mlsanityData to 7 Oct 2026

GenPhys: From Physical Processes to Generative Models

arXiv 2304.02637 ↗First posted 5 Apr 2023cs.LG cs.AI physics.comp-phcited by 19

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

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"odinger 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.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 18 of its 35 references that are in the map. First posted on arXiv 5 Apr 2023.

Builds on

18 of 35 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  4. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 14

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  2. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  3. 2022Flow Matching for Generative Modelingcited by 5,426
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  5. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  6. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
  7. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  8. 2022Generative Modelling With Inverse Heat Dissipationcited by 164
  9. 2021Unbalanced minibatch Optimal Transport; applications to Domain Adaptationcited by 123
  10. 2016Why does deep and cheap learning work so well?cited by 100
  11. 2022Poisson Flow Generative Modelscited by 95
  12. 2023PFGM++: Unlocking the Potential of Physics-Inspired Generative Modelscited by 73
2 more
  1. 2019Accelerating Langevin Sampling with Birth-deathcited by 45
  2. 2020Unbalanced Sobolev Descentcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 5; 2025: 3; 2026: 6.

19 papers.

Sort:

By area:

  1. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
  2. 2023Taming Mode Collapse in Score Distillation for Text-to-3D Generationcited by 35
  3. 2024QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptationcited by 23
  4. 2025Telegrapher's Generative Model via Kac Flowscited by 7
  5. 2023A Survey of Generative AI for Intelligent Transportation Systems: Road Transportation Perspectivecited by 6
  6. 2024Physics-Inspired Generative Models in Medical Imaging: A Reviewcited by 5
  7. 2024Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attackscited by 4
  8. 2023DiFace: Cross-Modal Face Recognition through Controlled Diffusioncited by 1
  9. 2024MERCURY: A fast and versatile multi-resolution based global emulator of compound climate hazardscited by 1
  10. 2025EquiReg: Equivariance Regularized Diffusion for Inverse Problemscited by 1
  11. 2026Unlocking the Duality between Flow and Field Matchingcited by 1
  12. 2023Augmenting Control over Exploration Space in Molecular Dynamics Simulators to Streamline De Novo Analysis through Generative Control Policiescited by 0
7 more
  1. 2023FreeFlow: A Comprehensive Understanding on Diffusion Probabilistic Models via Optimal Transportcited by 0
  2. 2025Learning with springs and stickscited by 0
  3. 2026Holographic generative flows with AdS/CFTcited by 0
  4. 2026GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videoscited by 0
  5. 2026LDDMM stochastic interpolants: an application to domain uncertainty quantification in hemodynamicscited by 0
  6. 2026PFlow-T: A Persistence-Driven Forward Process for Topology-Controlled Generationcited by 0
  7. 2026Low-Pass Flow Matchingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Generative diffusion models from a PDE perspective
  2. 2026Notes on generative modeling: flow matching, diffusion, optimal transport and Schr"odinger bridge
  3. 2023Interpretable ODE-style Generative Diffusion Model via Force Field Construction
  4. 2023The statistical thermodynamics of generative diffusion models: Phase transitions, symmetry breaking and critical instability
  5. 2026A Tutorial on Diffusion Theory: From Differential Equations to Diffusion Models
  6. 2024GUD: Generation with Unified Diffusion
  7. 2025A PDE Perspective on Generative Diffusion Models
  8. 2026A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models