discovery · Source published 2024-12-04
Forecasting more than one future.
GenCast used machine learning to generate ensembles of possible weather outcomes up to 15 days ahead.
Find your way in.
268 items: records, experiences, guides and model families. Source reports remain distinct from discoveries.
discovery · Source published 2022-03-09
Listening to the ancient world.
Historians working with Ithaca improved the restoration of damaged ancient Greek inscriptions.
discovery · Source published 2023-11-14
A faster view of the weather.
GraphCast produced skillful medium-range global weather forecasts using a learned model.
discovery · Source published 2023-07-05
Weather in three dimensions.
Pangu-Weather demonstrated medium-range forecasting with three-dimensional neural networks.
discovery · Source published 2024-07-22
Physics meets learning.
NeuralGCM combined atmospheric physics with machine learning for weather and climate modeling.
discovery · Source published 2025-02-25
From research to the forecast desk.
ECMWF brought its Artificial Intelligence Forecasting System into operational service.
discovery · Source published 2024-05-08
Seeing molecules together.
AlphaFold 3 expanded structural prediction to complexes of proteins and other biomolecules.
discovery · Source published 2021-07-22
A broader map of human proteins.
Researchers applied AlphaFold to a broad collection of human proteins.
discovery · Source published 2022-02-16
Holding a plasma in shape.
Researchers used reinforcement learning to control magnetic confinement in a research tokamak.
discovery · Source published 2023-12-14
New paths through mathematics.
FunSearch combined language models with program evaluation to discover mathematical constructions.
discovery · Source published 2018-08-13
Helping specialists see urgency.
Researchers demonstrated deep-learning diagnosis and referral recommendations from retinal scans.
discovery · Source published 2023-05-24
Reconnecting intention and movement.
A brain–spine interface enabled a participant with spinal cord injury to control standing and walking.
discovery · Source published 2023-12-20
Looking for new antibiotic families.
Researchers used explainable deep learning to identify a structural class of antibiotic candidates.
discovery · Source published 2023-11-29
Searching the space of materials.
GNoME used graph networks to search for energetically favorable crystal structures.
discovery · Source published 2022-04-27
An enzyme for a plastic problem.
Scientists used machine learning to help engineer an enzyme that breaks down PET plastic.
discovery · Source published 2023-07-11
Designing proteins with purpose.
RFdiffusion enabled researchers to generate proteins with specified structural and functional goals.
discovery · Source published 2026-06-15
A voice in everyday life.
Casey Harrell used a brain–computer interface at home to communicate and operate his computer without researchers present.
discovery · Source published 2024-06-13
Teaching a robot from demonstrations
OpenVLA gives robotics teams a pretrained vision-language-action model plus instructions for fine-tuning it on their own robot demonstrations.
discovery · Source published 2026-04-18
A shared starting point for humanoid skills
Isaac GR00T N1.7 is a downloadable vision-language-action model intended as a base for developing humanoid robot skills.
discovery · Source published 2023-03-16
Predicting a protein’s shape from its sequence
ESMFold applies a protein language model to infer three-dimensional structure directly from an amino-acid sequence, with checkpoints and bulk prediction tools available to researchers.