Cover Image

Broken neural scaling laws in materials science

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Großmann, Max, Grunert, Malte, Runge, Erich
Format:	Preprint
Published:	2026
Subjects:	Materials Science Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Discovery of sustainable energy materials via the machine-learned material space
by: Grunert, Malte, et al.
Published: (2025)

Deep learning of spectra: Predicting the dielectric function of semiconductors
by: Grunert, Malte, et al.
Published: (2024)

Many-body perturbation theory vs. density functional theory: A systematic benchmark for band gaps of solids
by: Großmann, Max, et al.
Published: (2025)

High-throughput screening and mechanistic insights into solid acid proton conductors
by: Hänseroth, Jonas, et al.
Published: (2026)

Discovery of Sustainable Energy Materials Via the Machine‐Learned Material Space
by: Malte Grunert, et al.
Published: (2025)

Modelling complex proton transport phenomena -- Exploring the limits of fine-tuning and transferability of foundational machine-learned force fields
by: Grunert, Malte, et al.
Published: (2025)

Lessons from the trenches on evaluating machine-learning systems in materials science
by: Alampara, Nawaf, et al.
Published: (2025)

Real-time experiment-theory closed-loop interaction for autonomous materials science
by: Liang, Haotong, et al.
Published: (2024)

Bayesian neural networks for predicting uncertainty in full-field material response
by: Pasparakis, George D., et al.
Published: (2024)

Towards an automated workflow in materials science for combining multi-modal simulative and experimental information using data mining and large language models
by: Katzer, Balduin, et al.
Published: (2025)

General time-reversal equivariant neural network potential for magnetic materials
by: Yu, Hongyu, et al.
Published: (2022)

Consistent machine learning for topology optimization with microstructure-dependent neural network material models
by: Vijayakumaran, Harikrishnan, et al.
Published: (2024)

On the origin of bulk-related anisotropies in surface optical spectra
by: Großmann, Max, et al.
Published: (2025)

A comparative study of transformer models and recurrent neural networks for path-dependent composite materials
by: Uvdal, Petter, et al.
Published: (2026)

Physically recurrent neural network for rate and path-dependent heterogeneous materials in a finite strain framework
by: Maia, M. A., et al.
Published: (2024)

Advancing atomic electron tomography with neural networks
by: Lee, Juhyeok, et al.
Published: (2025)

Machine-learned models for magnetic materials
by: Leszczyński, Paweł, et al.
Published: (2023)

Symmetry-enforcing neural networks with applications to constitutive modeling
by: Garanger, Kévin, et al.
Published: (2023)

Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science
by: Cheng, Austin, et al.
Published: (2024)

Leveraging neural network interatomic potentials for a foundation model of chemistry
by: Kim, So Yeon, et al.
Published: (2025)

Differentiable neural network representation of multi-well, locally-convex potentials
by: Jones, Reese E., et al.
Published: (2025)

Recurrent neural networks and transfer learning for elasto-plasticity in woven composites
by: Ghane, Ehsan, et al.
Published: (2023)

Machine learning for structure-guided materials and process design
by: Morand, Lukas, et al.
Published: (2023)

Symbolic regression for defect interactions in 2D materials
by: Lazarev, Mikhail, et al.
Published: (2025)

AI-driven materials design: a mini-review
by: Cheng, Mouyang, et al.
Published: (2025)

Machine learning driven search of hydrogen storage materials
by: Banerjee, Tanumoy, et al.
Published: (2025)

Probing the limitations of multimodal language models for chemistry and materials research
by: Alampara, Nawaf, et al.
Published: (2024)

Equivariant graph convolutional neural networks for the representation of homogenized anisotropic microstructural mechanical response
by: Patel, Ravi, et al.
Published: (2024)

Contrast transfer functions help quantify neural network out-of-distribution generalization in HRTEM
by: DaCosta, Luis Rangel, et al.
Published: (2025)

Machine learning assisted screening of metal binary alloys for anode materials
by: Shi, Xingyue, et al.
Published: (2024)

Accurate, transferable, and verifiable machine-learned interatomic potentials for layered materials
by: Georgaras, Johnathan D., et al.
Published: (2025)

Unleashing the power of novel conditional generative approaches for new materials discovery
by: Novitskiy, Lev, et al.
Published: (2024)

Gradient-based grand canonical optimization enabled by graph neural networks with fractional atomic existence
by: Christiansen, Mads-Peter Verner, et al.
Published: (2025)

Structural and mechanical properties of W-Cu compounds characterized by a neural-network-based potential
by: Liu, Jianchuan, et al.
Published: (2025)

Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability
by: Gouvêa, Rogério Almeida, et al.
Published: (2025)

Assessing data-driven predictions of band gap and electrical conductivity for transparent conducting materials
by: Ottomano, Federico, et al.
Published: (2024)

Structure-based out-of-distribution (OOD) materials property prediction: a benchmark study
by: Omee, Sadman Sadeed, et al.
Published: (2024)

Out-of-distribution materials property prediction using adversarial learning based fine-tuning
by: Li, Qinyang, et al.
Published: (2024)

Establishing Deep InfoMax as an effective self-supervised learning methodology in materials informatics
by: Moran, Michael, et al.
Published: (2024)

DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules
by: Du, Hongwei, et al.
Published: (2025)