate generative modeling as a path integral in which flow-based, diffusion-based, variational, and adversarial models arise as different evaluation principles for a single master action. Its Martin-Siggia-Rose-Janssen-de~Dominicis (MSRJD) form separates free from interacting probability flows and opens them to diagrammatic perturbation theory. The expansion yields a one-loop correction to deterministic samplers at no stochastic-sampling cost, which we validate on solvable and nonlinear drifts, where it reduces a 53 % tree-level error to 1.6 %. Imperfect learned scores enter as insertions and yield a response-weighted score-matching objective, and symmetry-equivariant drift design becomes an operator expansion with EFT power counting.
Related
- HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization
- Lipschitz-Guided Design of Interpolation Schedules in Generative Models
- Notes on generative modeling: flow matching, diffusion, optimal transport and Schr{odinger bridge
- One-Step Flow Matching for Generative Modeling of Path-Dependent Physical Fields
- Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and Deletions
Source: arXiv cs.LG | 2026-08-14