Non-Equilibrium Statistical Physics and Generative AI: Control, Transport, and Sampling
A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Statistical Physics".
Deadline for manuscript submissions: 31 December 2026 | Viewed by 30
Special Issue Editors
Interests: applied mathematics; generative AI; non-equilibrium statistical physics; fluid mechanics; energy systems; control and optimization theory
Special Issue Information
Dear Colleagues,
Recent advances in generative artificial intelligence have created a renewed convergence between non-equilibrium statistical physics, stochastic optimal control, optimal transport, and high-dimensional sampling. Diffusion and flow-based generative models, Schrödinger bridges, stochastic thermodynamics, path-integral control, rare-event methods, and interacting particle systems now provide complementary languages for learning, sampling, and steering complex stochastic systems.
This Special Issue will provide a focused cross-community venue for these rapidly interacting areas. The central objective is to bring together researchers who normally publish across physics, control, applied probability, optimization, and machine-learning venues, but who are now studying closely related mathematical structures: entropy-regularized transport, path measures, controlled diffusions, score functions, free-energy landscapes, fluctuation identities, and distribution-to-distribution modeling under constraints.
We welcome original research and review articles on theoretical foundations, algorithms, numerical methods, and scientific applications connecting entropy, information, stochastic dynamics, control, transport, and generative modeling. The issue is intended to be selective and coherent rather than broad: contributions should have a clear conceptual link to non-equilibrium/statistical-physics ideas, stochastic control or transport, or sampling methods motivated by generative AI.
Topics of Interest
- Schrödinger bridges, stochastic optimal control, path-integral control, and entropy-regularized optimal transport.
- Score-based, diffusion, flow-based, and bridge-based generative models, including controllability, interpretability, and path-space formulations.
- Non-equilibrium free-energy methods, stochastic thermodynamics, fluctuation relations, path measures, and large deviations.
- Rare-event sampling, importance sampling, interacting particle methods, sequential Monte Carlo, and sampling under constraints.
- Learning-based transport and real-time distribution-to-distribution modeling in scientific, engineering, and physical applications.
- Information-theoretic and statistical-mechanical foundations of generative modeling, inference, and high-dimensional learning dynamics.
Prof. Dr. Michael Misha Chertkov
Dr. Abhishek Halder
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- non-equilibrium statistical physics
- generative AI
- diffusion models
- Schrödinger bridges
- stochastic optimal control
- optimal transport
- statistical thermodynamics
- rare-event sampling
- interacting particle systems
- information theory
- path measures
- AI for scientific computing
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
