AI for molecular simulations may not need built-in physics to deliver strong results

Simulating how atoms and molecules move over time is a central challenge in computational chemistry and materials science.
Brown University

Do AI language models ‘understand’ the real world? On a basic level, they do, a new study finds

New research shows that AI language models can develop a mathematical “understanding” that differentiates between events that ...

Engineers develop a new system to track material design processes

Discovering and characterizing new materials is important for unlocking advances in fields like clean energy, advanced ...
IEEE

Hybrid Modeling Approach Combining Analytical and Neural Ordinary Differential Equations for Accelerated Simulation of Grid-Tied Inverter

Abstract: Fine solving time step is commonly required in the simulation of grid-tied inverters due to the fast inner-loop control and high-frequency switching behavior. However, the dynamics of the ...
Tech Xplore

Teaching AI models to say 'I'm not sure' in cases of calibration errors

Confidence is persuasive. In artificial intelligence systems, it is often misleading. Today's most capable reasoning models ...
MIT Technology Review

World models

Today’s AI is still unreliable. Some researchers think solving that problem requires teaching AI systems to understand the world around them.
Tech Xplore

Tag-teaming turbulence: Frontier supercomputer trains AI to model cosmic storms

Researchers used the world's fastest supercomputer for open science to train an artificial intelligence model that captures ...
IEEE

Using Distributed Simulation Capabilities to Support Studies and Mission Operations for NASA Artemis Program

Abstract: The National Aeronautics and Space Administration (NASA) established the Artemis Program, a series of missions to return humans to the Moon and explore further than before To execute the ...