Method teaches generative AI models to locate personalized objects
After being trained with this technique, vision-language models can better identify a unique item in a new scene.
Topic
Computer Science and Artificial Intelligence Laboratory (CSAIL)
Download RSS feed: News Articles / In the Media / Audio
Using generative AI to diversify virtual training grounds for robots
New tool from MIT CSAIL creates realistic virtual kitchens and living rooms where simulated robots can interact with models of real-world objects, scaling up training data for robot foundation models.
AI maps how a new antibiotic targets gut bacteria
MIT CSAIL and McMaster researchers used a generative AI model to reveal how a narrow-spectrum antibiotic attacks disease-causing bacteria, speeding up a process that normally takes years.
System lets people personalize online social spaces while staying connected with others
By enabling users to easily create social apps that serve communities’ needs, the Graffiti framework aims to promote healthier online interactions.
Responding to the climate impact of generative AI
Explosive growth of AI data centers is expected to increase greenhouse gas emissions. Researchers are now seeking solutions to reduce these environmental harms.
New AI system could accelerate clinical research
By enabling rapid annotation of areas of interest in medical images, the tool can help scientists study new treatments or map disease progression.
By attracting the world’s sharpest talent, MIT helps keep the US a step ahead
MIT is a global community whose international engagement bestows benefits well beyond the Cambridge campus.
What does the future hold for generative AI?
At the inaugural MIT Generative AI Impact Consortium Symposium, researchers and business leaders discussed potential advancements centered on this powerful technology.
How to build AI scaling laws for efficient LLM training and budget maximization
MIT-IBM Watson AI Lab researchers have developed a universal guide for estimating how large language models will perform based on smaller models in the same family.
Machine-learning tool gives doctors a more detailed 3D picture of fetal health
MIT CSAIL researchers developed a tool that can model the shape and movements of fetuses in 3D, potentially assisting doctors in finding abnormalities and making diagnoses.
MIT software tool turns everyday objects into animated, eye-catching displays
The FabObscura system helps users design and print barrier-grid animations without electronics, and can help produce dynamic household, workplace, and artistic objects.
Alzheimer’s erodes brain cells’ control of gene expression, undermining function, cognition
Study of 3.5 million cells from more than 100 human brains finds Alzheimer’s progression — and resilience to disease — depends on preserving epigenomic stability.
A human-centered approach to data visualization
Balancing automation and agency, Associate Professor Arvind Satyanarayan develops interactive data visualizations that amplify human creativity and cognition.
A greener way to 3D print stronger stuff
MIT CSAIL researchers developed SustainaPrint, a system that reinforces only the weakest zones of eco-friendly 3D prints, achieving strong results with less plastic.
Soft materials hold onto “memories” of their past, for longer than previously thought
New findings could help manufacturers design gels, lotions, or even paving materials that last longer and perform more predictably.