Technique enables AI on edge devices to keep learning over time
With the PockEngine training method, machine-learning models can efficiently and continuously learn from user data on edge devices like smartphones.
MIT-IBM Watson AI Lab
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.
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.
Learning the language of molecules to predict their properties
Discovering new materials and drugs typically involves a manual, trial-and-error process that can take decades and cost millions of dollars. To streamline this process, scientists often use machine learning to…
When computer vision works more like a brain, it sees more like people do
From cameras to self-driving cars, many of today’s technologies depend on artificial intelligence to extract meaning from visual information. Today’s AI technology has artificial neural networks at its core, and…
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.
Scaling audio-visual learning without labels
A new multimodal technique blends major self-supervised learning methods to learn more similarly to humans.
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.