REVIEW 4 cited by
GenPhys: From Physical Processes to Generative Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Since diffusion models (DM) and the more recent Poisson flow generative models (PFGM) are inspired by physical processes, it is reasonable to ask: Can physical processes offer additional new generative models? We show that the answer is yes. We introduce a general family, Generative Models from Physical Processes (GenPhys), where we translate partial differential equations (PDEs) describing physical processes to generative models. We show that generative models can be constructed from s-generative PDEs (s for smooth). GenPhys subsume the two existing generative models (DM and PFGM) and even give rise to new families of generative models, e.g., "Yukawa Generative Models" inspired from weak interactions. On the other hand, some physical processes by default do not belong to the GenPhys family, e.g., the wave equation and the Schr\"{o}dinger equation, but could be made into the GenPhys family with some modifications. Our goal with GenPhys is to explore and expand the design space of generative models.
Forward citations
Cited by 4 Pith papers
-
Telegrapher's Generative Model via Kac Flows
Kac flows, driven by the telegrapher's equation, provide a generative model with an explicit conditional velocity field and bounded velocity norm.
-
Learning with springs and sticks
A damped spring-and-stick lattice performs regression by energy relaxation, and a reported 'thermodynamic learning barrier' sets the minimum free energy needed for learning.
-
Optical Physics-Based Generative Models
Optical wave equations are claimed to work as generative models with big efficiency gains, but the derivations contain algebraic sign errors and the reported FID scores are mutually inconsistent.
-
Beyond Equilibrium: Non-Equilibrium Foundations Should Underpin Generative Processes in Complex Dynamical Systems
A position paper arguing that non-equilibrium-physics-inspired generative models (like diffusion models) are, and should be, the foundation for modeling time-varying complex systems, supported by one 2D simulation.
Discussion (0). Sign in to comment.