Category: Data & Computing
-
Letting atomic simulations learn from phase diagrams
Ten times more efficient than previous methods, a new machine learning method builds a two-way connection between atomic simulation and experimental data.
-
Interpretable machine learning to accelerate nanocatalyst discovery
A fast and accurate surrogate model screens over 10,000 possible metal-oxide supports for a platinum nanocatalyst to prevent sintering under high temperatures.
-
Large language models and research progress: A Q&A with Ricardo Vinuesa
Guidelines for responsible LLM use to help, not hinder, research progress.
-
AI for studying turbulence: A fresh look at an unsolved physics problem
Explainable AI helps find key drivers of turbulence, offering new insights that could improve flight safety and industrial efficiency.
-
Faster commutes in Oakland County—rollout underway for U-M-designed traffic flow system
Harnessing vehicle GPS data, the system offers a cost-efficient alternative to conventional timed signals.
-
Hurricane outages: analysis details the where, and who, of increased future power cuts
A new analytical tool from U-M provides guidance for municipal and emergency planning.
-
This digital hand enables hands-free virtual reality
More than just a stand-in, the AI-powered agent can complete tasks by following simple voice commands that don’t include nitty-gritty details.
-
U-M quantum testbed enables remote experiments
The optical fibers connecting two quantum research labs at the University of Michigan mark the first piece of a local quantum network and remote user test facility.
-
Quantum chemistry: Making key simulation approach more accurate
Density functional theory is limited by a mystery at its heart: the universal exchange-correlation functional. U-M researchers are trying to uncover it.
-
$19.4M for an ‘AI oracle’ to solve complex physics problems
U-Michigan leads new DOE-funded computational center focused on next-generation hypersonic flight.
-
AI system discovers visual categories while adapting to new contexts
Open ad-hoc categorization approach combines language guidance with visual clustering to learn contextualized features for flexible image interpretation.
-
AI leaderboards can be trustworthy by following these tips
Methods for ranking chess players and athletes don’t always translate to AI. U-M researchers identify and outline best practices.