Cornell researchers are demonstrating how artificial intelligence—particularly deep learning and generative modeling—can accelerate the design of new molecules and materials, and even function as an ...

A method to interpret artificial intelligence (AI) models used in materials discovery by analyzing their learned features has ...

For large language models (LLMs) like ChatGPT, accuracy often means complexity. To be able to make good predictions, ChatGPT must deeply understand the concepts and features that are associated with ...

Every year, more than 100 million animals are used globally in biomedical research, yet over 90% of drugs that appear effective in animal trials fail during human clinical testing. 1 This staggering ...

Scientists are exploring ways to mimic the origins of human life without two fundamental components: sperm and egg. They are coaxing clusters of stem cells – programmable cells that can transform into ...

AI language models, used to generate human-like text to power chatbots and create content, are also revolutionizing biology by treating complex biological data like a language. Language models are ...

Quantum decision-making models draw on mathematical principles of quantum theory to describe and predict choices that defy classical probability. By representing cognitive states as vectors in a ...

They could offer a more nuanced way to measure AI’s bias and its understanding of the world. New AI benchmarks could help developers reduce bias in AI models, potentially making them fairer and less ...

The use of AI models in scientific laboratories risks enabling dangerous experiments that could cause fires or explosions, researchers have warned. Such models offer a convincing illusion of ...