Imagen de Portada

Pretrained Model Representations as Acquisition Signals for Active Learning of MLIPs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Varga-Umbrich, Eszter, Surana, Shikha, Duckworth, Paul, Tilly, Jules, Peltre, Olivier, Weller-Davies, Zachary
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Chemical Physics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs
por: Varga-Umbrich, Eszter, et al.
Publicado: (2026)

Machine Learning Interatomic Potentials: Advancing Open-Source Software for Efficient and Scalable Molecular Simulation
por: Brunken, Christoph, et al.
Publicado: (2026)

Integral Formulas for Vector Spherical Tensor Products
por: Heyraud, Valentin, et al.
Publicado: (2026)

Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs
por: Neporozhnii, Ihor, et al.
Publicado: (2026)

Better without U: Impact of Selective Hubbard U Correction on Foundational MLIPs
por: Warford, Thomas, et al.
Publicado: (2026)

CrystalREPA: Transferring Physical Priors from Universal MLIPs to Crystal Generative Models
por: Zhang, Chengqian, et al.
Publicado: (2026)

An Equivariant Pretrained Transformer for Unified 3D Molecular Representation Learning
por: Jiao, Rui, et al.
Publicado: (2024)

BoostMD: Accelerating molecular sampling by leveraging ML force field features from previous time-steps
por: Schaaf, Lars L., et al.
Publicado: (2024)

A recipe for scalable attention-based MLIPs: unlocking long-range accuracy with all-to-all node attention
por: Qu, Eric, et al.
Publicado: (2026)

Overconfident Oracles: Limitations of In Silico Sequence Design Benchmarking
por: Surana, Shikha, et al.
Publicado: (2025)

Pretraining Strategy for Neural Potentials
por: Zhang, Zehua, et al.
Publicado: (2024)

Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations
por: Schopmans, Henrik, et al.
Publicado: (2024)

Active Causal Learning for Decoding Chemical Complexities with Targeted Interventions
por: Fox, Zachary R., et al.
Publicado: (2024)

Metalic: Meta-Learning In-Context with Protein Language Models
por: Beck, Jacob, et al.
Publicado: (2024)

Transfer Learning across Different Chemical Domains: Virtual Screening of Organic Materials with Deep Learning Models Pretrained on Small Molecule and Chemical Reaction Data
por: Zhang, Chengwei, et al.
Publicado: (2023)

Machine Learning Interatomic Potentials: library for efficient training, model development and simulation of molecular systems
por: Brunken, Christoph, et al.
Publicado: (2025)

Active Learning Enables Extrapolation in Molecular Generative Models
por: Antoniuk, Evan R., et al.
Publicado: (2025)

MUBen: Benchmarking the Uncertainty of Molecular Representation Models
por: Li, Yinghao, et al.
Publicado: (2023)

Learning Non-Local Molecular Interactions via Equivariant Local Representations and Charge Equilibration
por: Fuchs, Paul, et al.
Publicado: (2025)

Advancing Molecular Machine Learning Representations with Stereoelectronics-Infused Molecular Graphs
por: Boiko, Daniil A., et al.
Publicado: (2024)

ChemFlow:A Hierarchical Neural Network for Multiscale Representation Learning in Chemical Mixtures
por: Fan, Jinming, et al.
Publicado: (2026)

OrbitAll: A Unified Quantum Mechanical Representation Deep Learning Framework for All Molecular Systems
por: Kang, Beom Seok, et al.
Publicado: (2025)

Completeness of Atomic Structure Representations
por: Nigam, Jigyasa, et al.
Publicado: (2023)

Toward Routine CSP of Pharmaceuticals: A Fully Automated Protocol Using Neural Network Potentials
por: Glick, Zachary L., et al.
Publicado: (2025)

Implicit Neural Representations for Chemical Reaction Paths
por: Ramakrishnan, Kalyan, et al.
Publicado: (2025)

Adapting OC20-trained EquiformerV2 Models for High-Entropy Materials
por: Clausen, Christian M., et al.
Publicado: (2024)

FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentials
por: Plé, Thomas, et al.
Publicado: (2024)

Active Learning in Symbolic Regression with Physical Constraints
por: Medina, Jorge, et al.
Publicado: (2023)

LFaB: Low fidelity as Bias for Active Learning in the chemical configuration space
por: Vinod, Vivin, et al.
Publicado: (2025)

Nutmeg and SPICE: Models and Data for Biomolecular Machine Learning
por: Eastman, Peter, et al.
Publicado: (2024)

Meta-Learning Linear Models for Molecular Property Prediction
por: Pimonova, Yulia, et al.
Publicado: (2025)

Two-Stage Pretraining for Molecular Property Prediction in the Wild
por: Wijaya, Kevin Tirta, et al.
Publicado: (2024)

Deep Learning Foundation Models from Classical Molecular Descriptors
por: Burns, Jackson W., et al.
Publicado: (2025)

How False Data Affects Machine Learning Models in Electrochemistry?
por: Deshsorna, Krittapong, et al.
Publicado: (2023)

Lightweight Geometric Deep Learning for Molecular Modelling in Catalyst Discovery
por: Geitner, Patrick
Publicado: (2024)

chemtrain: Learning Deep Potential Models via Automatic Differentiation and Statistical Physics
por: Fuchs, Paul, et al.
Publicado: (2024)

Faster Molecular Dynamics with Neural Network Potentials via Distilled Multiple Time-Stepping and Non-Conservative Forces
por: Gouraud, Nicolaï, et al.
Publicado: (2026)

MolFusion: Multimodal Fusion Learning for Molecular Representations via Multi-granularity Views
por: Cai, Muzhen, et al.
Publicado: (2024)

Clever Hans in Chemistry: Chemist Style Signals Confound Activity Prediction on Public Benchmarks
por: Blevins, Andrew D., et al.
Publicado: (2025)

FastCSP: Accelerated Molecular Crystal Structure Prediction with Universal Model for Atoms
por: Gharakhanyan, Vahe, et al.
Publicado: (2025)