AI Framework Predicts Alloy Behavior Even for Elements It's Never Seen
Researchers combine LLM-extracted knowledge with experimental data using Dempster-Shafer theory, achieving 86-92% accuracy on unstudied compositions.
Tag
#machine-learning
An AI System Just Published Research in Nature After Passing Peer Review
Sakana AI's 'AI Scientist' generated a paper that scored higher than 55% of human submissions at ICLR 2025
NOAA's AI Weather Models Cut Computing by 99% While Improving Forecasts
New AIGFS system delivers 16-day forecasts in 40 minutes using 0.3% of traditional computing resources
A School District Tried to Help Train Waymo's Robots to Stop for School Buses. It Didn't Work.
Austin ISD offered real-world training data. Three software fixes later, the robotaxis still can't reliably stop when children are boarding.
AI Transformers Now Forecasting Seasonal Climate
New framework combines deep learning with climate models to predict temperature and rainfall months ahead, outperforming traditional methods in some regions.
AI Finds Promising Drugs for Liver Cancer and Lung Fibrosis
Michigan State researchers use machine learning to predict gene effects from chemical structures, identifying compounds that reduced tumors in mice.
ICML Rejects 497 Papers After Catching Reviewers Using AI Through Hidden Watermarks
The world's top machine learning conference used a clever watermarking trick to detect researchers using LLMs to write peer reviews, then desk-rejected their papers as punishment.
AI 'Laser Tag' Validates 100-Year-Old Theory of How Cancer Begins
EMBL scientists use AI to spot the earliest markers of chromosomal chaos in cells, finding one in ten divisions produces errors that can seed tumors.
NOAA's AI Weather Models Go Operational, Use 99% Less Computing Power
Three new AI-driven forecast systems dramatically cut energy costs while extending prediction accuracy
AI Predicts Cancer Spread With 80% Accuracy Across Multiple Tumor Types
University of Geneva's MangroveGS uses gene signatures to forecast metastasis risk, potentially sparing low-risk patients from aggressive treatment
NIH Scientists Used AI to Find 307 Drug Combinations That Kill Pancreatic Cancer Cells
Machine learning models screened 1.6 million potential drug pairings and identified synergistic combinations that neither drug achieves alone. Lab tests confirmed the predictions work.
Machine Learning Finds Hidden Signal That Could Accelerate Solid-State Battery Discovery
TUM researchers developed an AI pipeline that predicts Raman spectra to identify superionic materials, potentially cutting years off battery development timelines
The Geometry of Thinking: How Scientists Mapped What Happens Inside an AI's Mind
Researchers found that AI systems organize knowledge on curved surfaces with measurable geometric signatures - revealing when models truly understand language.
AI Chatbots Analyzed Medical Data Faster Than Human Teams, UCSF Study Finds
Half of the tested AI tools produced prediction models that matched or beat human researchers. A master's student and high schooler built working code in minutes.
AI Discovers 25 New Magnetic Materials That Could Replace Rare Earths in EVs
University of New Hampshire researchers built an AI system that read thousands of papers and identified high-temperature magnets for electric vehicles and clean energy.
AI Chatbots Analyze Pregnancy Data Faster Than Human Research Teams
UCSF study finds generative AI can build prediction models in minutes that took human teams months, though only half the tested systems worked.