Publications related to Integrating symmetry and physical constraints into atomic-scale machine learning

Related publications (25)

Roadmap for Molecular Benchmarks in Nonadiabatic Dynamics

Simulating the coupled electronic and nuclear response of a molecule to light excitation requires the application of nonadiabatic molecular dynamics. However, when faced with a specific photophysical or photochemical problem, selecting the most suitable th ...

AMER CHEMICAL SOC2025

Non-Resonant Magnetic X-ray Scattering as a Probe of Ultrafast Molecular Spin-State Dynamics: An Ab Initio Theory

Zhaoheng Guo

With the advancement of high harmonic generation and X-ray free-electron lasers (XFELs) to the attosecond domain, the studies of the ultrafast electron and spin dynamics became possible. Yet, the methods for efficient control and measurement of the quantum ...

AMER CHEMICAL SOC2025

Robust and Personalized Federated Learning: Handling Data Corruption and Heterogeneity

Ljubomir Rokvic

Federated Learning (FL) has emerged as a transformative paradigm in machine learning, enabling collaborative model training across decentralized devices while preserving data privacy. However, FL's success is highly contingent on the quality and integrity ...

EPFL2025

Intelligent and Self-Driving Microscopy of Protein Aggregation in Neurodegenerative Diseases

Khalid Ashraf Mohie Ibrahim

Neurodegenerative diseases, such as Alzheimer's, Parkinson's, and Huntington's, afflict tens of millions of patients worldwide. They are characterized by protein aggregation and progressive neuronal loss, leading to cognitive and motor impairments, and ult ...

EPFL2025

Exploring Conformational Transitions in Biased and Balanced Ligand Binding of GLP-1R

Horst Arthur Vogel

The glucagon-like peptide-1 receptor (GLP-1R), which belongs to the class B1 G protein-coupled receptor (GPCR) family, is an important target for treatment of metabolic disorders, including type 2 diabetes and obesity. The growing interest in GLP-1R-based ...

MDPI AG2025

Graph Neural Networks With Adaptive Structures

Zepeng Zhang

Graph neural networks (GNNs) have made significant progress in various machine learning tasks. Despite their success, many existing GNN models are shown to be vulnerable to adversarial attacks, creating a stringent need to build robust GNN architectures. I ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2025

Adaptive Interface-Pinns (Adai-Pinns) for Transient Diffusion: Applications to Forward and Inverse Problems in Heterogeneous Media

Brice Tanguy Alphonse Lecampion

We model transient diffusion in heterogeneous materials using a novel physics-informed neural networks framework (PINNs) termed Adaptive interface physics-informed neural networks or AdaI-PINNs (Roy et al. arXiv preprint arXiv:2406.04626, 2024). AdaI-PINNs ...

Elsevier BV2025

Learning transferable land cover semantics for open vocabulary interactions with remote sensing images

Devis Tuia, Javiera Francisca Castillo Navarro, Valérie Zermatten

Why should we confine land cover classes to rigid and arbitrary definitions? Land cover mapping is a central task in remote sensing image processing, but the rigorous class definitions can sometimes restrict the transferability of annotations between datas ...

2025

NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability

Alexandre Massoud Alahi, Krishna Kanth Nakka

The generation of transferable adversarial perturbations typically involves training a generator to maximize embedding separation between clean and adversarial images at a single mid-layer of a source model. In this work, we build on this approach and intr ...

IEEE2025

Modeling the ferroelectric phase transition in barium titanate with DFT accuracy and converged sampling

Michele Ceriotti, Alexander Jan Goscinski, Lorenzo Gigli

The accurate description of the structural and thermodynamic properties of ferroelectrics has been one of the most remarkable achievements of density functional theory (DFT). However, running large simulation cells with DFT is computationally demanding, wh ...

2024

Machine learning potential for the Cu-W system

William Curtin

Combining the excellent thermal and electrical properties of Cu with the high abrasion resistance and thermal stability of W, Cu-W nanoparticle-reinforced metal matrix composites and nano-multilayers are finding applications as brazing fillers and shieldin ...

2024

Giant Splitting of the Hydrogen Rotational Eigenenergies in the C2 Filled Ice

Richard Gaal

Hydrogen hydrates exhibit a rich phase diagram influenced by both pressure and temperature, with the so-called C2 phase emerging prominently above 2.5 GPa. In this phase, hydrogen molecules are densely packed within a cubic icelike lattice and the interact ...

2024

Quantum Variational Algorithms: Exploring Applications and Potentials Amid Trainability and Classical Simulability Limitations

Su Yeon Chang

Since its proposal, quantum computing has made significant strides in various domains. Among the different emerging techniques, Variational Quantum Algorithms (VQAs) have become one of the most promising approaches in the current era, where quantum computa ...

EPFL2024

Constrained Zero-Shot Neural Architecture Search on Small Classification Dataset

Liza Carol Andrea Dunbar

The rapid evolution of Deep Learning (DL) has brought about significant transformations across scientific domains, marked by the development of increasingly intricate models demanding powerful GPU platforms. However, edge applications like wearables and mo ...

IEEE2024

Bridging Discrete Choice Modeling and Neural Networks: Unifying Statistical Rigor and Predictive Power

Brian Alan Tappy-Sifringer

This thesis explores the innovative integration of Discrete Choice Modeling (DCM) and Machine Learning (ML), specifically Neural Networks (NN), within the transportation sector. DCM, with its highly interpretable and hand-designed models grounded in robust ...

EPFL2024

Distributed Machine Learning Targeting Embedded Systems for Epilepsy Detection

Saleh Baghersalimi

Epileptic seizure detection and monitoring is critical in healthcare, particularly for individuals requiring continuous oversight. Current methods, primarily based on electroencephalogram (EEG) technologies, face limitations due to their complexity in term ...

EPFL2024

A hybrid tau-leap for simulating chemical kinetics with applications to parameter estimation

Thomas Simon Spencer Trigo Trindade

We consider the problem of efficiently simulating stochastic models of chemical kinetics. The Gillespie stochastic simulation algorithm (SSA) is often used to simulate these models; however, in many scenarios of interest, the computational cost quickly bec ...

2024

Single vibronic level fluorescence spectra from Hagedorn wavepacket dynamics

Jiri Vanicek, Zhan Tong Zhang

In single vibronic level (SVL) fluorescence experiments, the electronically excited initial state is also excited in one or several vibrational modes. Because computing such spectra by evaluating all contributing Franck–Condon factors becomes impractical ( ...

AIP Publishing2024

PyTorch 2 Model for the prediction of single-artery segmentations for "AngioPy segmentation: An open-source, user-guided deep learning tool for coronary artery segmentation"

Edward Carlo Giorgio Andò, Thabodhan Mahendiran

These are pytorch model weights for the angiopy-segmentation deep learning model, descriped in a paper published in 2024 in the International Journal of Cardiology: AngioPy segmentation: An open-source, user-guided deep learning tool for coronary artery se ...

Zenodo2024

Bootstrapping Autonomous Driving Radars with Self-Supervised Learning

Haitham Al Hassanieh, Junfeng Guan

The perception of autonomous vehicles using radars has attracted increased research interest due its ability to operate in fog and bad weather. However, training radar models is hindered by the cost and difficulty of annotating largescale radar data. To ov ...

IEEE2024