Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Typical Model Studies01:30

Typical Model Studies

299
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
299
Plane Potential Flows01:23

Plane Potential Flows

323
Plane potential flows simplify fluid motion by assuming the fluid to be irrotational and incompressible. These characteristics allow these flows to be described by a velocity potential function, ϕ, representing the flow speed in a given direction, and a stream function, ψ, that visualizes the flow path, both governed by Laplace's equation. These parameters help in estimating flow patterns, velocity distributions, and pressure fields around various hydraulic structures.
Uniform...
323
Reynolds Transport Theorem01:24

Reynolds Transport Theorem

797
The Reynolds transport theorem provides a framework to relate the time rate of change of an extensive property within a system to that in a control volume, which is crucial for analyzing fluid dynamics. Extensive properties, such as mass, velocity, acceleration, temperature, and momentum, can be expressed in terms of the mass of a fluid portion. These properties are called extensive because they depend on the system's size, while intensive properties are their corresponding values per unit...
797
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

38
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
38
General Characteristics of Pipe Flow I01:22

General Characteristics of Pipe Flow I

648
Pipe flow refers to the movement of fluids within fully enclosed conduits, typically cylindrical in shape, such as water pipes or hydraulic hoses. These conduits are designed to withstand high-pressure gradients that drive fluid movement, contrasting with open-channel flows, where gravity is the primary driving force. Rectangular conduits, like air conditioning and heating ducts, generally operate at lower pressures and are less suited for high-pressure applications.
The classification of fluid...
648
Gene Flow02:39

Gene Flow

34.6K
Gene flow is the transfer of genes among populations, resulting from either the dispersal of gametes or from the migration of individuals.
34.6K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

GeoToken: Hierarchical Geolocalization of Images via Next Token Prediction.

Proceedings. IEEE International Conference on Data Mining·2026
Same author

Machine learning symmetry discovery for integrable Hamiltonian dynamics.

Physical review. E·2026
Same author

A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks.

Advances in neural information processing systems·2026
Same author

mL-BFGS: A Momentum-based L-BFGS for Distributed Large-Scale Neural Network Optimization.

Transactions on machine learning research·2025
Same author

Towards fair decentralized benchmarking of healthcare AI algorithms with the Federated Tumor Segmentation (FeTS) challenge.

Nature communications·2025
Same author

Demonstration of robust and efficient quantum property learning with shallow shadows.

Nature communications·2025

Related Experiment Video

Updated: May 27, 2025

Combining Fluidic Devices with Microscopy and Flow Cytometry to Study Microbial Transport in Porous Media Across Spatial Scales
12:32

Combining Fluidic Devices with Microscopy and Flow Cytometry to Study Microbial Transport in Porous Media Across Spatial Scales

Published on: November 25, 2020

6.4K

Renormalization group flow, optimal transport, and diffusion-based generative model.

Artan Sheshmani1,2,3, Yi-Zhuang You4, Baturalp Buyukates5

  • 1MIT, Institute for Artificial Intelligence and Fundamental Interactions, Cambridge, Massachusetts 02138, USA.

Physical Review. E
|February 20, 2025
PubMed
Summary
This summary is machine-generated.

We developed a novel generative artificial intelligence (AI) model using diffusion processes inspired by physics. This new approach generates high-quality images faster by reversing renormalization group flow in Fourier space.

More Related Videos

Generation of Size-controlled Poly ethylene Glycol Diacrylate Droplets via Semi-3-Dimensional Flow Focusing Microfluidic Devices
11:08

Generation of Size-controlled Poly ethylene Glycol Diacrylate Droplets via Semi-3-Dimensional Flow Focusing Microfluidic Devices

Published on: July 3, 2018

7.7K
Visualizing Hyporheic Flow Through Bedforms Using Dye Experiments and Simulation
09:49

Visualizing Hyporheic Flow Through Bedforms Using Dye Experiments and Simulation

Published on: November 18, 2015

12.1K

Related Experiment Videos

Last Updated: May 27, 2025

Combining Fluidic Devices with Microscopy and Flow Cytometry to Study Microbial Transport in Porous Media Across Spatial Scales
12:32

Combining Fluidic Devices with Microscopy and Flow Cytometry to Study Microbial Transport in Porous Media Across Spatial Scales

Published on: November 25, 2020

6.4K
Generation of Size-controlled Poly ethylene Glycol Diacrylate Droplets via Semi-3-Dimensional Flow Focusing Microfluidic Devices
11:08

Generation of Size-controlled Poly ethylene Glycol Diacrylate Droplets via Semi-3-Dimensional Flow Focusing Microfluidic Devices

Published on: July 3, 2018

7.7K
Visualizing Hyporheic Flow Through Bedforms Using Dye Experiments and Simulation
09:49

Visualizing Hyporheic Flow Through Bedforms Using Dye Experiments and Simulation

Published on: November 18, 2015

12.1K

Area of Science:

  • Artificial Intelligence
  • Statistical Physics
  • Information Theory

Background:

  • Diffusion-based generative models are a key area in AI research.
  • Recent physics research links renormalization group (RG) flow to diffusion processes.

Purpose of the Study:

  • To develop a diffusion-based generative model by reversing momentum-space RG flow.
  • To bridge statistical physics and information theory using optimal transport.

Main Methods:

  • Interpreting RG flow as optimal transport gradient flow.
  • Applying forward and reverse diffusion in Fourier space for image generation.
  • Utilizing a scale-dependent noise schedule informed by dispersion relations.

Main Results:

  • The model efficiently separates signal from noise and manages image features across scales in Fourier space.
  • Achieved high-quality image generation with significantly reduced training time compared to existing models.
  • Demonstrated effectiveness on standard image datasets.

Conclusions:

  • The study presents a novel framework for generative AI inspired by theoretical physics.
  • This approach enhances understanding of image generative processes and offers new research avenues.
  • Highlights the convergence of physics, optimal transport, and machine learning.