New technique helps robots pack objects into a tight space
Researchers coaxed a family of generative AI models to work together to solve multistep robot manipulation problems.
MIT-IBM Watson AI Lab
A more effective experimental design for engineering a cell into a new state
By focusing on causal relationships in genome regulation, a new AI method could help scientists identify new immunotherapy techniques or regenerative therapies.
How machine-learning models can amplify inequities in medical diagnosis and treatment
MIT researchers investigate the causes of health care disparities among underrepresented groups.
AI models are powerful, but are they biologically plausible?
A new study bridging neuroscience and machine learning offers insights into the potential role of astrocytes in the human brain.
New quantum magnet unleashes electronics potential
Researchers discover how to control the anomalous Hall effect and Berry curvature to create flexible quantum magnets for use in computers, robotics, and sensors.
Statistics, operations research, and better algorithms
MIT Sloan Associate Professor Rahul Mazumder finds ways to create and refine statistical models with an array of applications.
Learning the language of molecules to predict their properties
This AI system only needs a small amount of data to predict molecular properties, which could speed up drug discovery and material development.
When computer vision works more like a brain, it sees more like people do
Training artificial neural networks with data from real brains can make computer vision more robust.
Computer vision system marries image recognition and generation
MAGE merges the two key tasks of image generation and recognition, typically trained separately, into a single system.
MIT researchers make language models scalable self-learners
The scientists used a natural language-based logical inference dataset to create smaller language models that outperformed much larger counterparts.
Scaling audio-visual learning without labels
A new multimodal technique blends major self-supervised learning methods to learn more similarly to humans.
Computational model mimics humans’ ability to predict emotions
Using insights into how people intuit others’ emotions, researchers have designed a model that approximates this aspect of human social intelligence.
New tool helps people choose the right method for evaluating AI models
Selecting the right method gives users a more accurate picture of how their model is behaving, so they are better equipped to correctly interpret its predictions.
Helping robots handle fluids
Researchers create a new simulation tool for robots to manipulate complex fluids in a step toward helping them more effortlessly assist with daily tasks.
Open-source platform simulates wildlife for soft robotics designers
SoftZoo is a soft robot co-design platform that can test optimal shapes and sizes for robotic performance in different environments.