Imagen de Portada

Open Materials Generation with Inference-Time Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hoellmer, Philipp, Martiniani, Stefano
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Materials Science
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Open Materials Generation with Stochastic Interpolants
por: Hoellmer, Philipp, et al.
Publicado: (2025)

All that structure matches does not glitter
por: Martirossyan, Maya M., et al.
Publicado: (2025)

MolCrystalFlow: Molecular Crystal Structure Prediction via Flow Matching
por: Zeng, Cheng, et al.
Publicado: (2026)

Transport Novelty Distance: A Distributional Metric for Evaluating Material Generative Models
por: Hagemann, Paul, et al.
Publicado: (2025)

AMShortcut: An Inference- and Training-Efficient Inverse Design Model for Amorphous Materials
por: Lin, Yan, et al.
Publicado: (2026)

Generative Models for Crystalline Materials
por: Metni, Houssam, et al.
Publicado: (2025)

Materium: An Autoregressive Approach for Material Generation
por: Dobberstein, Niklas, et al.
Publicado: (2025)

DMFlow: Disordered Materials Generation by Flow Matching
por: Wu, Liming, et al.
Publicado: (2026)

Reinforcement Fine-Tuning for Materials Design
por: Cao, Zhendong, et al.
Publicado: (2025)

Generating Symmetric Materials using Latent Flow Matching
por: Karmush, Anmar, et al.
Publicado: (2026)

VAE for Modified 1-Hot Generative Materials Modeling, A Step Towards Inverse Material Design
por: El-Awady, Khalid
Publicado: (2023)

Efficient Symmetry-Aware Materials Generation via Hierarchical Generative Flow Networks
por: Nguyen, Tri Minh, et al.
Publicado: (2024)

Machine Learning - Driven Materials Discovery: Unlocking Next-Generation Functional Materials - A review
por: Nematov, Dilshod, et al.
Publicado: (2025)

AIMatDesign: Knowledge-Augmented Reinforcement Learning for Inverse Materials Design under Data Scarcity
por: Yu, Yeyong, et al.
Publicado: (2025)

Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation
por: Yan, Keqiang, et al.
Publicado: (2025)

Enhancing Materials Discovery with Valence Constrained Design in Generative Modeling
por: Cheng, Mouyang, et al.
Publicado: (2025)

Semantic Embeddings of Chemical Elements for Enhanced Materials Inference and Discovery
por: Jia, Yunze, et al.
Publicado: (2025)

Structural Constraint Integration in Generative Model for Discovery of Quantum Material Candidates
por: Okabe, Ryotaro, et al.
Publicado: (2024)

Fine-Tuned Language Models Generate Stable Inorganic Materials as Text
por: Gruver, Nate, et al.
Publicado: (2024)

Inverse Materials Design by Large Language Model-Assisted Generative Framework
por: Hao, Yun, et al.
Publicado: (2025)

Periodic Materials Generation using Text-Guided Joint Diffusion Model
por: Das, Kishalay, et al.
Publicado: (2025)

Learning ORDER-Aware Multimodal Representations for Composite Materials Design
por: Li, Xinyao, et al.
Publicado: (2026)

A Critical Examination of Active Learning Workflows in Materials Science
por: Nair, Akhil S., et al.
Publicado: (2026)

A Materials Map Integrating Experimental and Computational Data via Graph-Based Machine Learning for Enhanced Materials Discovery
por: Hashimoto, Yusuke, et al.
Publicado: (2025)

Learning Physics-Consistent Material Behavior from Dynamic Displacements
por: Han, Zhichao, et al.
Publicado: (2024)

Multi-Task Multi-Fidelity Learning of Properties for Energetic Materials
por: Appleton, Robert J., et al.
Publicado: (2024)

Generative Inversion for Property-Targeted Materials Design: Application to Shape Memory Alloys
por: Li, Cheng, et al.
Publicado: (2025)

Learning Magnetic Order Classification from Large-Scale Materials Databases
por: Fahmy, Ahmed E.
Publicado: (2025)

Composite Material Design for Optimized Fracture Toughness Using Machine Learning
por: Jahromi, Mohammad Naqizadeh, et al.
Publicado: (2024)

Toward Multi-Fidelity Machine Learning Force Field for Cathode Materials
por: Dong, Guangyi, et al.
Publicado: (2025)

UniMat: Unifying Materials Embeddings through Multi-modal Learning
por: Ock, Janghoon, et al.
Publicado: (2024)

Boltzmann Reinforcement Learning for Noise resilience in Analog Ising Machines
por: Choudhary, Aditya, et al.
Publicado: (2026)

Foundation-Model Surrogates Enable Data-Efficient Active Learning for Materials Discovery
por: Hu, Jeffrey, et al.
Publicado: (2026)

Bridging Text and Crystal Structures: Literature-driven Contrastive Learning for Materials Science
por: Suzuki, Yuta, et al.
Publicado: (2025)

Training-Free Active Learning Framework in Materials Science with Large Language Models
por: Wang, Hongchen, et al.
Publicado: (2025)

MoMa: A Modular Deep Learning Framework for Material Property Prediction
por: Wang, Botian, et al.
Publicado: (2025)

Efficient and Accurate Spatial Mixing of Machine Learned Interatomic Potentials for Materials Science
por: Birks, Fraser, et al.
Publicado: (2025)

Extended Low-Rank Approximation Accelerates Learning of Elastic Response in Heterogeneous Materials
por: Karmakar, Prabhat, et al.
Publicado: (2025)

Materials Learning Algorithms (MALA): Scalable Machine Learning for Electronic Structure Calculations in Large-Scale Atomistic Simulations
por: Cangi, Attila, et al.
Publicado: (2024)

Accelerating the Training and Improving the Reliability of Machine-Learned Interatomic Potentials for Strongly Anharmonic Materials through Active Learning
por: Kang, Kisung, et al.
Publicado: (2024)