Skip To Main Content
Benjamin Kurt on Muck Rack

Benjamin Kurt

As seen in: arXiv
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile
Back to Benjamin Kurt’s profile

Articles by Benjamin Kurt

Condensed Matter > Materials Science

|
By Benjamin Kurt
| arXiv
Free energies govern solid-state phase stability, yet computational materials discovery still relies largely on ground-state energies because free energy calculations require ensemble averages. We introduce the thermodynamic interatomic potential (TIP), which extends an interatomic potential from its static energy to a thermodynamically consistent Gibbs free energy model, with thermodynamic responses following from temperature and pressure by automatic differentiation.
Open in Who Shared Issue with article?

Computer Science > Machine Learning

|
By José Miguel, Benjamin Kurt
| arXiv
Recent progress in flow-based generative modeling has led to models that output high-quality samples while using only a small number of function evaluations. However, at present, there is a lack of similar advances in estimating the model likelihood.
Open in Who Shared Issue with article?

[2603.06082] Offline Materials Optimization with CliqueFlowmer

|
By Jakub Grudzien, Benjamin Kurt
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (700) Issue with article?

[2509.23822] Space Group Conditional Flow Matching

|
By Benjamin Kurt
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (511) Issue with article?

Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching

|
By Benjamin Kurt, Ricky T. Q
| arXiv
[Submitted on 16 Apr 2025 ( v1 ), last revised 18 Apr 2025 (this version, v2)] Title:Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching Authors:Aaron Havens , Benjamin Kurt Miller , Bing Yan , Carles Domingo-Enrich , Anuroop Sriram , Brandon Wood , Daniel Levine , Bin Hu , Brandon Amos , Brian Karrer , Xiang Fu , Guan-Horng Liu , Ricky T. Q.
Open in Who Shared Issue with article?

All-atom Diffusion Transformers: Unified generative modelling of molecules and materials

|
By Benjamin Kurt
| arXiv
[Submitted on 5 Mar 2025] Title:All-atom Diffusion Transformers: Unified generative modelling of molecules and materials View a PDF of the paper titled All-atom Diffusion Transformers: Unified generative modelling of molecules and materials, by Chaitanya K. Joshi and 6 other authors View PDF HTML (experimental) Abstract:Diffusion models are the standard toolkit for generative modelling of 3D atomic systems.
Open in Who Shared Issue with article?

sbi reloaded: a toolkit for simulation-based inference workflows

|
By Benjamin Kurt, Faried Abu
| arXiv
Open in Who Shared Issue with article?

FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributions

|
By Benjamin Kurt, Ricky T. Q
| arXiv
Open in Who Shared Issue with article?

FlowMM: Generating Materials with Riemannian Flow Matching

|
By Benjamin Kurt, Ricky T. Q
| arXiv
Open in Who Shared Issue with article?

[2304.10978] Balancing Simulation-based Inference for Conservative Posteriors

|
By Benjamin Kurt
| arXiv
Conservative inference is a major concern in simulation-based inference. It has been shown that commonly used algorithms can produce overconfident posterior approximations. Balancing has empirically proven to be an effective way to mitigate this issue. However, its application remains limited to neural ratio estimation.
Open in Who Shared Issue with article?

CERN Document Server

|
By Benjamin Kurt
| cds.cern.ch
Report number arXiv:2007.02005 Title Finding symmetry breaking order parameters with Euclidean neural networks Author(s) Smidt, Tess E. (LBL, Berkeley ; LBL, Berkeley ; Tsinghua U., Beijing) ; Geiger, Mario (LBL, Berkeley ; CERN ; Ecole Polytechnique, Lausanne) ; Miller, Benjamin Kurt (LBL, Berkeley ; LBL, Berkeley ; Tsinghua U., Beijing ; Freie U., Berlin) Imprint 2020-07-04. - 6 p. Note 6 pages, 3 figures In: Phys. Rev. Res.
Open in Who Shared Issue with article?
Show More