Related papers: The Open Catalyst 2020 (OC20) Dataset and Communit…
Tailored Pt nanoparticle catalysts are promising candidates to accelerate the oxygen reduction reaction (ORR) in fuel cells. However, the search for active nanoparticle catalysts is hindered by laborious effort of experimental synthesis and…
Despite long-standing efforts in accelerating scientific discovery with AI, building AI co-scientists remains challenging due to limited high-quality data for training and evaluation. To tackle this data scarcity issue, we present AutoSDT,…
Density functional theory (DFT) underpins modern atomistic simulations of transition-metal surfaces. It can predict key properties linked to catalytic performance, such as adsorption energies and barrier heights, enabling new paradigms in…
Accurately modeling chemical reactions at the atomistic level requires high-level electronic structure theory due to the presence of unpaired electrons and the need to properly describe bond breaking and making energetics. Commonly used…
Improving datacenter operations is vital for the digital society. We posit that doing so requires our community to shift, from operational aspects taken in isolation to holistic analysis of datacenter resources, energy, and workloads. In…
The conversion of natural gas (methane) to ethane and ethylene (OCM: oxidative coupling of methane) facilitates its transportation and provides a way to synthesize higher value chemicals. The search for high-performance catalysts to achieve…
Density Functional Theory (DFT) is a robust framework for modeling interacting many-body systems, including the equation of state (EoS) of dense matter. Many models, however, rely on energy functionals based on assumptions that have not…
Accurate potential energy surface (PES) descriptions are essential for atomistic simulations of materials. Universal machine learning interatomic potentials (UMLIPs)$^{1-3}$ offer a computationally efficient alternative to density…
One of the grand challenges in modern theoretical chemistry is designing and implementing approximations that expedite ab initio methods without loss of accuracy. Machine learning (ML), in particular neural networks, are emerging as a…
Object recognition is among the fundamental tasks in the computer vision applications, paving the path for all other image understanding operations. In every stage of progress in object recognition research, efforts have been made to…
Orbital-free density functional theory (OF-DFT) holds the promise to compute ground state molecular properties at minimal cost. However, it has been held back by our inability to compute the kinetic energy as a functional of the electron…
Photocatalytic water splitting has emerged as a sustainable pathway for hydrogen production, leveraging sunlight to drive chemical reactions. This review explores the integration of density functional theory (DFT) with machine learning (ML)…
Table Detection has become a fundamental task for visually rich document understanding with the surging number of electronic documents. However, popular public datasets widely used in related studies have inherent limitations, including…
We present the Open MatSci ML Toolkit: a flexible, self-contained, and scalable Python-based framework to apply deep learning models and methods on scientific data with a specific focus on materials science and the OpenCatalyst Dataset. Our…
Solving the AC optimal power flow problem (AC-OPF) is critical to the efficient and safe planning and operation of power grids. Small efficiency improvements in this domain have the potential to lead to billions of dollars of cost savings,…
The advancement of machine learning for compiler optimization, particularly within the polyhedral model, is constrained by the scarcity of large-scale, public performance datasets. This data bottleneck forces researchers to undertake costly…
We introduce gridfm-datakit-v1, a Python library for generating realistic and diverse Power Flow (PF) and Optimal Power Flow (OPF) datasets for training Machine Learning (ML) solvers. Existing datasets and libraries face three main…
Given the increasing complexity of omics datasets, a key challenge is not only improving classification performance but also enhancing the transparency and reliability of model decisions. Effective model performance and feature selection…
Machine Learning Interatomic Potentials (MLIPs) are a highly promising alternative to force-fields for molecular dynamics (MD) simulations, offering precise and rapid energy and force calculations. However, Quantum-Mechanical (QM) datasets,…
Transforming CO$_2$ into methanol represents a crucial step towards closing the carbon cycle, with thermoreduction technology nearing industrial application. However, obtaining high methanol yields and ensuring the stability of…