Mace
PulseAugur coverage of Mace — every cluster mentioning Mace across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
LLM agents struggle with multi-agent exploration, new research finds
A new research paper published on arXiv explores the limitations of current Large Language Model (LLM) agents in multi-agent exploration scenarios. The study reveals that these agents often exhibit myopic and polarized …
-
New method extracts electrostatics from AI potentials
Researchers have developed a method called Latent Ewald Summation (LES) to extract electrostatic properties from foundation machine learning interatomic potentials (MLIPs). This technique allows for the creation of more…
-
New methods boost accuracy of interatomic potential models
Researchers have developed novel methods, Physics-Aware Neighborhood (PAN) pooling and Physics-Guided Spectral (PGS) mixers, to enhance the accuracy of short-range equivariant interatomic potentials. These techniques fo…
-
New Framework Aligns CT and EHR Data for Improved Time-to-Event Prediction
Researchers have developed a new framework for cross-modal representation alignment to improve time-to-event (TTE) prediction using both CT imaging and longitudinal electronic health records (EHR). This foundation model…
-
New ML dataset accelerates catalysis research in 2D MXenes
Researchers have developed a new benchmark dataset and machine learning models to accelerate the study of catalysis in 2D MXenes. By combining density functional theory calculations with machine learning interatomic pot…
-
New MLIP methods improve accuracy and automate research
Researchers are developing advanced machine learning interatomic potentials (MLIPs) to improve atomistic simulations. New methods like Stein Kernelized Molecular Dynamics (SKMD) enhance data acquisition for active learn…
-
New MuSE Model Accurately Captures Multiscale Interactions in Physics
Researchers have introduced the Multiscale Structural Ensemble (MuSE), a novel hierarchical model designed to address the challenge of predicting emergent interactions across multiple scales in physical systems. Unlike …
-
New kernels from pretrained MACE potentials improve active learning for MLIPs
Researchers have developed a new method for active learning in machine learning interatomic potentials (MLIPs) by utilizing pretrained model representations. This approach leverages the latent space of a pretrained MACE…
-
Machine learning potentials struggle to predict silica glass structure
Researchers have investigated the limitations of machine learning potentials in accurately predicting the medium-range order of silica glass. Using neutron and X-ray diffraction alongside molecular dynamics, they found …