Pith. sign in

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

arxiv 2304.02637 v1 pith:TEYNP3RZ submitted 2023-04-05 cs.LG cs.AIphysics.comp-phphysics.data-anquant-ph

classification cs.LGcs.AIphysics.comp-phphysics.data-anquant-ph
keywords modelsgenerativegenphysphysicalprocessesfamilyequationinspired
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Telegrapher's Generative Model via Kac Flows

    math.AP 2025-06 conditional novelty 6.0 of 10

    Kac flows, driven by the telegrapher's equation, provide a generative model with an explicit conditional velocity field and bounded velocity norm.

  2. Learning with springs and sticks

    cs.LG 2025-08 conditional novelty 5.0 of 10

    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.

  3. Optical Physics-Based Generative Models

    physics.optics 2025-06 reject novelty 4.0 of 10

    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.

  4. Beyond Equilibrium: Non-Equilibrium Foundations Should Underpin Generative Processes in Complex Dynamical Systems

    cs.CE 2025-05 conditional novelty 3.0 of 10

    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.

Pith tools