New research demonstrates how training deep learning models with a focus on image robustness can overcome technical variations in histopathology, paving the way for more consistent and trustworthy diagnostic tools.
New research reveals that self-propelled particles within liquid crystals can transition from orderly movement to unpredictable, chaotic behavior through dynamic interactions.
![This computational pipeline leverages machine learning to efficiently calculate electron-phonon interactions in materials, employing density functional theory to generate training data for neural networks that predict interatomic forces and electronic Hamiltonians, ultimately enabling Monte Carlo sampling and the inference of key physical quantities related to material behavior-a process schematically represented by structural perturbations around equilibrium configurations [latex]\Delta\sigma[/latex].](https://arxiv.org/html/2602.23084v1/2602.23084v1/x1.png)
A new machine learning framework dramatically speeds up the calculation of how electrons interact with atomic vibrations in complex materials.
New research reveals the key strategies teams are using to maintain productivity and collaboration when working both remotely and in the office.
A new approach to testing vision-language models in robotics reveals hidden behavioral flaws that traditional methods often miss.
A flexible new framework, FlexMS, is enabling rigorous evaluation of deep learning methods for predicting mass spectra, paving the way for more accurate molecular identification.
Researchers introduce a comprehensive evaluation of robotic systems that translate natural language into physical actions, revealing the challenges and opportunities for more intuitive robot control.
Researchers have developed a new foundation model capable of understanding and generating complex 3D structures for both molecules and materials.
A new algorithm efficiently combines data from multiple sensors to reliably track stationary objects, even in complex environments.
A rigorous mathematical framework originally developed to understand magnetic materials is now proving surprisingly powerful in fields like computer science and statistical learning.